/lib/python3.11/site-packages/torch/jit/_script.py:1491: FutureWarning: `torch.jit.script` is deprecated. Please switch to `torch.compile` or `torch.export`. warnings.warn( /lib/python3.11/site-packages/mujoco_warp/_src/io.py:713: UserWarning: MULTICCD is enabled, but the scene contains CCD pairs without multicontact support: [('CYLINDER', 'CYLINDER'), ('CYLINDER', 'BOX')]. At most 1 contact will be generated for these pairs. warnings.warn( Setting seed: 0 Warp 1.14.0 initialized: CUDA Toolkit 12.9, Driver 13.0 Devices: "cpu" : "x86_64" "cuda:0" : "NVIDIA GeForce RTX 5070 Ti" (15 GiB, sm_120, mempool enabled) Kernel cache: /1.14.0 Module mujoco_warp._src.smooth e597d07 load on device 'cuda:0' took 4.41 ms (cached) Module _nxn_broadphase__locals__kernel_df6640ed df6640e load on device 'cuda:0' took 0.98 ms (cached) Module ccd_kernel_builder__locals__ccd_kernel_f3c975b7 f3c975b load on device 'cuda:0' took 2.00 ms (cached) Module ccd_kernel_builder__locals__ccd_kernel_f3c975b7 fa59860 load on device 'cuda:0' took 2.13 ms (cached) Module ccd_kernel_builder__locals__ccd_kernel_82ff21e7 82ff21e load on device 'cuda:0' took 1.87 ms (cached) Module ccd_kernel_builder__locals__ccd_kernel_82ff21e7 fa618bd load on device 'cuda:0' took 1.87 ms (cached) Module ccd_kernel_builder__locals__ccd_kernel_240d51e8 240d51e load on device 'cuda:0' took 2.54 ms (cached) Module ccd_kernel_builder__locals__ccd_kernel_240d51e8 a5c9e1e load on device 'cuda:0' took 2.35 ms (cached) Module _primitive_narrowphase__locals__primitive_narrowphase_9aaa7d98 9aaa7d9 load on device 'cuda:0' took 0.91 ms (cached) Module mujoco_warp._src.constraint 880bd7f load on device 'cuda:0' took 0.70 ms (cached) Module _friction_dof__locals__kernel_3c14efda 3c14efd load on device 'cuda:0' took 2.07 ms (cached) Module _limit_slide_hinge__locals__kernel_4d6c55ab 4d6c55a load on device 'cuda:0' took 1.11 ms (cached) Module _efc_contact_init__locals__kernel_744a1fda 744a1fd load on device 'cuda:0' took 0.84 ms (cached) Module _efc_contact_jac_dense__locals__kernel_760e2e1a d6aba00 load on device 'cuda:0' took 0.80 ms (cached) Module _efc_contact_update__locals__kernel_c40b0799 c40b079 load on device 'cuda:0' took 1.10 ms (cached) Module mujoco_warp._src.forward 687ddb7 load on device 'cuda:0' took 1.62 ms (cached) Module mujoco_warp._src.passive 8ff6993 load on device 'cuda:0' took 1.62 ms (cached) Module mujoco_warp._src.forward 2190340 load on device 'cuda:0' took 1.60 ms (cached) Module _qfrc_smooth__locals__kernel_6eb3d958 6eb3d95 load on device 'cuda:0' took 0.76 ms (cached) Module mujoco_warp._src.support d1e71d9 load on device 'cuda:0' took 0.88 ms (cached) Module _tile_cholesky_factorize_solve_block__locals__kernel_b44bd18c 0966f64 load on device 'cuda:0' took 19.14 ms (cached) Module _solve_init_dof__locals__kernel_99a497d1 99a497d load on device 'cuda:0' took 0.81 ms (cached) Module mujoco_warp._src.solver 245b5b3 load on device 'cuda:0' took 2.01 ms (cached) Module _solve_init_jaref_kernel__locals__kernel_d620bcf9 d620bcf load on device 'cuda:0' took 0.74 ms (cached) Module mul_m_kernel__locals___mul_m_fd2186c4 fd2186c load on device 'cuda:0' took 0.90 ms (cached) Module _update_constraint_efc__locals__kernel_4af8f110 4af8f11 load on device 'cuda:0' took 0.74 ms (cached) Module _update_constraint_init_qfrc_constraint_dense__locals__kernel_391cb5b4 391cb5b load on device 'cuda:0' took 0.80 ms (cached) Module _update_gradient_zero_grad_dot__locals__kernel_cb780630 cb78063 load on device 'cuda:0' took 0.78 ms (cached) Module _update_gradient_grad__locals__kernel_0cbf4927 0cbf492 load on device 'cuda:0' took 0.69 ms (cached) Module _update_gradient_JTDAJ_dense_tiled__locals__kernel_5d6c5d76 c826079 load on device 'cuda:0' took 1.27 ms (cached) Module _update_gradient_cholesky__locals__kernel_b27fc0c0 f9b150c load on device 'cuda:0' took 19.42 ms (cached) Module _linesearch_iterative_kernel__locals__kernel_d3ea36af e1537a9 load on device 'cuda:0' took 1.25 ms (cached) Module mujoco_warp._src.sensor 42e0a24 load on device 'cuda:0' took 2.53 ms (cached) Module _contact_sort__locals__contact_sort_321f5f3e 33ea4e1 load on device 'cuda:0' took 0.99 ms (cached) Module mujoco_warp._src.derivative e770e28 load on device 'cuda:0' took 1.36 ms (cached) Module _next_time_builder__locals___next_time_95ad6d7a 95ad6d7 load on device 'cuda:0' took 0.98 ms (cached) Module reset_data__locals__reset_xfrc_applied_03030511 0303051 load on device 'cuda:0' took 0.69 ms (cached) Module reset_data__locals__reset_M_631075dd 631075d load on device 'cuda:0' took 0.90 ms (cached) Module reset_data__locals__reset_mocap_6513201c 6513201 load on device 'cuda:0' took 0.69 ms (cached) Module reset_data__locals__reset_contact_5c08f689 5c08f68 load on device 'cuda:0' took 0.78 ms (cached) Module reset_data__locals__reset_sleep_50b990da 50b990d load on device 'cuda:0' took 0.70 ms (cached) Module reset_data__locals__reset_nworld_69a10925 69a1092 load on device 'cuda:0' took 0.81 ms (cached) +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 4096 | | Environment device | cuda:0 | | Environment seed | 0 | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 2 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ +---------------------------------------+ | Active Event Terms in Mode: 'startup' | +-----------+---------------------------+ | Index | Name | +-----------+---------------------------+ | 0 | foot_friction | | 1 | encoder_bias | | 2 | base_com | +-----------+---------------------------+ +-----------------------------+ | Domain Randomization Fields | +-------+---------------------+ | Index | Field Name | +-------+---------------------+ | 0 | geom_friction | | 1 | body_ipos | | 2 | body_subtreemass | | 3 | dof_invweight0 | | 4 | body_invweight0 | | 5 | tendon_length0 | | 6 | tendon_invweight0 | | 7 | actuator_acc0 | +-------+---------------------+ Module repeat_array_kernel_4f67a4c3 711f54c load on device 'cuda:0' took 0.87 ms (cached) Module repeat_array_kernel_4f67a4c3 7224d07 load on device 'cuda:0' took 0.81 ms (cached) Module repeat_array_kernel_4f67a4c3 b2885b0 load on device 'cuda:0' took 0.73 ms (cached) [INFO] contains 1 active terms. +--------------------------------------+ | Active Command Terms | +-------+-------+----------------------+ | Index | Name | Type | +-------+-------+----------------------+ | 0 | twist | MixedVelocityCommand | +-------+-------+----------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 2 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ +------------------------------------------------------------+ | Active Observation Terms in Group: 'critic' (shape: (56,)) | +-----------+----------------------------------+-------------+ | Index | Name | Shape | +-----------+----------------------------------+-------------+ | 0 | base_ang_vel | (3,) | | 1 | projected_gravity | (3,) | | 2 | joint_pos | (12,) | | 3 | joint_vel | (12,) | | 4 | wheel_vel | (4,) | | 5 | actions | (16,) | | 6 | command | (3,) | | 7 | base_lin_vel | (3,) | +-----------+----------------------------------+-------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 11 active terms. +-----------------------------------------+ | Active Reward Terms | +-------+------------------------+--------+ | Index | Name | Weight | +-------+------------------------+--------+ | 0 | track_linear_velocity | 2.0 | | 1 | track_angular_velocity | 2.0 | | 2 | upright | 1.0 | | 3 | leg_posture | -0.4 | | 4 | standstill | -2.0 | | 5 | action_rate_l2 | -0.05 | | 6 | joint_torques_l2 | -2e-05 | | 7 | dof_pos_limits | -1.0 | | 8 | terminated | -20.0 | | 9 | unnecessary_wheel_lift | -0.2 | | 10 | rolling_leg_motion | -0.12 | +-------+------------------------+--------+ [INFO] contains 1 active terms. +-------------------------+ | Active Curriculum Terms | +-----------+-------------+ | Index | Name | +-----------+-------------+ | 0 | course | +-----------+-------------+ [INFO] contains 1 active terms. +-------------------------+ | Active Metrics Terms | +-------+-----------------+ | Index | Name | +-------+-----------------+ | 0 | mean_action_acc | +-------+-----------------+ [INFO] (inactive) Module mujoco_warp._src.io 19274fb load on device 'cuda:0' took 1.88 ms (cached) Module _tile_cholesky_factorize_block__locals__kernel_ccbdb7fb c86e457 load on device 'cuda:0' took 15.09 ms (cached) Module _tile_cholesky_solve_block__locals__kernel_320f9d39 639ca7f load on device 'cuda:0' took 15.19 ms (cached) Shared terrain atlas: 21.6 MiB S10 replay storage: 3344.0 MiB +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_020000.mp4 {"step": 20010, "actor_lr": 1.6326254762964657e-05, "archive_windows": 521, "env_steps": 20010, "total_transitions": 81960960, "num_steps_per_env": 1, "wm_loss": 0.21316659450531006, "actor_loss": null, "critic_loss": null, "reward": 0.06422033160924911, "falls": 0, "interval_steps": 10, "velocity_mae": [0.417668879032135, 0.1449698805809021, 0.3302408456802368], "policy_updates": 19950, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 6.111450314999985, "contact_bce": 0.22499379515647888, "contact_force_loss": 0.030082207173109055, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20020, "actor_lr": 1.6299886349978423e-05, "archive_windows": 1735, "env_steps": 20020, "total_transitions": 82001920, "num_steps_per_env": 1, "wm_loss": 0.19536051154136658, "actor_loss": null, "critic_loss": null, "reward": 0.0753982737660408, "falls": 0, "interval_steps": 10, "velocity_mae": [0.22319285571575165, 0.1280742585659027, 0.22749905288219452], "policy_updates": 19950, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 7.782994487999986, "contact_bce": 0.225437194108963, "contact_force_loss": 0.02602911740541458, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20030, "actor_lr": 1.627353394780695e-05, "archive_windows": 2620, "env_steps": 20030, "total_transitions": 82042880, "num_steps_per_env": 1, "wm_loss": 0.1846635341644287, "actor_loss": null, "critic_loss": null, "reward": 0.07840166985988617, "falls": 0, "interval_steps": 10, "velocity_mae": [0.1614307314157486, 0.113187275826931, 0.20591974258422852], "policy_updates": 19950, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 9.46057042999999, "contact_bce": 0.23175622522830963, "contact_force_loss": 0.024039845913648605, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20040, "actor_lr": 1.624719758534885e-05, "archive_windows": 3393, "env_steps": 20040, "total_transitions": 82083840, "num_steps_per_env": 1, "wm_loss": 0.18683867156505585, "actor_loss": null, "critic_loss": null, "reward": 0.0784832164645195, "falls": 0, "interval_steps": 10, "velocity_mae": [0.15102940797805786, 0.11057059466838837, 0.20834259688854218], "policy_updates": 19950, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 11.14265653199999, "contact_bce": 0.23354536294937134, "contact_force_loss": 0.024231363087892532, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20050, "actor_lr": 1.6220877291485223e-05, "archive_windows": 4082, "env_steps": 20050, "total_transitions": 82124800, "num_steps_per_env": 1, "wm_loss": 0.20950332283973694, "actor_loss": null, "critic_loss": null, "reward": 0.07697949558496475, "falls": 0, "interval_steps": 10, "velocity_mae": [0.16485223174095154, 0.11597958952188492, 0.2235407829284668], "policy_updates": 19950, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 12.821831344999993, "contact_bce": 0.23688700795173645, "contact_force_loss": 0.024115249514579773, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20060, "actor_lr": 1.619457309507945e-05, "archive_windows": 4773, "env_steps": 20060, "total_transitions": 82165760, "num_steps_per_env": 1, "wm_loss": 0.21756643056869507, "actor_loss": -9.057455062866211, "critic_loss": 0.01280834712088108, "reward": 0.07560659945011139, "falls": 0, "interval_steps": 10, "velocity_mae": [0.18705949187278748, 0.12627176940441132, 0.23328562080860138], "policy_updates": 19960, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 16.464764949, "contact_bce": 0.2409585863351822, "contact_force_loss": 0.024994414299726486, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20070, "actor_lr": 1.616828502497732e-05, "archive_windows": 5498, "env_steps": 20070, "total_transitions": 82206720, "num_steps_per_env": 1, "wm_loss": 0.2803006172180176, "actor_loss": -8.990995407104492, "critic_loss": 0.014726313762366772, "reward": 0.07512756437063217, "falls": 0, "interval_steps": 10, "velocity_mae": [0.200344517827034, 0.13332810997962952, 0.2382344901561737], "policy_updates": 19970, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 20.079112973999997, "contact_bce": 0.2511277198791504, "contact_force_loss": 0.025752782821655273, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20080, "actor_lr": 1.6142013110006935e-05, "archive_windows": 6153, "env_steps": 20080, "total_transitions": 82247680, "num_steps_per_env": 1, "wm_loss": 0.27878838777542114, "actor_loss": -9.04252815246582, "critic_loss": 0.010502624325454235, "reward": 0.07474604994058609, "falls": 2, "interval_steps": 10, "velocity_mae": [0.20661775767803192, 0.1401214301586151, 0.23693501949310303], "policy_updates": 19980, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 23.720109318999988, "contact_bce": 0.2587551474571228, "contact_force_loss": 0.026138199493288994, "terrain_level_mean": 2.728271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20090, "actor_lr": 1.611575737897867e-05, "archive_windows": 6869, "env_steps": 20090, "total_transitions": 82288640, "num_steps_per_env": 1, "wm_loss": 0.31620317697525024, "actor_loss": -8.975420951843262, "critic_loss": 0.0157699566334486, "reward": 0.07403380423784256, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2130427062511444, 0.1448594629764557, 0.2422793209552765], "policy_updates": 19990, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 27.33086057899999, "contact_bce": 0.2637094259262085, "contact_force_loss": 0.026140252128243446, "terrain_level_mean": 2.7275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20100, "actor_lr": 1.6089517860685155e-05, "archive_windows": 7556, "env_steps": 20100, "total_transitions": 82329600, "num_steps_per_env": 1, "wm_loss": 0.3817184269428253, "actor_loss": -8.974813461303711, "critic_loss": 0.018143460154533386, "reward": 0.0734577476978302, "falls": 8, "interval_steps": 10, "velocity_mae": [0.21991802752017975, 0.14883825182914734, 0.24526381492614746], "policy_updates": 20000, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 31.295185336999992, "contact_bce": 0.2706976532936096, "contact_force_loss": 0.027234762907028198, "terrain_level_mean": 2.7255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20110, "actor_lr": 1.606329458390123e-05, "archive_windows": 8278, "env_steps": 20110, "total_transitions": 82370560, "num_steps_per_env": 1, "wm_loss": 0.3724896311759949, "actor_loss": -8.911405563354492, "critic_loss": 0.01657923310995102, "reward": 0.07297036796808243, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22846822440624237, 0.15034064650535583, 0.25168880820274353], "policy_updates": 20010, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 34.91155469200001, "contact_bce": 0.28216612339019775, "contact_force_loss": 0.02814226597547531, "terrain_level_mean": 2.7236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20120, "actor_lr": 1.603708757738394e-05, "archive_windows": 9047, "env_steps": 20120, "total_transitions": 82411520, "num_steps_per_env": 1, "wm_loss": 0.4201374351978302, "actor_loss": -8.967427253723145, "critic_loss": 0.01597275398671627, "reward": 0.07247164845466614, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23569761216640472, 0.15076926350593567, 0.25620830059051514], "policy_updates": 20020, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 38.527099545, "contact_bce": 0.2857254445552826, "contact_force_loss": 0.028610169887542725, "terrain_level_mean": 2.72265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9988961219787598, 0.9982041120529175, 2.999654769897461]} {"step": 20130, "actor_lr": 1.601089686987246e-05, "archive_windows": 9810, "env_steps": 20130, "total_transitions": 82452480, "num_steps_per_env": 1, "wm_loss": 0.43961483240127563, "actor_loss": -8.955169677734375, "critic_loss": 0.012040413916110992, "reward": 0.07231596857309341, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2406766265630722, 0.15282852947711945, 0.25711604952812195], "policy_updates": 20030, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 42.14563279699999, "contact_bce": 0.2830177843570709, "contact_force_loss": 0.029214078560471535, "terrain_level_mean": 2.72021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9988961219787598, 0.9989525079727173, 2.999654769897461]} {"step": 20140, "actor_lr": 1.5984722490088147e-05, "archive_windows": 10597, "env_steps": 20140, "total_transitions": 82493440, "num_steps_per_env": 1, "wm_loss": 0.4376775622367859, "actor_loss": -8.935831069946289, "critic_loss": 0.0130216209217906, "reward": 0.07225389778614044, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24770057201385498, 0.1556074470281601, 0.2541804313659668], "policy_updates": 20040, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 45.76111179200001, "contact_bce": 0.2907693684101105, "contact_force_loss": 0.02944939211010933, "terrain_level_mean": 2.718994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9988961219787598, 0.9989525079727173, 2.999654769897461]} {"step": 20150, "actor_lr": 1.5958564466734397e-05, "archive_windows": 11358, "env_steps": 20150, "total_transitions": 82534400, "num_steps_per_env": 1, "wm_loss": 0.4178351163864136, "actor_loss": -8.932432174682617, "critic_loss": 0.014189422130584717, "reward": 0.07192934304475784, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2506665289402008, 0.15630458295345306, 0.25586122274398804], "policy_updates": 20050, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 49.386448707, "contact_bce": 0.29436543583869934, "contact_force_loss": 0.029052916914224625, "terrain_level_mean": 2.716552734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9988961219787598, 0.9989525079727173, 2.999654769897461]} {"step": 20160, "actor_lr": 1.59324228284967e-05, "archive_windows": 12155, "env_steps": 20160, "total_transitions": 82575360, "num_steps_per_env": 1, "wm_loss": 0.4807029068470001, "actor_loss": -8.959339141845703, "critic_loss": 0.012658168561756611, "reward": 0.07144229114055634, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2585383653640747, 0.16057495772838593, 0.26118841767311096], "policy_updates": 20060, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 53.032907607, "contact_bce": 0.2964911460876465, "contact_force_loss": 0.030690640211105347, "terrain_level_mean": 2.715576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9988961219787598, 0.9989525079727173, 2.999654769897461]} {"step": 20170, "actor_lr": 1.5906297604042558e-05, "archive_windows": 12942, "env_steps": 20170, "total_transitions": 82616320, "num_steps_per_env": 1, "wm_loss": 0.422037810087204, "actor_loss": -8.899922370910645, "critic_loss": 0.01653663069009781, "reward": 0.07008397579193115, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2683020830154419, 0.16641128063201904, 0.26708605885505676], "policy_updates": 20070, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 56.666123400000004, "contact_bce": 0.3015426993370056, "contact_force_loss": 0.030773865059018135, "terrain_level_mean": 2.7138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9988961219787598, 0.9989525079727173, 2.999654769897461]} {"step": 20180, "actor_lr": 1.5880188822021482e-05, "archive_windows": 13710, "env_steps": 20180, "total_transitions": 82657280, "num_steps_per_env": 1, "wm_loss": 0.490801066160202, "actor_loss": -8.905542373657227, "critic_loss": 0.018357930704951286, "reward": 0.06983760744333267, "falls": 9, "interval_steps": 10, "velocity_mae": [0.26517224311828613, 0.16562055051326752, 0.2638651728630066], "policy_updates": 20080, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 60.299191104000016, "contact_bce": 0.30281496047973633, "contact_force_loss": 0.031060725450515747, "terrain_level_mean": 2.714111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9988961219787598, 0.9989525079727173, 2.999654769897461]} {"step": 20190, "actor_lr": 1.5854096511064952e-05, "archive_windows": 14522, "env_steps": 20190, "total_transitions": 82698240, "num_steps_per_env": 1, "wm_loss": 0.444739431142807, "actor_loss": -8.901339530944824, "critic_loss": 0.015855705365538597, "reward": 0.06982763856649399, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2656906247138977, 0.16520698368549347, 0.2662159204483032], "policy_updates": 20090, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 63.92463059299999, "contact_bce": 0.2961570620536804, "contact_force_loss": 0.030809907242655754, "terrain_level_mean": 2.715576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9988961219787598, 0.9989525079727173, 2.999654769897461]} {"step": 20200, "actor_lr": 1.5828020699786396e-05, "archive_windows": 15355, "env_steps": 20200, "total_transitions": 82739200, "num_steps_per_env": 1, "wm_loss": 0.5488653779029846, "actor_loss": -8.886072158813477, "critic_loss": 0.023092936724424362, "reward": 0.06931746006011963, "falls": 14, "interval_steps": 10, "velocity_mae": [0.26749375462532043, 0.1646069586277008, 0.26746687293052673], "policy_updates": 20100, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 67.57022755400001, "contact_bce": 0.3066575825214386, "contact_force_loss": 0.03190036863088608, "terrain_level_mean": 2.71533203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.999654769897461]} {"step": 20210, "actor_lr": 1.5801961416781137e-05, "archive_windows": 16133, "env_steps": 20210, "total_transitions": 82780160, "num_steps_per_env": 1, "wm_loss": 0.5187259316444397, "actor_loss": -8.876380920410156, "critic_loss": 0.01820959709584713, "reward": 0.07001737505197525, "falls": 4, "interval_steps": 10, "velocity_mae": [0.26265662908554077, 0.16282321512699127, 0.26289308071136475], "policy_updates": 20110, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 71.22078624600002, "contact_bce": 0.30657804012298584, "contact_force_loss": 0.03086705692112446, "terrain_level_mean": 2.7177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.99847674369812]} {"step": 20220, "actor_lr": 1.5775918690626374e-05, "archive_windows": 16977, "env_steps": 20220, "total_transitions": 82821120, "num_steps_per_env": 1, "wm_loss": 0.4747474193572998, "actor_loss": -8.894522666931152, "critic_loss": 0.01740136556327343, "reward": 0.07020234316587448, "falls": 9, "interval_steps": 10, "velocity_mae": [0.26081979274749756, 0.15945591032505035, 0.2641312777996063], "policy_updates": 20120, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 74.85799576100001, "contact_bce": 0.3028484284877777, "contact_force_loss": 0.03160626068711281, "terrain_level_mean": 2.71826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.9945549964904785]} {"step": 20230, "actor_lr": 1.5749892549881143e-05, "archive_windows": 17850, "env_steps": 20230, "total_transitions": 82862080, "num_steps_per_env": 1, "wm_loss": 0.5235415101051331, "actor_loss": -8.901161193847656, "critic_loss": 0.016878044232726097, "reward": 0.0704292580485344, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2601412832736969, 0.1555035412311554, 0.2588614225387573], "policy_updates": 20130, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 78.508472265, "contact_bce": 0.3134968876838684, "contact_force_loss": 0.03234151005744934, "terrain_level_mean": 2.72021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.9945549964904785]} {"step": 20240, "actor_lr": 1.57238830230863e-05, "archive_windows": 18634, "env_steps": 20240, "total_transitions": 82903040, "num_steps_per_env": 1, "wm_loss": 0.48881345987319946, "actor_loss": -8.936317443847656, "critic_loss": 0.01874682866036892, "reward": 0.07085058838129044, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2516705393791199, 0.15401048958301544, 0.2584225535392761], "policy_updates": 20140, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 82.15095729700002, "contact_bce": 0.3063907325267792, "contact_force_loss": 0.030231747776269913, "terrain_level_mean": 2.720458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.9945549964904785]} {"step": 20250, "actor_lr": 1.5697890138764475e-05, "archive_windows": 19487, "env_steps": 20250, "total_transitions": 82944000, "num_steps_per_env": 1, "wm_loss": 0.49945828318595886, "actor_loss": -8.947500228881836, "critic_loss": 0.021812189370393753, "reward": 0.07065039128065109, "falls": 9, "interval_steps": 10, "velocity_mae": [0.25202298164367676, 0.1537422090768814, 0.2569741904735565], "policy_updates": 20150, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 85.79885032299998, "contact_bce": 0.31177571415901184, "contact_force_loss": 0.031594857573509216, "terrain_level_mean": 2.720947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.9945549964904785]} {"step": 20260, "actor_lr": 1.5671913925420063e-05, "archive_windows": 20327, "env_steps": 20260, "total_transitions": 82984960, "num_steps_per_env": 1, "wm_loss": 0.5154222249984741, "actor_loss": -8.924388885498047, "critic_loss": 0.029011815786361694, "reward": 0.07056206464767456, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2502436339855194, 0.15439651906490326, 0.2571103274822235], "policy_updates": 20160, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 89.44645666199997, "contact_bce": 0.30997878313064575, "contact_force_loss": 0.0313885435461998, "terrain_level_mean": 2.721923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.9945549964904785]} {"step": 20270, "actor_lr": 1.5645954411539177e-05, "archive_windows": 21160, "env_steps": 20270, "total_transitions": 83025920, "num_steps_per_env": 1, "wm_loss": 0.5401203036308289, "actor_loss": -8.886679649353027, "critic_loss": 0.017484677955508232, "reward": 0.07079588621854782, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24295108020305634, 0.15466952323913574, 0.2618218958377838], "policy_updates": 20170, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 93.084108713, "contact_bce": 0.31580740213394165, "contact_force_loss": 0.03187359496951103, "terrain_level_mean": 2.72216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9983863830566406, 0.9989525079727173, 2.9937686920166016]} {"step": 20280, "actor_lr": 1.562001162558957e-05, "archive_windows": 21971, "env_steps": 20280, "total_transitions": 83066880, "num_steps_per_env": 1, "wm_loss": 0.5081512331962585, "actor_loss": -8.926790237426758, "critic_loss": 0.017160655930638313, "reward": 0.07103772461414337, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24165941774845123, 0.15371987223625183, 0.26192885637283325], "policy_updates": 20180, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 96.72288085, "contact_bce": 0.3164902925491333, "contact_force_loss": 0.03249849006533623, "terrain_level_mean": 2.722900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9961992502212524, 0.9989525079727173, 2.9937686920166016]} {"step": 20290, "actor_lr": 1.5594085596020723e-05, "archive_windows": 22835, "env_steps": 20290, "total_transitions": 83107840, "num_steps_per_env": 1, "wm_loss": 0.4798016846179962, "actor_loss": -8.88565444946289, "critic_loss": 0.027235016226768494, "reward": 0.07127177715301514, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24048861861228943, 0.15129707753658295, 0.256902813911438], "policy_updates": 20190, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 100.36803894099998, "contact_bce": 0.31627583503723145, "contact_force_loss": 0.032015398144721985, "terrain_level_mean": 2.724853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9961992502212524, 0.9989525079727173, 2.9937686920166016]} {"step": 20300, "actor_lr": 1.556817635126369e-05, "archive_windows": 23711, "env_steps": 20300, "total_transitions": 83148800, "num_steps_per_env": 1, "wm_loss": 0.5021501779556274, "actor_loss": -8.887157440185547, "critic_loss": 0.020453637465834618, "reward": 0.07133927941322327, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24023805558681488, 0.1508645862340927, 0.25300514698028564], "policy_updates": 20200, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 103.99735664699998, "contact_bce": 0.31991904973983765, "contact_force_loss": 0.0331505611538887, "terrain_level_mean": 2.7255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9961992502212524, 0.9982041120529175, 2.9937686920166016]} {"step": 20310, "actor_lr": 1.5542283919731134e-05, "archive_windows": 24496, "env_steps": 20310, "total_transitions": 83189760, "num_steps_per_env": 1, "wm_loss": 0.4977363049983978, "actor_loss": -8.893183708190918, "critic_loss": 0.02102850191295147, "reward": 0.07148418575525284, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2404315322637558, 0.14868667721748352, 0.2583734691143036], "policy_updates": 20210, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 107.63341172300002, "contact_bce": 0.3121193051338196, "contact_force_loss": 0.03166814148426056, "terrain_level_mean": 2.7265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9961992502212524, 0.9982041120529175, 2.9937686920166016]} {"step": 20320, "actor_lr": 1.5516408329817287e-05, "archive_windows": 25335, "env_steps": 20320, "total_transitions": 83230720, "num_steps_per_env": 1, "wm_loss": 0.49709340929985046, "actor_loss": -8.887434005737305, "critic_loss": 0.02063555084168911, "reward": 0.07125557959079742, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2372574657201767, 0.15149927139282227, 0.2542833089828491], "policy_updates": 20220, "skipped_updates": 0, "invalid_env_resets": 0, "elapsed_s": 111.27815886599998, "contact_bce": 0.3157927989959717, "contact_force_loss": 0.03211825713515282, "terrain_level_mean": 2.72705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9961992502212524, 0.9982041120529175, 2.9937686920166016]} RECOVERY reset 1 invalid environments; first IDs=[1648] {"step": 20330, "actor_lr": 1.5490549609897926e-05, "archive_windows": 26121, "env_steps": 20330, "total_transitions": 83271680, "num_steps_per_env": 1, "wm_loss": 0.5176635384559631, "actor_loss": -8.891063690185547, "critic_loss": 0.018057528883218765, "reward": 0.0718487799167633, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23576247692108154, 0.15226875245571136, 0.25237539410591125], "policy_updates": 20230, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 114.914821042, "contact_bce": 0.3209988474845886, "contact_force_loss": 0.03217034786939621, "terrain_level_mean": 2.726806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9961992502212524, 0.9982041120529175, 2.9937686920166016]} {"step": 20340, "actor_lr": 1.5464707788330258e-05, "archive_windows": 26929, "env_steps": 20340, "total_transitions": 83312640, "num_steps_per_env": 1, "wm_loss": 0.49618470668792725, "actor_loss": -8.839014053344727, "critic_loss": 0.022981636226177216, "reward": 0.07167753577232361, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23254825174808502, 0.15199799835681915, 0.25847551226615906], "policy_updates": 20240, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 118.56096629800001, "contact_bce": 0.31471550464630127, "contact_force_loss": 0.03219623491168022, "terrain_level_mean": 2.72705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.999070644378662, 0.9986367225646973, 2.9937686920166016]} {"step": 20350, "actor_lr": 1.543888289345305e-05, "archive_windows": 27713, "env_steps": 20350, "total_transitions": 83353600, "num_steps_per_env": 1, "wm_loss": 0.5201985836029053, "actor_loss": -8.909246444702148, "critic_loss": 0.0151105597615242, "reward": 0.07132617384195328, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2342381477355957, 0.15368475019931793, 0.2589142918586731], "policy_updates": 20250, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 122.18753616000001, "contact_bce": 0.32041803002357483, "contact_force_loss": 0.03241537883877754, "terrain_level_mean": 2.7275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9993915557861328, 0.9996663331985474, 2.9937686920166016]} {"step": 20360, "actor_lr": 1.541307495358645e-05, "archive_windows": 28514, "env_steps": 20360, "total_transitions": 83394560, "num_steps_per_env": 1, "wm_loss": 0.4831741154193878, "actor_loss": -8.90880012512207, "critic_loss": 0.02507573924958706, "reward": 0.07104434072971344, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23945169150829315, 0.1553843915462494, 0.2597399652004242], "policy_updates": 20260, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 125.822572619, "contact_bce": 0.3133414089679718, "contact_force_loss": 0.031031973659992218, "terrain_level_mean": 2.728271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9993915557861328, 0.9996663331985474, 2.9937686920166016]} {"step": 20370, "actor_lr": 1.5387283997032017e-05, "archive_windows": 29321, "env_steps": 20370, "total_transitions": 83435520, "num_steps_per_env": 1, "wm_loss": 0.48280587792396545, "actor_loss": -8.885799407958984, "critic_loss": 0.021882103756070137, "reward": 0.07082582265138626, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24157674610614777, 0.1532992124557495, 0.26083895564079285], "policy_updates": 20270, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 129.45462507800002, "contact_bce": 0.3204534947872162, "contact_force_loss": 0.03179539740085602, "terrain_level_mean": 2.72900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9993915557861328, 0.9996663331985474, 2.9912312030792236]} {"step": 20380, "actor_lr": 1.536151005207274e-05, "archive_windows": 30172, "env_steps": 20380, "total_transitions": 83476480, "num_steps_per_env": 1, "wm_loss": 0.5082535147666931, "actor_loss": -8.917689323425293, "critic_loss": 0.016397221013903618, "reward": 0.07030773907899857, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24289628863334656, 0.15578196942806244, 0.26409992575645447], "policy_updates": 20280, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 133.11174586, "contact_bce": 0.31882354617118835, "contact_force_loss": 0.031880784779787064, "terrain_level_mean": 2.728759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9993915557861328, 0.9996663331985474, 2.9912312030792236]} {"step": 20390, "actor_lr": 1.5335753146972872e-05, "archive_windows": 30956, "env_steps": 20390, "total_transitions": 83517440, "num_steps_per_env": 1, "wm_loss": 0.5491940379142761, "actor_loss": -8.913360595703125, "critic_loss": 0.02308066003024578, "reward": 0.07056453078985214, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24208299815654755, 0.1595085710287094, 0.26285213232040405], "policy_updates": 20290, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 136.74602577, "contact_bce": 0.3173605501651764, "contact_force_loss": 0.03202463313937187, "terrain_level_mean": 2.728271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9993915557861328, 0.9996663331985474, 2.9912312030792236]} {"step": 20400, "actor_lr": 1.5310013309978005e-05, "archive_windows": 31790, "env_steps": 20400, "total_transitions": 83558400, "num_steps_per_env": 1, "wm_loss": 0.5413563251495361, "actor_loss": -8.865914344787598, "critic_loss": 0.029910428449511528, "reward": 0.07083175331354141, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23728284239768982, 0.1601022332906723, 0.2622118294239044], "policy_updates": 20300, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 140.38005666, "contact_bce": 0.31993281841278076, "contact_force_loss": 0.032918818295001984, "terrain_level_mean": 2.72900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9993915557861328, 0.9996663331985474, 2.9912312030792236]} {"step": 20410, "actor_lr": 1.5284290569315067e-05, "archive_windows": 32625, "env_steps": 20410, "total_transitions": 83599360, "num_steps_per_env": 1, "wm_loss": 0.5416064262390137, "actor_loss": -8.885963439941406, "critic_loss": 0.024319926276803017, "reward": 0.07140205055475235, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23288336396217346, 0.15516716241836548, 0.25730767846107483], "policy_updates": 20310, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 144.01522725599997, "contact_bce": 0.3212031126022339, "contact_force_loss": 0.033127252012491226, "terrain_level_mean": 2.730224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9993915557861328, 0.9996663331985474, 2.9912312030792236]} {"step": 20420, "actor_lr": 1.5258584953192176e-05, "archive_windows": 33427, "env_steps": 20420, "total_transitions": 83640320, "num_steps_per_env": 1, "wm_loss": 0.5479004979133606, "actor_loss": -8.856827735900879, "critic_loss": 0.026508400216698647, "reward": 0.07173769176006317, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23240666091442108, 0.15276044607162476, 0.25748899579048157], "policy_updates": 20320, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 147.91892348899998, "contact_bce": 0.3192119598388672, "contact_force_loss": 0.0320439338684082, "terrain_level_mean": 2.73046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20430, "actor_lr": 1.523289648979869e-05, "archive_windows": 34257, "env_steps": 20430, "total_transitions": 83681280, "num_steps_per_env": 1, "wm_loss": 0.509556233882904, "actor_loss": -8.92559814453125, "critic_loss": 0.01746884360909462, "reward": 0.07219571620225906, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22797037661075592, 0.1495041400194168, 0.25063443183898926], "policy_updates": 20330, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 151.55248254400001, "contact_bce": 0.32579320669174194, "contact_force_loss": 0.03248355910181999, "terrain_level_mean": 2.73095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20440, "actor_lr": 1.5207225207305169e-05, "archive_windows": 35057, "env_steps": 20440, "total_transitions": 83722240, "num_steps_per_env": 1, "wm_loss": 0.5153657793998718, "actor_loss": -8.875844955444336, "critic_loss": 0.029607487842440605, "reward": 0.07162848860025406, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2299848049879074, 0.15148290991783142, 0.2543506920337677], "policy_updates": 20340, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 155.184229176, "contact_bce": 0.32356470823287964, "contact_force_loss": 0.03291691839694977, "terrain_level_mean": 2.73046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20450, "actor_lr": 1.518157113386331e-05, "archive_windows": 35868, "env_steps": 20450, "total_transitions": 83763200, "num_steps_per_env": 1, "wm_loss": 0.5109527707099915, "actor_loss": -8.885784149169922, "critic_loss": 0.02391221933066845, "reward": 0.07151185721158981, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2327807992696762, 0.1542813777923584, 0.2553458511829376], "policy_updates": 20350, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 158.821059367, "contact_bce": 0.327139288187027, "contact_force_loss": 0.03274282440543175, "terrain_level_mean": 2.731689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20460, "actor_lr": 1.5155934297605947e-05, "archive_windows": 36703, "env_steps": 20460, "total_transitions": 83804160, "num_steps_per_env": 1, "wm_loss": 0.4732830226421356, "actor_loss": -8.8546781539917, "critic_loss": 0.02263110689818859, "reward": 0.07156828045845032, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23281313478946686, 0.15391695499420166, 0.25291168689727783], "policy_updates": 20360, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 162.449837858, "contact_bce": 0.3226947784423828, "contact_force_loss": 0.03191850334405899, "terrain_level_mean": 2.73095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20470, "actor_lr": 1.5130314726647029e-05, "archive_windows": 37503, "env_steps": 20470, "total_transitions": 83845120, "num_steps_per_env": 1, "wm_loss": 0.4967069923877716, "actor_loss": -8.903968811035156, "critic_loss": 0.021134953945875168, "reward": 0.07141182571649551, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23233726620674133, 0.15405918657779694, 0.2555443048477173], "policy_updates": 20370, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 166.086496847, "contact_bce": 0.31802383065223694, "contact_force_loss": 0.0326882041990757, "terrain_level_mean": 2.730224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20480, "actor_lr": 1.5104712449081558e-05, "archive_windows": 38283, "env_steps": 20480, "total_transitions": 83886080, "num_steps_per_env": 1, "wm_loss": 0.5516672730445862, "actor_loss": -8.888904571533203, "critic_loss": 0.02113981544971466, "reward": 0.0716964527964592, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23435407876968384, 0.15296311676502228, 0.24970193207263947], "policy_updates": 20380, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 169.72233583300002, "contact_bce": 0.323520302772522, "contact_force_loss": 0.03301769122481346, "terrain_level_mean": 2.729736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332275390625, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20490, "actor_lr": 1.507912749298556e-05, "archive_windows": 39130, "env_steps": 20490, "total_transitions": 83927040, "num_steps_per_env": 1, "wm_loss": 0.5358039140701294, "actor_loss": -8.841669082641602, "critic_loss": 0.02956961654126644, "reward": 0.07106556743383408, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2351238876581192, 0.15312042832374573, 0.2504640221595764], "policy_updates": 20390, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 173.36022922100003, "contact_bce": 0.3220764100551605, "contact_force_loss": 0.033248383551836014, "terrain_level_mean": 2.72998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20500, "actor_lr": 1.5053559886416077e-05, "archive_windows": 39920, "env_steps": 20500, "total_transitions": 83968000, "num_steps_per_env": 1, "wm_loss": 0.526951789855957, "actor_loss": -8.90504264831543, "critic_loss": 0.024722125381231308, "reward": 0.07065324485301971, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23091253638267517, 0.1548224240541458, 0.2501053512096405], "policy_updates": 20400, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 176.99764296700002, "contact_bce": 0.3247956335544586, "contact_force_loss": 0.033530112355947495, "terrain_level_mean": 2.730712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20510, "actor_lr": 1.5028009657411127e-05, "archive_windows": 40744, "env_steps": 20510, "total_transitions": 84008960, "num_steps_per_env": 1, "wm_loss": 0.5136014819145203, "actor_loss": -8.908472061157227, "critic_loss": 0.021266404539346695, "reward": 0.07087378948926926, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2305321991443634, 0.1551125943660736, 0.2586513161659241], "policy_updates": 20410, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 180.67032129100002, "contact_bce": 0.3245609402656555, "contact_force_loss": 0.033298734575510025, "terrain_level_mean": 2.731201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.9912312030792236]} {"step": 20520, "actor_lr": 1.5002476833989667e-05, "archive_windows": 41514, "env_steps": 20520, "total_transitions": 84049920, "num_steps_per_env": 1, "wm_loss": 0.5382612943649292, "actor_loss": -8.872085571289062, "critic_loss": 0.02392040565609932, "reward": 0.07091395556926727, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2327975332736969, 0.15496383607387543, 0.2578929364681244], "policy_updates": 20420, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 184.302645109, "contact_bce": 0.3303374946117401, "contact_force_loss": 0.03387288749217987, "terrain_level_mean": 2.731201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.998176097869873]} {"step": 20530, "actor_lr": 1.4976961444151562e-05, "archive_windows": 42322, "env_steps": 20530, "total_transitions": 84090880, "num_steps_per_env": 1, "wm_loss": 0.49397873878479004, "actor_loss": -8.844221115112305, "critic_loss": 0.03015669248998165, "reward": 0.07113903015851974, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23372714221477509, 0.15453070402145386, 0.2543467581272125], "policy_updates": 20430, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 187.946360134, "contact_bce": 0.3246585726737976, "contact_force_loss": 0.032186709344387054, "terrain_level_mean": 2.73095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.998176097869873]} {"step": 20540, "actor_lr": 1.4951463515877584e-05, "archive_windows": 43142, "env_steps": 20540, "total_transitions": 84131840, "num_steps_per_env": 1, "wm_loss": 0.5346823930740356, "actor_loss": -8.868982315063477, "critic_loss": 0.027940822765231133, "reward": 0.07137548178434372, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23495341837406158, 0.15697044134140015, 0.2544792592525482], "policy_updates": 20440, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 191.57881922700003, "contact_bce": 0.33002036809921265, "contact_force_loss": 0.032838188111782074, "terrain_level_mean": 2.731689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.998176097869873]} {"step": 20550, "actor_lr": 1.4925983077129337e-05, "archive_windows": 43949, "env_steps": 20550, "total_transitions": 84172800, "num_steps_per_env": 1, "wm_loss": 0.5573769211769104, "actor_loss": -8.892436981201172, "critic_loss": 0.02192465029656887, "reward": 0.07135357707738876, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23235049843788147, 0.15852230787277222, 0.2557736933231354], "policy_updates": 20450, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 195.221153602, "contact_bce": 0.3336174488067627, "contact_force_loss": 0.03393804281949997, "terrain_level_mean": 2.733642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9927513599395752, 0.9996663331985474, 2.998176097869873]} {"step": 20560, "actor_lr": 1.4900520155849216e-05, "archive_windows": 44803, "env_steps": 20560, "total_transitions": 84213760, "num_steps_per_env": 1, "wm_loss": 0.5311431288719177, "actor_loss": -8.87291145324707, "critic_loss": 0.029099101200699806, "reward": 0.07070165127515793, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2382446974515915, 0.1610242873430252, 0.259931355714798], "policy_updates": 20460, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 198.851185986, "contact_bce": 0.3279913365840912, "contact_force_loss": 0.0329323410987854, "terrain_level_mean": 2.735107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9976580142974854, 0.9986367225646973, 2.998176097869873]} {"step": 20570, "actor_lr": 1.4875074779960467e-05, "archive_windows": 45600, "env_steps": 20570, "total_transitions": 84254720, "num_steps_per_env": 1, "wm_loss": 0.5690380930900574, "actor_loss": -8.893030166625977, "critic_loss": 0.02246713824570179, "reward": 0.07085651159286499, "falls": 12, "interval_steps": 10, "velocity_mae": [0.23752056062221527, 0.16145384311676025, 0.25646185874938965], "policy_updates": 20470, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 202.48872141500001, "contact_bce": 0.32975250482559204, "contact_force_loss": 0.034315671771764755, "terrain_level_mean": 2.734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3310546875, "command_abs_max": [1.9976580142974854, 0.9986367225646973, 2.998176097869873]} {"step": 20580, "actor_lr": 1.4849646977367054e-05, "archive_windows": 46392, "env_steps": 20580, "total_transitions": 84295680, "num_steps_per_env": 1, "wm_loss": 0.5630894899368286, "actor_loss": -8.88929557800293, "critic_loss": 0.02227911353111267, "reward": 0.07140090316534042, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23001983761787415, 0.1573115885257721, 0.25429627299308777], "policy_updates": 20480, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 206.13837352800002, "contact_bce": 0.33811524510383606, "contact_force_loss": 0.032967716455459595, "terrain_level_mean": 2.73486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9976580142974854, 0.9986367225646973, 2.998176097869873]} {"step": 20590, "actor_lr": 1.482423677595367e-05, "archive_windows": 47225, "env_steps": 20590, "total_transitions": 84336640, "num_steps_per_env": 1, "wm_loss": 0.5795897841453552, "actor_loss": -8.872215270996094, "critic_loss": 0.022676806896924973, "reward": 0.07204216718673706, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2213304340839386, 0.1522057205438614, 0.2477608323097229], "policy_updates": 20490, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 209.779383717, "contact_bce": 0.33187946677207947, "contact_force_loss": 0.033899493515491486, "terrain_level_mean": 2.73583984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32763671875, "command_abs_max": [1.9976580142974854, 0.9986367225646973, 2.998176097869873]} {"step": 20600, "actor_lr": 1.4798844203585748e-05, "archive_windows": 48062, "env_steps": 20600, "total_transitions": 84377600, "num_steps_per_env": 1, "wm_loss": 0.5701911449432373, "actor_loss": -8.839168548583984, "critic_loss": 0.030801594257354736, "reward": 0.07216360419988632, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22238558530807495, 0.15455569326877594, 0.24843725562095642], "policy_updates": 20500, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 213.42470144299998, "contact_bce": 0.335065633058548, "contact_force_loss": 0.03372340276837349, "terrain_level_mean": 2.73681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326904296875, "command_abs_max": [1.9976580142974854, 0.9986367225646973, 2.998176097869873]} {"step": 20610, "actor_lr": 1.4773469288109324e-05, "archive_windows": 48879, "env_steps": 20610, "total_transitions": 84418560, "num_steps_per_env": 1, "wm_loss": 0.5448272824287415, "actor_loss": -8.874246597290039, "critic_loss": 0.025549083948135376, "reward": 0.07178949564695358, "falls": 6, "interval_steps": 10, "velocity_mae": [0.22450216114521027, 0.15629428625106812, 0.2532951831817627], "policy_updates": 20510, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 217.07480731400003, "contact_bce": 0.33521518111228943, "contact_force_loss": 0.03369029983878136, "terrain_level_mean": 2.738037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328369140625, "command_abs_max": [1.9976580142974854, 0.9986367225646973, 2.998176097869873]} {"step": 20620, "actor_lr": 1.4748112057351108e-05, "archive_windows": 49690, "env_steps": 20620, "total_transitions": 84459520, "num_steps_per_env": 1, "wm_loss": 0.5638167858123779, "actor_loss": -8.839868545532227, "critic_loss": 0.03618655726313591, "reward": 0.07200506329536438, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22348149120807648, 0.1529957503080368, 0.25260797142982483], "policy_updates": 20520, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 220.71320516, "contact_bce": 0.33398154377937317, "contact_force_loss": 0.03317359462380409, "terrain_level_mean": 2.7392578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32861328125, "command_abs_max": [1.9976580142974854, 0.9986367225646973, 2.998176097869873]} {"step": 20630, "actor_lr": 1.4722772539118428e-05, "archive_windows": 50491, "env_steps": 20630, "total_transitions": 84500480, "num_steps_per_env": 1, "wm_loss": 0.5178534388542175, "actor_loss": -8.86365032196045, "critic_loss": 0.028276801109313965, "reward": 0.07188745588064194, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22277341783046722, 0.1520538479089737, 0.251411110162735], "policy_updates": 20530, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 224.351786636, "contact_bce": 0.3334335386753082, "contact_force_loss": 0.03279569745063782, "terrain_level_mean": 2.740478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32861328125, "command_abs_max": [1.9976580142974854, 0.9975606799125671, 2.998176097869873]} {"step": 20640, "actor_lr": 1.4697450761199168e-05, "archive_windows": 51268, "env_steps": 20640, "total_transitions": 84541440, "num_steps_per_env": 1, "wm_loss": 0.5805236101150513, "actor_loss": -8.861307144165039, "critic_loss": 0.024968629702925682, "reward": 0.07208196073770523, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22456741333007812, 0.15020935237407684, 0.2500941753387451], "policy_updates": 20540, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 227.995017417, "contact_bce": 0.33219796419143677, "contact_force_loss": 0.033749934285879135, "terrain_level_mean": 2.7412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327880859375, "command_abs_max": [1.9976580142974854, 0.9975606799125671, 2.998176097869873]} {"step": 20650, "actor_lr": 1.4672146751361755e-05, "archive_windows": 52102, "env_steps": 20650, "total_transitions": 84582400, "num_steps_per_env": 1, "wm_loss": 0.5776737332344055, "actor_loss": -8.860262870788574, "critic_loss": 0.02243659645318985, "reward": 0.0718507319688797, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2241644263267517, 0.15204504132270813, 0.2514529824256897], "policy_updates": 20550, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 231.64760234500002, "contact_bce": 0.32856592535972595, "contact_force_loss": 0.033190835267305374, "terrain_level_mean": 2.740478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9976580142974854, 0.9975606799125671, 2.998176097869873]} {"step": 20660, "actor_lr": 1.4646860537355146e-05, "archive_windows": 52939, "env_steps": 20660, "total_transitions": 84623360, "num_steps_per_env": 1, "wm_loss": 0.5318315029144287, "actor_loss": -8.8295316696167, "critic_loss": 0.02484230510890484, "reward": 0.07234225422143936, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22415685653686523, 0.15110211074352264, 0.25448504090309143], "policy_updates": 20560, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 235.29527511900002, "contact_bce": 0.33840012550354004, "contact_force_loss": 0.03405255079269409, "terrain_level_mean": 2.74072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9976580142974854, 0.9975606799125671, 2.998176097869873]} {"step": 20670, "actor_lr": 1.4621592146908771e-05, "archive_windows": 53703, "env_steps": 20670, "total_transitions": 84664320, "num_steps_per_env": 1, "wm_loss": 0.5457022786140442, "actor_loss": -8.863727569580078, "critic_loss": 0.027636220678687096, "reward": 0.07178067415952682, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2287343293428421, 0.15165381133556366, 0.2522106170654297], "policy_updates": 20570, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 238.94101408999998, "contact_bce": 0.32884490489959717, "contact_force_loss": 0.033395979553461075, "terrain_level_mean": 2.74267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.995295524597168, 0.9975606799125671, 2.998176097869873]} {"step": 20680, "actor_lr": 1.4596341607732511e-05, "archive_windows": 54536, "env_steps": 20680, "total_transitions": 84705280, "num_steps_per_env": 1, "wm_loss": 0.553533673286438, "actor_loss": -8.887661933898926, "critic_loss": 0.02447059564292431, "reward": 0.07189571112394333, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22840121388435364, 0.1529480516910553, 0.24958370625972748], "policy_updates": 20580, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 242.59944216800002, "contact_bce": 0.32916459441185, "contact_force_loss": 0.032435934990644455, "terrain_level_mean": 2.74365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.995295524597168, 0.9975606799125671, 2.998176097869873]} {"step": 20690, "actor_lr": 1.4571108947516695e-05, "archive_windows": 55342, "env_steps": 20690, "total_transitions": 84746240, "num_steps_per_env": 1, "wm_loss": 0.5438496470451355, "actor_loss": -8.873544692993164, "critic_loss": 0.021855128929018974, "reward": 0.07197996228933334, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22868739068508148, 0.15239030122756958, 0.252842515707016], "policy_updates": 20590, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 246.517328966, "contact_bce": 0.3290179371833801, "contact_force_loss": 0.033443812280893326, "terrain_level_mean": 2.74365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.995295524597168, 0.9975606799125671, 2.9985318183898926]} {"step": 20700, "actor_lr": 1.454589419393202e-05, "archive_windows": 56164, "env_steps": 20700, "total_transitions": 84787200, "num_steps_per_env": 1, "wm_loss": 0.5646421909332275, "actor_loss": -8.903802871704102, "critic_loss": 0.028344709426164627, "reward": 0.0717194452881813, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22747333347797394, 0.15269224345684052, 0.2636420726776123], "policy_updates": 20600, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 250.182070562, "contact_bce": 0.33294084668159485, "contact_force_loss": 0.03376263752579689, "terrain_level_mean": 2.745361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.995295524597168, 0.9965275526046753, 2.9985318183898926]} {"step": 20710, "actor_lr": 1.4520697374629554e-05, "archive_windows": 56930, "env_steps": 20710, "total_transitions": 84828160, "num_steps_per_env": 1, "wm_loss": 0.5331267714500427, "actor_loss": -8.8886079788208, "critic_loss": 0.02342861331999302, "reward": 0.07107755541801453, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2335437387228012, 0.15353694558143616, 0.2576065957546234], "policy_updates": 20610, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 253.843356553, "contact_bce": 0.3343970775604248, "contact_force_loss": 0.033360108733177185, "terrain_level_mean": 2.747314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.995295524597168, 0.9965275526046753, 2.9985318183898926]} {"step": 20720, "actor_lr": 1.4495518517240701e-05, "archive_windows": 57741, "env_steps": 20720, "total_transitions": 84869120, "num_steps_per_env": 1, "wm_loss": 0.537726879119873, "actor_loss": -8.828386306762695, "critic_loss": 0.030789703130722046, "reward": 0.07128489762544632, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23096810281276703, 0.1536385715007782, 0.25720342993736267], "policy_updates": 20620, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 257.49297424400004, "contact_bce": 0.33338847756385803, "contact_force_loss": 0.0328868143260479, "terrain_level_mean": 2.749755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.995295524597168, 0.9965275526046753, 2.9985318183898926]} {"step": 20730, "actor_lr": 1.4470357649377162e-05, "archive_windows": 58521, "env_steps": 20730, "total_transitions": 84910080, "num_steps_per_env": 1, "wm_loss": 0.5560959577560425, "actor_loss": -8.914833068847656, "critic_loss": 0.020766792818903923, "reward": 0.07150836288928986, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22961755096912384, 0.1536211520433426, 0.2588646709918976], "policy_updates": 20630, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 261.133311467, "contact_bce": 0.33751776814460754, "contact_force_loss": 0.0337369330227375, "terrain_level_mean": 2.749755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.995295524597168, 0.9965275526046753, 2.9985318183898926]} {"step": 20740, "actor_lr": 1.4445214798630908e-05, "archive_windows": 59296, "env_steps": 20740, "total_transitions": 84951040, "num_steps_per_env": 1, "wm_loss": 0.5720176100730896, "actor_loss": -8.897618293762207, "critic_loss": 0.021890107542276382, "reward": 0.0715305283665657, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22626467049121857, 0.15206511318683624, 0.25565916299819946], "policy_updates": 20640, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 264.77530837200004, "contact_bce": 0.3333337903022766, "contact_force_loss": 0.03279547393321991, "terrain_level_mean": 2.75, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.995295524597168, 0.9965275526046753, 2.9985318183898926]} {"step": 20750, "actor_lr": 1.4420089992574174e-05, "archive_windows": 60079, "env_steps": 20750, "total_transitions": 84992000, "num_steps_per_env": 1, "wm_loss": 0.5300863981246948, "actor_loss": -8.865869522094727, "critic_loss": 0.02061714045703411, "reward": 0.07222498953342438, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2222108244895935, 0.15157802402973175, 0.2516171634197235], "policy_updates": 20650, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 268.412498048, "contact_bce": 0.3351120948791504, "contact_force_loss": 0.033611539751291275, "terrain_level_mean": 2.749755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9975144863128662, 0.9965275526046753, 2.9985318183898926]} {"step": 20760, "actor_lr": 1.4394983258759382e-05, "archive_windows": 60860, "env_steps": 20760, "total_transitions": 85032960, "num_steps_per_env": 1, "wm_loss": 0.4948042333126068, "actor_loss": -8.86375904083252, "critic_loss": 0.029142890125513077, "reward": 0.07209327816963196, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2202114462852478, 0.15313903987407684, 0.2577659785747528], "policy_updates": 20660, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 272.059278909, "contact_bce": 0.32581549882888794, "contact_force_loss": 0.03348659351468086, "terrain_level_mean": 2.750244140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9975144863128662, 0.9965275526046753, 2.9985318183898926]} {"step": 20770, "actor_lr": 1.4369894624719143e-05, "archive_windows": 61606, "env_steps": 20770, "total_transitions": 85073920, "num_steps_per_env": 1, "wm_loss": 0.532359778881073, "actor_loss": -8.90565013885498, "critic_loss": 0.02745475247502327, "reward": 0.07198354601860046, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22287148237228394, 0.1566437929868698, 0.25342443585395813], "policy_updates": 20670, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 275.703152575, "contact_bce": 0.33462750911712646, "contact_force_loss": 0.03318681940436363, "terrain_level_mean": 2.751220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9992175102233887, 0.9965275526046753, 2.9985318183898926]} {"step": 20780, "actor_lr": 1.4344824117966222e-05, "archive_windows": 62408, "env_steps": 20780, "total_transitions": 85114880, "num_steps_per_env": 1, "wm_loss": 0.5755343437194824, "actor_loss": -8.887818336486816, "critic_loss": 0.02653380110859871, "reward": 0.07162998616695404, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22662602365016937, 0.15681739151477814, 0.25418779253959656], "policy_updates": 20680, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 279.346569358, "contact_bce": 0.3306899964809418, "contact_force_loss": 0.03397750481963158, "terrain_level_mean": 2.752197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9992175102233887, 0.9965275526046753, 2.9985318183898926]} {"step": 20790, "actor_lr": 1.43197717659935e-05, "archive_windows": 63226, "env_steps": 20790, "total_transitions": 85155840, "num_steps_per_env": 1, "wm_loss": 0.5159899592399597, "actor_loss": -8.890323638916016, "critic_loss": 0.019920317456126213, "reward": 0.07142754644155502, "falls": 7, "interval_steps": 10, "velocity_mae": [0.22478334605693817, 0.15563750267028809, 0.2584210932254791], "policy_updates": 20690, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 283.02172110699996, "contact_bce": 0.33410224318504333, "contact_force_loss": 0.033141277730464935, "terrain_level_mean": 2.752685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9992175102233887, 0.9996832609176636, 2.9985318183898926]} {"step": 20800, "actor_lr": 1.4294737596273951e-05, "archive_windows": 64039, "env_steps": 20800, "total_transitions": 85196800, "num_steps_per_env": 1, "wm_loss": 0.5552870035171509, "actor_loss": -8.914379119873047, "critic_loss": 0.018299292773008347, "reward": 0.07175194472074509, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2266695648431778, 0.155012845993042, 0.2591148912906647], "policy_updates": 20700, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 286.66791129499995, "contact_bce": 0.32903409004211426, "contact_force_loss": 0.03360707312822342, "terrain_level_mean": 2.7529296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9992175102233887, 0.9996832609176636, 2.9985318183898926]} {"step": 20810, "actor_lr": 1.4269721636260619e-05, "archive_windows": 64797, "env_steps": 20810, "total_transitions": 85237760, "num_steps_per_env": 1, "wm_loss": 0.525821328163147, "actor_loss": -8.84520435333252, "critic_loss": 0.02693055383861065, "reward": 0.07156642526388168, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23058927059173584, 0.15537263453006744, 0.26010313630104065], "policy_updates": 20710, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 290.30282408899996, "contact_bce": 0.3360198140144348, "contact_force_loss": 0.034004271030426025, "terrain_level_mean": 2.753173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9992175102233887, 0.9996832609176636, 2.9913578033447266]} {"step": 20820, "actor_lr": 1.4244723913386582e-05, "archive_windows": 65553, "env_steps": 20820, "total_transitions": 85278720, "num_steps_per_env": 1, "wm_loss": 0.5348741412162781, "actor_loss": -8.854177474975586, "critic_loss": 0.03477264568209648, "reward": 0.07148494571447372, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2313949316740036, 0.15629535913467407, 0.2613389194011688], "policy_updates": 20720, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 293.944167022, "contact_bce": 0.32969146966934204, "contact_force_loss": 0.033546082675457, "terrain_level_mean": 2.752197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9992175102233887, 0.9996832609176636, 2.9913578033447266]} {"step": 20830, "actor_lr": 1.4219744455064874e-05, "archive_windows": 66325, "env_steps": 20830, "total_transitions": 85319680, "num_steps_per_env": 1, "wm_loss": 0.5495380759239197, "actor_loss": -8.883544921875, "critic_loss": 0.020853564143180847, "reward": 0.07159123569726944, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22851912677288055, 0.1557438224554062, 0.25990626215934753], "policy_updates": 20730, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 297.58447153400004, "contact_bce": 0.3360402286052704, "contact_force_loss": 0.033593952655792236, "terrain_level_mean": 2.754150390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9992175102233887, 0.9996832609176636, 2.9913578033447266]} {"step": 20840, "actor_lr": 1.4194783288688563e-05, "archive_windows": 67128, "env_steps": 20840, "total_transitions": 85360640, "num_steps_per_env": 1, "wm_loss": 0.5973169803619385, "actor_loss": -8.921333312988281, "critic_loss": 0.030879301950335503, "reward": 0.07078283280134201, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22909994423389435, 0.15482650697231293, 0.2650035619735718], "policy_updates": 20740, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 301.23608083, "contact_bce": 0.33699026703834534, "contact_force_loss": 0.0342053584754467, "terrain_level_mean": 2.754150390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9992175102233887, 0.9996832609176636, 2.9913578033447266]} {"step": 20850, "actor_lr": 1.4169840441630621e-05, "archive_windows": 67963, "env_steps": 20850, "total_transitions": 85401600, "num_steps_per_env": 1, "wm_loss": 0.5538063049316406, "actor_loss": -8.856929779052734, "critic_loss": 0.03170311450958252, "reward": 0.0709034651517868, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23298563063144684, 0.15348519384860992, 0.2624175250530243], "policy_updates": 20750, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 304.886972246, "contact_bce": 0.329399049282074, "contact_force_loss": 0.0326923206448555, "terrain_level_mean": 2.7548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9992175102233887, 0.9996832609176636, 2.9913578033447266]} {"step": 20860, "actor_lr": 1.4144915941243928e-05, "archive_windows": 68783, "env_steps": 20860, "total_transitions": 85442560, "num_steps_per_env": 1, "wm_loss": 0.5214372873306274, "actor_loss": -8.93066120147705, "critic_loss": 0.02871757559478283, "reward": 0.07135499268770218, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23201178014278412, 0.1561693698167801, 0.26222458481788635], "policy_updates": 20760, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 308.540187402, "contact_bce": 0.32735952734947205, "contact_force_loss": 0.032872769981622696, "terrain_level_mean": 2.7548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.99998140335083, 0.9996832609176636, 2.9913578033447266]} {"step": 20870, "actor_lr": 1.412000981486128e-05, "archive_windows": 69554, "env_steps": 20870, "total_transitions": 85483520, "num_steps_per_env": 1, "wm_loss": 0.5266097784042358, "actor_loss": -8.891014099121094, "critic_loss": 0.031918205320835114, "reward": 0.07163665443658829, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23141084611415863, 0.15524692833423615, 0.2583785057067871], "policy_updates": 20770, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 312.186872206, "contact_bce": 0.328831285238266, "contact_force_loss": 0.032554320991039276, "terrain_level_mean": 2.7548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.99998140335083, 0.9996832609176636, 2.9913578033447266]} {"step": 20880, "actor_lr": 1.4095122089795274e-05, "archive_windows": 70330, "env_steps": 20880, "total_transitions": 85524480, "num_steps_per_env": 1, "wm_loss": 0.5455704927444458, "actor_loss": -8.897222518920898, "critic_loss": 0.031239021569490433, "reward": 0.07171043008565903, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23101596534252167, 0.15487119555473328, 0.26208189129829407], "policy_updates": 20780, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 315.83298571, "contact_bce": 0.32820892333984375, "contact_force_loss": 0.03255346044898033, "terrain_level_mean": 2.7568359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.99998140335083, 0.9996832609176636, 2.9913578033447266]} {"step": 20890, "actor_lr": 1.4070252793338346e-05, "archive_windows": 71106, "env_steps": 20890, "total_transitions": 85565440, "num_steps_per_env": 1, "wm_loss": 0.5327157974243164, "actor_loss": -8.819917678833008, "critic_loss": 0.025195986032485962, "reward": 0.07177872210741043, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23050662875175476, 0.15349963307380676, 0.26278382539749146], "policy_updates": 20790, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 319.4770400069999, "contact_bce": 0.33126047253608704, "contact_force_loss": 0.03269817307591438, "terrain_level_mean": 2.7578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.99998140335083, 0.9996832609176636, 2.993083953857422]} {"step": 20900, "actor_lr": 1.4045401952762756e-05, "archive_windows": 71919, "env_steps": 20900, "total_transitions": 85606400, "num_steps_per_env": 1, "wm_loss": 0.5614390969276428, "actor_loss": -8.895137786865234, "critic_loss": 0.03153645992279053, "reward": 0.07164040207862854, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2307213544845581, 0.15482646226882935, 0.26025521755218506], "policy_updates": 20800, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 323.11216270399996, "contact_bce": 0.3328135013580322, "contact_force_loss": 0.03350471705198288, "terrain_level_mean": 2.758544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.99998140335083, 0.9996832609176636, 2.993083953857422]} {"step": 20910, "actor_lr": 1.402056959532048e-05, "archive_windows": 72667, "env_steps": 20910, "total_transitions": 85647360, "num_steps_per_env": 1, "wm_loss": 0.5299882292747498, "actor_loss": -8.912461280822754, "critic_loss": 0.020782966166734695, "reward": 0.07157836854457855, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2328455150127411, 0.15790627896785736, 0.25960174202919006], "policy_updates": 20810, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 327.013907969, "contact_bce": 0.33456680178642273, "contact_force_loss": 0.033300966024398804, "terrain_level_mean": 2.760498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.99998140335083, 0.9996832609176636, 2.993083953857422]} {"step": 20920, "actor_lr": 1.3995755748243253e-05, "archive_windows": 73522, "env_steps": 20920, "total_transitions": 85688320, "num_steps_per_env": 1, "wm_loss": 0.5204759836196899, "actor_loss": -8.922307014465332, "critic_loss": 0.01895521581172943, "reward": 0.07158732414245605, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23534591495990753, 0.1564994752407074, 0.2596805691719055], "policy_updates": 20820, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 330.6850976999999, "contact_bce": 0.3304448425769806, "contact_force_loss": 0.03275921195745468, "terrain_level_mean": 2.76123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.993083953857422]} {"step": 20930, "actor_lr": 1.3970960438742493e-05, "archive_windows": 74323, "env_steps": 20930, "total_transitions": 85729280, "num_steps_per_env": 1, "wm_loss": 0.5406056642532349, "actor_loss": -8.921857833862305, "critic_loss": 0.022984815761446953, "reward": 0.07178198546171188, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23434016108512878, 0.15609173476696014, 0.25601404905319214], "policy_updates": 20830, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 334.35391863099994, "contact_bce": 0.3301708400249481, "contact_force_loss": 0.03283372148871422, "terrain_level_mean": 2.761962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.993083953857422]} {"step": 20940, "actor_lr": 1.3946183694009299e-05, "archive_windows": 75109, "env_steps": 20940, "total_transitions": 85770240, "num_steps_per_env": 1, "wm_loss": 0.5347294807434082, "actor_loss": -8.851056098937988, "critic_loss": 0.025606751441955566, "reward": 0.0719214528799057, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23471221327781677, 0.15788815915584564, 0.25569841265678406], "policy_updates": 20840, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 338.023423041, "contact_bce": 0.3305518627166748, "contact_force_loss": 0.033300116658210754, "terrain_level_mean": 2.7626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.993083953857422]} {"step": 20950, "actor_lr": 1.3921425541214396e-05, "archive_windows": 75860, "env_steps": 20950, "total_transitions": 85811200, "num_steps_per_env": 1, "wm_loss": 0.5953439474105835, "actor_loss": -8.875543594360352, "critic_loss": 0.026975540444254875, "reward": 0.0722762942314148, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23271504044532776, 0.15751315653324127, 0.25475218892097473], "policy_updates": 20850, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 341.7043891569999, "contact_bce": 0.3379090428352356, "contact_force_loss": 0.03364301472902298, "terrain_level_mean": 2.762939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.9989349842071533]} {"step": 20960, "actor_lr": 1.3896686007508158e-05, "archive_windows": 76637, "env_steps": 20960, "total_transitions": 85852160, "num_steps_per_env": 1, "wm_loss": 0.5406078100204468, "actor_loss": -8.885740280151367, "critic_loss": 0.019068969413638115, "reward": 0.07222017645835876, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2308649867773056, 0.15540392696857452, 0.25576716661453247], "policy_updates": 20860, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 345.3397716669999, "contact_bce": 0.3346244692802429, "contact_force_loss": 0.03294502571225166, "terrain_level_mean": 2.763427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.9989349842071533]} {"step": 20970, "actor_lr": 1.387196512002051e-05, "archive_windows": 77450, "env_steps": 20970, "total_transitions": 85893120, "num_steps_per_env": 1, "wm_loss": 0.5319665670394897, "actor_loss": -8.879918098449707, "critic_loss": 0.027393175289034843, "reward": 0.07233162224292755, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22964218258857727, 0.15447837114334106, 0.25656402111053467], "policy_updates": 20870, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 348.98034495799993, "contact_bce": 0.3294711410999298, "contact_force_loss": 0.033051688224077225, "terrain_level_mean": 2.765869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.9989349842071533]} {"step": 20980, "actor_lr": 1.3847262905860928e-05, "archive_windows": 78266, "env_steps": 20980, "total_transitions": 85934080, "num_steps_per_env": 1, "wm_loss": 0.5726035833358765, "actor_loss": -8.854009628295898, "critic_loss": 0.034305423498153687, "reward": 0.07226629555225372, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23171915113925934, 0.15781381726264954, 0.25732138752937317], "policy_updates": 20880, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 352.62624591199994, "contact_bce": 0.3340250253677368, "contact_force_loss": 0.03375941887497902, "terrain_level_mean": 2.767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.9989349842071533]} {"step": 20990, "actor_lr": 1.3822579392118424e-05, "archive_windows": 79071, "env_steps": 20990, "total_transitions": 85975040, "num_steps_per_env": 1, "wm_loss": 0.5629273653030396, "actor_loss": -8.877115249633789, "critic_loss": 0.026828190311789513, "reward": 0.07176406681537628, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2338961958885193, 0.15740108489990234, 0.25955846905708313], "policy_updates": 20890, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 356.2724397679999, "contact_bce": 0.3298720121383667, "contact_force_loss": 0.03274047002196312, "terrain_level_mean": 2.76708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.9989349842071533]} {"step": 21000, "actor_lr": 1.3797914605861499e-05, "archive_windows": 79837, "env_steps": 21000, "total_transitions": 86016000, "num_steps_per_env": 1, "wm_loss": 0.5560855865478516, "actor_loss": -8.864612579345703, "critic_loss": 0.027641577646136284, "reward": 0.07186336070299149, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2323705404996872, 0.15492640435695648, 0.25614026188850403], "policy_updates": 20900, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 359.91342151699996, "contact_bce": 0.33090728521347046, "contact_force_loss": 0.03233855962753296, "terrain_level_mean": 2.767822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.9989349842071533]} {"step": 21010, "actor_lr": 1.3773268574138102e-05, "archive_windows": 80637, "env_steps": 21010, "total_transitions": 86056960, "num_steps_per_env": 1, "wm_loss": 0.5013642311096191, "actor_loss": -8.912515640258789, "critic_loss": 0.019536510109901428, "reward": 0.07136307656764984, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23403404653072357, 0.1547841578722, 0.2587934732437134], "policy_updates": 20910, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 363.5917194059999, "contact_bce": 0.32998019456863403, "contact_force_loss": 0.032399822026491165, "terrain_level_mean": 2.768798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.999307632446289, 0.9996832609176636, 2.9989349842071533]} {"step": 21020, "actor_lr": 1.3748641323975648e-05, "archive_windows": 81433, "env_steps": 21020, "total_transitions": 86097920, "num_steps_per_env": 1, "wm_loss": 0.5550487637519836, "actor_loss": -8.868518829345703, "critic_loss": 0.017065787687897682, "reward": 0.07116862386465073, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23804287612438202, 0.15658238530158997, 0.25830963253974915], "policy_updates": 20920, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 367.23342852099995, "contact_bce": 0.3246302604675293, "contact_force_loss": 0.03244486078619957, "terrain_level_mean": 2.76904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.999307632446289, 0.9977035522460938, 2.9989349842071533]} {"step": 21030, "actor_lr": 1.3724032882380928e-05, "archive_windows": 82208, "env_steps": 21030, "total_transitions": 86138880, "num_steps_per_env": 1, "wm_loss": 0.5076605677604675, "actor_loss": -8.876138687133789, "critic_loss": 0.026863453909754753, "reward": 0.0713343545794487, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23611687123775482, 0.1575220376253128, 0.2566489279270172], "policy_updates": 20930, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 370.8733848669999, "contact_bce": 0.32718443870544434, "contact_force_loss": 0.03263455629348755, "terrain_level_mean": 2.770263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.999307632446289, 0.9994723200798035, 2.9989349842071533]} {"step": 21040, "actor_lr": 1.3699443276340115e-05, "archive_windows": 83005, "env_steps": 21040, "total_transitions": 86179840, "num_steps_per_env": 1, "wm_loss": 0.535031795501709, "actor_loss": -8.916425704956055, "critic_loss": 0.02752085030078888, "reward": 0.07146888971328735, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2356065958738327, 0.15717622637748718, 0.26000484824180603], "policy_updates": 20940, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 374.514267205, "contact_bce": 0.33008918166160583, "contact_force_loss": 0.03307904675602913, "terrain_level_mean": 2.7705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.999307632446289, 0.9994723200798035, 2.9989349842071533]} {"step": 21050, "actor_lr": 1.3674872532818732e-05, "archive_windows": 83762, "env_steps": 21050, "total_transitions": 86220800, "num_steps_per_env": 1, "wm_loss": 0.5183672904968262, "actor_loss": -8.897477149963379, "critic_loss": 0.017675502225756645, "reward": 0.07130437344312668, "falls": 11, "interval_steps": 10, "velocity_mae": [0.2369190901517868, 0.15685537457466125, 0.260375440120697], "policy_updates": 20950, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 378.15457256499997, "contact_bce": 0.32990023493766785, "contact_force_loss": 0.03229445219039917, "terrain_level_mean": 2.76904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.999307632446289, 0.9994723200798035, 2.9989349842071533]} {"step": 21060, "actor_lr": 1.3650320678761602e-05, "archive_windows": 84517, "env_steps": 21060, "total_transitions": 86261760, "num_steps_per_env": 1, "wm_loss": 0.5357380509376526, "actor_loss": -8.908988952636719, "critic_loss": 0.03012237511575222, "reward": 0.07153638452291489, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23553134500980377, 0.15719270706176758, 0.25354719161987305], "policy_updates": 20960, "skipped_updates": 0, "invalid_env_resets": 1, "elapsed_s": 381.8293104449999, "contact_bce": 0.3289519250392914, "contact_force_loss": 0.0328635536134243, "terrain_level_mean": 2.770263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.999307632446289, 0.9994723200798035, 2.9989349842071533]} RECOVERY reset 1 invalid environments; first IDs=[577] {"step": 21070, "actor_lr": 1.362578774109284e-05, "archive_windows": 85301, "env_steps": 21070, "total_transitions": 86302720, "num_steps_per_env": 1, "wm_loss": 0.5566495656967163, "actor_loss": -8.816420555114746, "critic_loss": 0.02453920803964138, "reward": 0.07152704894542694, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2350657880306244, 0.1549389362335205, 0.2570214867591858], "policy_updates": 20970, "skipped_updates": 0, "invalid_env_resets": 2, "elapsed_s": 385.49489266599994, "contact_bce": 0.32956627011299133, "contact_force_loss": 0.0333578959107399, "terrain_level_mean": 2.77099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.999307632446289, 0.9994723200798035, 2.9989349842071533]} {"step": 21080, "actor_lr": 1.3601273746715836e-05, "archive_windows": 86051, "env_steps": 21080, "total_transitions": 86343680, "num_steps_per_env": 1, "wm_loss": 0.5563585758209229, "actor_loss": -8.891134262084961, "critic_loss": 0.01970819942653179, "reward": 0.07179733365774155, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23037543892860413, 0.15512551367282867, 0.251194566488266], "policy_updates": 20980, "skipped_updates": 0, "invalid_env_resets": 2, "elapsed_s": 389.138860389, "contact_bce": 0.33805304765701294, "contact_force_loss": 0.034375280141830444, "terrain_level_mean": 2.772216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9996614456176758, 0.9994723200798035, 2.9989349842071533]} {"step": 21090, "actor_lr": 1.3576778722513198e-05, "archive_windows": 86869, "env_steps": 21090, "total_transitions": 86384640, "num_steps_per_env": 1, "wm_loss": 0.5119759440422058, "actor_loss": -8.918561935424805, "critic_loss": 0.019167939200997353, "reward": 0.0713854655623436, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22813838720321655, 0.1552087515592575, 0.252625972032547], "policy_updates": 20990, "skipped_updates": 0, "invalid_env_resets": 2, "elapsed_s": 393.051166601, "contact_bce": 0.3332393765449524, "contact_force_loss": 0.03330165520310402, "terrain_level_mean": 2.77294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9996614456176758, 0.9994723200798035, 2.9989349842071533]} {"step": 21100, "actor_lr": 1.3552302695346683e-05, "archive_windows": 87711, "env_steps": 21100, "total_transitions": 86425600, "num_steps_per_env": 1, "wm_loss": 0.5464970469474792, "actor_loss": -8.830801963806152, "critic_loss": 0.027425527572631836, "reward": 0.07061658054590225, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22738686203956604, 0.15625721216201782, 0.2598826289176941], "policy_updates": 21000, "skipped_updates": 0, "invalid_env_resets": 2, "elapsed_s": 396.703133738, "contact_bce": 0.33740517497062683, "contact_force_loss": 0.033813588321208954, "terrain_level_mean": 2.7744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9996614456176758, 0.9994723200798035, 2.9989349842071533]} {"step": 21110, "actor_lr": 1.3527845692057296e-05, "archive_windows": 88476, "env_steps": 21110, "total_transitions": 86466560, "num_steps_per_env": 1, "wm_loss": 0.5239261388778687, "actor_loss": -8.885883331298828, "critic_loss": 0.024008503183722496, "reward": 0.07076356559991837, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2293895035982132, 0.15765324234962463, 0.26053881645202637], "policy_updates": 21010, "skipped_updates": 0, "invalid_env_resets": 2, "elapsed_s": 400.35535282399997, "contact_bce": 0.333150178194046, "contact_force_loss": 0.03246243670582771, "terrain_level_mean": 2.775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9996614456176758, 0.9994723200798035, 2.9989349842071533]} {"step": 21120, "actor_lr": 1.3503407739465124e-05, "archive_windows": 89306, "env_steps": 21120, "total_transitions": 86507520, "num_steps_per_env": 1, "wm_loss": 0.5446048378944397, "actor_loss": -8.92514419555664, "critic_loss": 0.02078297734260559, "reward": 0.0710592195391655, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23235410451889038, 0.15829600393772125, 0.2594645321369171], "policy_updates": 21020, "skipped_updates": 0, "invalid_env_resets": 2, "elapsed_s": 403.99264638499994, "contact_bce": 0.3347732126712799, "contact_force_loss": 0.033702243119478226, "terrain_level_mean": 2.77734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9996614456176758, 0.9994723200798035, 2.9989349842071533]} {"step": 21130, "actor_lr": 1.3478988864369367e-05, "archive_windows": 90120, "env_steps": 21130, "total_transitions": 86548480, "num_steps_per_env": 1, "wm_loss": 0.5313394665718079, "actor_loss": -8.843875885009766, "critic_loss": 0.026444166898727417, "reward": 0.0711321085691452, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23448653519153595, 0.15899382531642914, 0.2608078718185425], "policy_updates": 21030, "skipped_updates": 0, "invalid_env_resets": 2, "elapsed_s": 407.6431236899999, "contact_bce": 0.33328184485435486, "contact_force_loss": 0.03326185792684555, "terrain_level_mean": 2.776611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9998602867126465, 0.9994723200798035, 2.9989349842071533]} RECOVERY reset 1 invalid environments; first IDs=[1589] {"step": 21140, "actor_lr": 1.3454589093548353e-05, "archive_windows": 90921, "env_steps": 21140, "total_transitions": 86589440, "num_steps_per_env": 1, "wm_loss": 0.5658208131790161, "actor_loss": -8.851554870605469, "critic_loss": 0.027860721573233604, "reward": 0.0716879591345787, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23148375749588013, 0.1560477465391159, 0.25881078839302063], "policy_updates": 21040, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 411.32155279899996, "contact_bce": 0.34018152952194214, "contact_force_loss": 0.034929487854242325, "terrain_level_mean": 2.77783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9998602867126465, 0.9994723200798035, 2.9989349842071533]} {"step": 21150, "actor_lr": 1.3430208453759384e-05, "archive_windows": 91691, "env_steps": 21150, "total_transitions": 86630400, "num_steps_per_env": 1, "wm_loss": 0.5274661779403687, "actor_loss": -8.877544403076172, "critic_loss": 0.025788700208067894, "reward": 0.07187604159116745, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2289181500673294, 0.15476204454898834, 0.2581360936164856], "policy_updates": 21050, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 414.974637743, "contact_bce": 0.3333064913749695, "contact_force_loss": 0.032962020486593246, "terrain_level_mean": 2.777587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9998602867126465, 0.9994723200798035, 2.9989349842071533]} {"step": 21160, "actor_lr": 1.3405846971738823e-05, "archive_windows": 92473, "env_steps": 21160, "total_transitions": 86671360, "num_steps_per_env": 1, "wm_loss": 0.5383644700050354, "actor_loss": -8.886505126953125, "critic_loss": 0.025975359603762627, "reward": 0.07198809087276459, "falls": 6, "interval_steps": 10, "velocity_mae": [0.22573867440223694, 0.15684708952903748, 0.2559841573238373], "policy_updates": 21060, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 418.62600491499995, "contact_bce": 0.3305477797985077, "contact_force_loss": 0.033309709280729294, "terrain_level_mean": 2.77734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9998602867126465, 0.9994723200798035, 2.9989349842071533]} {"step": 21170, "actor_lr": 1.3381504674202046e-05, "archive_windows": 93230, "env_steps": 21170, "total_transitions": 86712320, "num_steps_per_env": 1, "wm_loss": 0.5388315916061401, "actor_loss": -8.867830276489258, "critic_loss": 0.024656204506754875, "reward": 0.07194028049707413, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22577409446239471, 0.16010400652885437, 0.2555527687072754], "policy_updates": 21070, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 422.2868972819999, "contact_bce": 0.33148273825645447, "contact_force_loss": 0.033520620316267014, "terrain_level_mean": 2.778076171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9998602867126465, 0.9994723200798035, 2.9989349842071533]} {"step": 21180, "actor_lr": 1.3357181587843355e-05, "archive_windows": 94035, "env_steps": 21180, "total_transitions": 86753280, "num_steps_per_env": 1, "wm_loss": 0.5488899946212769, "actor_loss": -8.876354217529297, "critic_loss": 0.017546243965625763, "reward": 0.07198549807071686, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22459906339645386, 0.15890543162822723, 0.2565288245677948], "policy_updates": 21080, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 425.92576520599994, "contact_bce": 0.32711338996887207, "contact_force_loss": 0.03249739855527878, "terrain_level_mean": 2.776611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9998602867126465, 0.9994723200798035, 2.9989349842071533]} {"step": 21190, "actor_lr": 1.3332877739335994e-05, "archive_windows": 94860, "env_steps": 21190, "total_transitions": 86794240, "num_steps_per_env": 1, "wm_loss": 0.5305717587471008, "actor_loss": -8.904138565063477, "critic_loss": 0.017070872709155083, "reward": 0.07219402492046356, "falls": 4, "interval_steps": 10, "velocity_mae": [0.222942516207695, 0.158734530210495, 0.25309526920318604], "policy_updates": 21090, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 429.56736789799993, "contact_bce": 0.3324010372161865, "contact_force_loss": 0.0332736000418663, "terrain_level_mean": 2.77783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9998602867126465, 0.9994723200798035, 2.9989349842071533]} {"step": 21200, "actor_lr": 1.3308593155332116e-05, "archive_windows": 95681, "env_steps": 21200, "total_transitions": 86835200, "num_steps_per_env": 1, "wm_loss": 0.54152512550354, "actor_loss": -8.915925979614258, "critic_loss": 0.020986616611480713, "reward": 0.07239746302366257, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22619928419589996, 0.1571238785982132, 0.2530358135700226], "policy_updates": 21100, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 433.2981402319999, "contact_bce": 0.3339599370956421, "contact_force_loss": 0.03372584655880928, "terrain_level_mean": 2.779541015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21210, "actor_lr": 1.3284327862462743e-05, "archive_windows": 96478, "env_steps": 21210, "total_transitions": 86876160, "num_steps_per_env": 1, "wm_loss": 0.5610643625259399, "actor_loss": -8.88254165649414, "critic_loss": 0.018234968185424805, "reward": 0.07208685576915741, "falls": 7, "interval_steps": 10, "velocity_mae": [0.22932061553001404, 0.1550757735967636, 0.2558586001396179], "policy_updates": 21110, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 436.95472884699996, "contact_bce": 0.3320311903953552, "contact_force_loss": 0.033744458109140396, "terrain_level_mean": 2.779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21220, "actor_lr": 1.3260081887337733e-05, "archive_windows": 97235, "env_steps": 21220, "total_transitions": 86917120, "num_steps_per_env": 1, "wm_loss": 0.5458952188491821, "actor_loss": -8.899128913879395, "critic_loss": 0.022727664560079575, "reward": 0.07233291119337082, "falls": 6, "interval_steps": 10, "velocity_mae": [0.22677741944789886, 0.15404349565505981, 0.25458166003227234], "policy_updates": 21120, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 440.606154639, "contact_bce": 0.33138567209243774, "contact_force_loss": 0.03382403030991554, "terrain_level_mean": 2.780517578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21230, "actor_lr": 1.3235855256545793e-05, "archive_windows": 98008, "env_steps": 21230, "total_transitions": 86958080, "num_steps_per_env": 1, "wm_loss": 0.5458086729049683, "actor_loss": -8.871831893920898, "critic_loss": 0.021476518362760544, "reward": 0.07264707237482071, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22412973642349243, 0.15492871403694153, 0.25264546275138855], "policy_updates": 21130, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 444.25234399299995, "contact_bce": 0.3315030336380005, "contact_force_loss": 0.0340203233063221, "terrain_level_mean": 2.782470703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21240, "actor_lr": 1.3211647996654383e-05, "archive_windows": 98801, "env_steps": 21240, "total_transitions": 86999040, "num_steps_per_env": 1, "wm_loss": 0.5021576881408691, "actor_loss": -8.87657356262207, "critic_loss": 0.017281442880630493, "reward": 0.07192157953977585, "falls": 1, "interval_steps": 10, "velocity_mae": [0.22971417009830475, 0.1581825613975525, 0.25481271743774414], "policy_updates": 21140, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 447.902779346, "contact_bce": 0.3295394480228424, "contact_force_loss": 0.032761815935373306, "terrain_level_mean": 2.78369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21250, "actor_lr": 1.3187460134209729e-05, "archive_windows": 99585, "env_steps": 21250, "total_transitions": 87040000, "num_steps_per_env": 1, "wm_loss": 0.4955585300922394, "actor_loss": -8.881940841674805, "critic_loss": 0.016727980226278305, "reward": 0.07155825197696686, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23357020318508148, 0.1563146561384201, 0.2539915144443512], "policy_updates": 21150, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 451.559783701, "contact_bce": 0.328403115272522, "contact_force_loss": 0.03279021009802818, "terrain_level_mean": 2.78466796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21260, "actor_lr": 1.3163291695736795e-05, "archive_windows": 100000, "env_steps": 21260, "total_transitions": 87080960, "num_steps_per_env": 1, "wm_loss": 0.531249463558197, "actor_loss": -8.882200241088867, "critic_loss": 0.023128289729356766, "reward": 0.07181818038225174, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2319166213274002, 0.15485528111457825, 0.25511622428894043], "policy_updates": 21160, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 455.4576641929999, "contact_bce": 0.3314351737499237, "contact_force_loss": 0.03329106420278549, "terrain_level_mean": 2.783935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21270, "actor_lr": 1.313914270773923e-05, "archive_windows": 100000, "env_steps": 21270, "total_transitions": 87121920, "num_steps_per_env": 1, "wm_loss": 0.519000768661499, "actor_loss": -8.86709213256836, "critic_loss": 0.018749991431832314, "reward": 0.07194449752569199, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23467737436294556, 0.15600882470607758, 0.2573528587818146], "policy_updates": 21170, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 459.13881878099994, "contact_bce": 0.3314141035079956, "contact_force_loss": 0.03267321735620499, "terrain_level_mean": 2.78662109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21280, "actor_lr": 1.3115013196699351e-05, "archive_windows": 100000, "env_steps": 21280, "total_transitions": 87162880, "num_steps_per_env": 1, "wm_loss": 0.5527426600456238, "actor_loss": -8.894525527954102, "critic_loss": 0.016397301107645035, "reward": 0.07215104252099991, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2345791906118393, 0.15712375938892365, 0.254368394613266], "policy_updates": 21180, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 462.78550629899996, "contact_bce": 0.33624765276908875, "contact_force_loss": 0.033901918679475784, "terrain_level_mean": 2.78759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21290, "actor_lr": 1.309090318907815e-05, "archive_windows": 100000, "env_steps": 21290, "total_transitions": 87203840, "num_steps_per_env": 1, "wm_loss": 0.5719232559204102, "actor_loss": -8.83342456817627, "critic_loss": 0.03032207489013672, "reward": 0.07237174361944199, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23049519956111908, 0.15466424822807312, 0.25424402952194214], "policy_updates": 21190, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 466.43330395499993, "contact_bce": 0.3309738337993622, "contact_force_loss": 0.033579759299755096, "terrain_level_mean": 2.786865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9998602867126465, 0.999568521976471, 2.9989349842071533]} {"step": 21300, "actor_lr": 1.3066812711315192e-05, "archive_windows": 100000, "env_steps": 21300, "total_transitions": 87244800, "num_steps_per_env": 1, "wm_loss": 0.5347087979316711, "actor_loss": -8.889644622802734, "critic_loss": 0.01846884749829769, "reward": 0.07244813442230225, "falls": 10, "interval_steps": 10, "velocity_mae": [0.22688278555870056, 0.15288181602954865, 0.25381794571876526], "policy_updates": 21200, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 470.0666927689999, "contact_bce": 0.3338138461112976, "contact_force_loss": 0.03293773904442787, "terrain_level_mean": 2.786376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9977344274520874, 0.999568521976471, 2.9989349842071533]} {"step": 21310, "actor_lr": 1.304274178982864e-05, "archive_windows": 100000, "env_steps": 21310, "total_transitions": 87285760, "num_steps_per_env": 1, "wm_loss": 0.566000759601593, "actor_loss": -8.88363265991211, "critic_loss": 0.02335088513791561, "reward": 0.07254207134246826, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2285870462656021, 0.15201041102409363, 0.2569209337234497], "policy_updates": 21210, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 473.735589127, "contact_bce": 0.33522704243659973, "contact_force_loss": 0.0333486869931221, "terrain_level_mean": 2.786865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9977344274520874, 0.999568521976471, 2.997490882873535]} {"step": 21320, "actor_lr": 1.3018690451015216e-05, "archive_windows": 100000, "env_steps": 21320, "total_transitions": 87326720, "num_steps_per_env": 1, "wm_loss": 0.5682674646377563, "actor_loss": -8.856090545654297, "critic_loss": 0.020066719502210617, "reward": 0.07248830050230026, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2292662262916565, 0.15876317024230957, 0.2561890780925751], "policy_updates": 21220, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 477.380007085, "contact_bce": 0.33343321084976196, "contact_force_loss": 0.034201111644506454, "terrain_level_mean": 2.78955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9977344274520874, 0.999568521976471, 2.9969630241394043]} {"step": 21330, "actor_lr": 1.2994658721250153e-05, "archive_windows": 100000, "env_steps": 21330, "total_transitions": 87367680, "num_steps_per_env": 1, "wm_loss": 0.5477072596549988, "actor_loss": -8.889375686645508, "critic_loss": 0.027779078111052513, "reward": 0.07240644097328186, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2268860936164856, 0.15850211679935455, 0.2522745728492737], "policy_updates": 21230, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 481.025431155, "contact_bce": 0.33596256375312805, "contact_force_loss": 0.033859387040138245, "terrain_level_mean": 2.7890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9977344274520874, 0.999568521976471, 2.9969630241394043]} {"step": 21340, "actor_lr": 1.2970646626887187e-05, "archive_windows": 100000, "env_steps": 21340, "total_transitions": 87408640, "num_steps_per_env": 1, "wm_loss": 0.5615872740745544, "actor_loss": -8.857925415039062, "critic_loss": 0.03115193359553814, "reward": 0.07212554663419724, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2270548790693283, 0.1534995287656784, 0.25603899359703064], "policy_updates": 21240, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 484.675831842, "contact_bce": 0.33261507749557495, "contact_force_loss": 0.033192362636327744, "terrain_level_mean": 2.788818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9977344274520874, 0.999568521976471, 2.9969630241394043]} {"step": 21350, "actor_lr": 1.2946654194258541e-05, "archive_windows": 100000, "env_steps": 21350, "total_transitions": 87449600, "num_steps_per_env": 1, "wm_loss": 0.538557767868042, "actor_loss": -8.919172286987305, "critic_loss": 0.023361360654234886, "reward": 0.07186514139175415, "falls": 6, "interval_steps": 10, "velocity_mae": [0.22977344691753387, 0.1539721041917801, 0.2559955418109894], "policy_updates": 21250, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 488.3130590349999, "contact_bce": 0.3342650234699249, "contact_force_loss": 0.03318455442786217, "terrain_level_mean": 2.789306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.9969630241394043]} {"step": 21360, "actor_lr": 1.292268144967486e-05, "archive_windows": 100000, "env_steps": 21360, "total_transitions": 87490560, "num_steps_per_env": 1, "wm_loss": 0.5703387260437012, "actor_loss": -8.880672454833984, "critic_loss": 0.023251784965395927, "reward": 0.07175769656896591, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2323039323091507, 0.15579774975776672, 0.25610849261283875], "policy_updates": 21260, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 491.96608835999996, "contact_bce": 0.3359465003013611, "contact_force_loss": 0.033966314047575, "terrain_level_mean": 2.789306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9999593496322632, 0.999568521976471, 2.9969630241394043]} {"step": 21370, "actor_lr": 1.2898728419425165e-05, "archive_windows": 100000, "env_steps": 21370, "total_transitions": 87531520, "num_steps_per_env": 1, "wm_loss": 0.5318605303764343, "actor_loss": -8.881832122802734, "critic_loss": 0.021668700501322746, "reward": 0.07190808653831482, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22960315644741058, 0.15535040199756622, 0.25379058718681335], "policy_updates": 21270, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 495.6168697439999, "contact_bce": 0.33000215888023376, "contact_force_loss": 0.033233992755413055, "terrain_level_mean": 2.79052734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.9969630241394043]} {"step": 21380, "actor_lr": 1.2874795129776922e-05, "archive_windows": 100000, "env_steps": 21380, "total_transitions": 87572480, "num_steps_per_env": 1, "wm_loss": 0.5386291742324829, "actor_loss": -8.87503433227539, "critic_loss": 0.028205901384353638, "reward": 0.07199755311012268, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22734706103801727, 0.1563023179769516, 0.2572210729122162], "policy_updates": 21280, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 499.399594201, "contact_bce": 0.3346194922924042, "contact_force_loss": 0.03291868045926094, "terrain_level_mean": 2.790771484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.9969630241394043]} {"step": 21390, "actor_lr": 1.2850881606975913e-05, "archive_windows": 100000, "env_steps": 21390, "total_transitions": 87613440, "num_steps_per_env": 1, "wm_loss": 0.5387280583381653, "actor_loss": -8.88525676727295, "critic_loss": 0.01990402676165104, "reward": 0.07180796563625336, "falls": 6, "interval_steps": 10, "velocity_mae": [0.22900860011577606, 0.1554940938949585, 0.2558332681655884], "policy_updates": 21290, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 503.300439879, "contact_bce": 0.3328379988670349, "contact_force_loss": 0.03264157101511955, "terrain_level_mean": 2.79150390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.9969630241394043]} {"step": 21400, "actor_lr": 1.2826987877246227e-05, "archive_windows": 100000, "env_steps": 21400, "total_transitions": 87654400, "num_steps_per_env": 1, "wm_loss": 0.5634863972663879, "actor_loss": -8.899078369140625, "critic_loss": 0.014705601148307323, "reward": 0.07203882187604904, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2314923256635666, 0.15685994923114777, 0.25648999214172363], "policy_updates": 21300, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 506.94161607499996, "contact_bce": 0.3384758234024048, "contact_force_loss": 0.03386407345533371, "terrain_level_mean": 2.792236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.9969630241394043]} {"step": 21410, "actor_lr": 1.2803113966790306e-05, "archive_windows": 100000, "env_steps": 21410, "total_transitions": 87695360, "num_steps_per_env": 1, "wm_loss": 0.5584518313407898, "actor_loss": -8.860447883605957, "critic_loss": 0.021263672038912773, "reward": 0.07173725217580795, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2309248149394989, 0.1564169079065323, 0.25346148014068604], "policy_updates": 21310, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 510.611621001, "contact_bce": 0.33436301350593567, "contact_force_loss": 0.033977970480918884, "terrain_level_mean": 2.791748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.9969630241394043]} {"step": 21420, "actor_lr": 1.2779259901788785e-05, "archive_windows": 100000, "env_steps": 21420, "total_transitions": 87736320, "num_steps_per_env": 1, "wm_loss": 0.5709508061408997, "actor_loss": -8.907510757446289, "critic_loss": 0.02580069936811924, "reward": 0.07122006267309189, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23137935996055603, 0.15549413859844208, 0.2548871636390686], "policy_updates": 21320, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 514.272565957, "contact_bce": 0.3375665545463562, "contact_force_loss": 0.0338188111782074, "terrain_level_mean": 2.792236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.999065637588501]} {"step": 21430, "actor_lr": 1.2755425708400578e-05, "archive_windows": 100000, "env_steps": 21430, "total_transitions": 87777280, "num_steps_per_env": 1, "wm_loss": 0.5699607133865356, "actor_loss": -8.897520065307617, "critic_loss": 0.015551879070699215, "reward": 0.07139294594526291, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2345597743988037, 0.1558064967393875, 0.25258612632751465], "policy_updates": 21330, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 517.9190266979999, "contact_bce": 0.3334132432937622, "contact_force_loss": 0.033607594668865204, "terrain_level_mean": 2.792724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.999065637588501]} {"step": 21440, "actor_lr": 1.2731611412762815e-05, "archive_windows": 100000, "env_steps": 21440, "total_transitions": 87818240, "num_steps_per_env": 1, "wm_loss": 0.5490900278091431, "actor_loss": -8.88014030456543, "critic_loss": 0.019344639033079147, "reward": 0.07154130190610886, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23492731153964996, 0.15544503927230835, 0.2574104964733124], "policy_updates": 21340, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 521.579198677, "contact_bce": 0.3381834924221039, "contact_force_loss": 0.03398527204990387, "terrain_level_mean": 2.79296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.999065637588501]} {"step": 21450, "actor_lr": 1.2707817040990783e-05, "archive_windows": 100000, "env_steps": 21450, "total_transitions": 87859200, "num_steps_per_env": 1, "wm_loss": 0.5991591811180115, "actor_loss": -8.902708053588867, "critic_loss": 0.018591750413179398, "reward": 0.0717206820845604, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23694278299808502, 0.15579672157764435, 0.2542620301246643], "policy_updates": 21350, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 525.22195713, "contact_bce": 0.3350621461868286, "contact_force_loss": 0.03331785649061203, "terrain_level_mean": 2.791748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.999065637588501]} {"step": 21460, "actor_lr": 1.2684042619177927e-05, "archive_windows": 100000, "env_steps": 21460, "total_transitions": 87900160, "num_steps_per_env": 1, "wm_loss": 0.5543981194496155, "actor_loss": -8.896175384521484, "critic_loss": 0.022134587168693542, "reward": 0.07173845916986465, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23535683751106262, 0.1563197821378708, 0.2524831295013428], "policy_updates": 21360, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 528.888802481, "contact_bce": 0.33256712555885315, "contact_force_loss": 0.033218804746866226, "terrain_level_mean": 2.79248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9993846416473389, 0.999568521976471, 2.999065637588501]} {"step": 21470, "actor_lr": 1.2660288173395817e-05, "archive_windows": 100000, "env_steps": 21470, "total_transitions": 87941120, "num_steps_per_env": 1, "wm_loss": 0.5752959251403809, "actor_loss": -8.880969047546387, "critic_loss": 0.022789645940065384, "reward": 0.07146824151277542, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2290741205215454, 0.156369149684906, 0.2565182149410248], "policy_updates": 21370, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 532.536839906, "contact_bce": 0.33496344089508057, "contact_force_loss": 0.033399298787117004, "terrain_level_mean": 2.792724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21480, "actor_lr": 1.2636553729694113e-05, "archive_windows": 100000, "env_steps": 21480, "total_transitions": 87982080, "num_steps_per_env": 1, "wm_loss": 0.5155776143074036, "actor_loss": -8.872072219848633, "critic_loss": 0.01819620095193386, "reward": 0.07151053845882416, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22791455686092377, 0.1557169258594513, 0.25514477491378784], "policy_updates": 21380, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 536.186634093, "contact_bce": 0.3313891589641571, "contact_force_loss": 0.032563596963882446, "terrain_level_mean": 2.795166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21490, "actor_lr": 1.2612839314100534e-05, "archive_windows": 100000, "env_steps": 21490, "total_transitions": 88023040, "num_steps_per_env": 1, "wm_loss": 0.5883919596672058, "actor_loss": -8.873113632202148, "critic_loss": 0.026067856699228287, "reward": 0.07157382369041443, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2322598397731781, 0.1567697376012802, 0.2531304359436035], "policy_updates": 21390, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 539.845537327, "contact_bce": 0.33701208233833313, "contact_force_loss": 0.03316731005907059, "terrain_level_mean": 2.796142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21500, "actor_lr": 1.2589144952620866e-05, "archive_windows": 100000, "env_steps": 21500, "total_transitions": 88064000, "num_steps_per_env": 1, "wm_loss": 0.5683601498603821, "actor_loss": -8.904672622680664, "critic_loss": 0.023731159046292305, "reward": 0.07224691659212112, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22582177817821503, 0.1571173369884491, 0.25116780400276184], "policy_updates": 21400, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 543.748295427, "contact_bce": 0.33382073044776917, "contact_force_loss": 0.03329971432685852, "terrain_level_mean": 2.79736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21510, "actor_lr": 1.2565470671238869e-05, "archive_windows": 100000, "env_steps": 21510, "total_transitions": 88104960, "num_steps_per_env": 1, "wm_loss": 0.529800534248352, "actor_loss": -8.835866928100586, "critic_loss": 0.03056470863521099, "reward": 0.07210264354944229, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22685155272483826, 0.15734995901584625, 0.2560846209526062], "policy_updates": 21410, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 547.433027219, "contact_bce": 0.33776208758354187, "contact_force_loss": 0.03336162865161896, "terrain_level_mean": 2.796142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21520, "actor_lr": 1.2541816495916298e-05, "archive_windows": 100000, "env_steps": 21520, "total_transitions": 88145920, "num_steps_per_env": 1, "wm_loss": 0.5188322067260742, "actor_loss": -8.89043140411377, "critic_loss": 0.018938515335321426, "reward": 0.07202555239200592, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22692042589187622, 0.16010743379592896, 0.25446996092796326], "policy_updates": 21420, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 551.094000973, "contact_bce": 0.32941603660583496, "contact_force_loss": 0.03270384296774864, "terrain_level_mean": 2.794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21530, "actor_lr": 1.2518182452592852e-05, "archive_windows": 100000, "env_steps": 21530, "total_transitions": 88186880, "num_steps_per_env": 1, "wm_loss": 0.5601910352706909, "actor_loss": -8.894646644592285, "critic_loss": 0.023808768019080162, "reward": 0.07215858995914459, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22868594527244568, 0.1582856923341751, 0.25511741638183594], "policy_updates": 21430, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 554.737039227, "contact_bce": 0.33931633830070496, "contact_force_loss": 0.03375081717967987, "terrain_level_mean": 2.796142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21540, "actor_lr": 1.2494568567186163e-05, "archive_windows": 100000, "env_steps": 21540, "total_transitions": 88227840, "num_steps_per_env": 1, "wm_loss": 0.5259016752243042, "actor_loss": -8.911666870117188, "critic_loss": 0.02556060627102852, "reward": 0.07210322469472885, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2314165234565735, 0.15404574573040009, 0.2526165544986725], "policy_updates": 21440, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 558.390233689, "contact_bce": 0.32671844959259033, "contact_force_loss": 0.03249329701066017, "terrain_level_mean": 2.795654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21550, "actor_lr": 1.2470974865591734e-05, "archive_windows": 100000, "env_steps": 21550, "total_transitions": 88268800, "num_steps_per_env": 1, "wm_loss": 0.5858179330825806, "actor_loss": -8.84000301361084, "critic_loss": 0.021012013778090477, "reward": 0.07221990823745728, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23141537606716156, 0.1522534340620041, 0.25256356596946716], "policy_updates": 21450, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 562.059296765, "contact_bce": 0.33712369203567505, "contact_force_loss": 0.03298439830541611, "terrain_level_mean": 2.79541015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21560, "actor_lr": 1.2447401373682982e-05, "archive_windows": 100000, "env_steps": 21560, "total_transitions": 88309760, "num_steps_per_env": 1, "wm_loss": 0.550948977470398, "actor_loss": -8.852739334106445, "critic_loss": 0.02008998394012451, "reward": 0.07192178815603256, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23425544798374176, 0.15362510085105896, 0.2582772374153137], "policy_updates": 21460, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 565.8517314119999, "contact_bce": 0.33642345666885376, "contact_force_loss": 0.03390408679842949, "terrain_level_mean": 2.7958984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21570, "actor_lr": 1.2423848117311113e-05, "archive_windows": 100000, "env_steps": 21570, "total_transitions": 88350720, "num_steps_per_env": 1, "wm_loss": 0.5649498105049133, "actor_loss": -8.91451644897461, "critic_loss": 0.018021468073129654, "reward": 0.07198385149240494, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23464182019233704, 0.15350864827632904, 0.2575594186782837], "policy_updates": 21470, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 569.601820462, "contact_bce": 0.3349539041519165, "contact_force_loss": 0.03328824043273926, "terrain_level_mean": 2.796630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21580, "actor_lr": 1.2400315122305162e-05, "archive_windows": 100000, "env_steps": 21580, "total_transitions": 88391680, "num_steps_per_env": 1, "wm_loss": 0.5638203620910645, "actor_loss": -8.897344589233398, "critic_loss": 0.021887365728616714, "reward": 0.07208916544914246, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23262952268123627, 0.15548017621040344, 0.2607984244823456], "policy_updates": 21480, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 573.30954672, "contact_bce": 0.3332577347755432, "contact_force_loss": 0.033660124987363815, "terrain_level_mean": 2.7978515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9993846416473389, 0.9997336864471436, 2.999065637588501]} {"step": 21590, "actor_lr": 1.2376802414471948e-05, "archive_windows": 100000, "env_steps": 21590, "total_transitions": 88432640, "num_steps_per_env": 1, "wm_loss": 0.5311277508735657, "actor_loss": -8.85825252532959, "critic_loss": 0.01972430758178234, "reward": 0.07168642431497574, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23161163926124573, 0.15896642208099365, 0.25782784819602966], "policy_updates": 21490, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 576.987175463, "contact_bce": 0.3272162973880768, "contact_force_loss": 0.03260607644915581, "terrain_level_mean": 2.799072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.9987282752990723, 0.9997336864471436, 2.999065637588501]} {"step": 21600, "actor_lr": 1.235331001959603e-05, "archive_windows": 100000, "env_steps": 21600, "total_transitions": 88473600, "num_steps_per_env": 1, "wm_loss": 0.5086336135864258, "actor_loss": -8.836373329162598, "critic_loss": 0.022330623120069504, "reward": 0.0717233419418335, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2291228324174881, 0.15900038182735443, 0.25903627276420593], "policy_updates": 21500, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 580.627108712, "contact_bce": 0.33004337549209595, "contact_force_loss": 0.03255768492817879, "terrain_level_mean": 2.799072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9987282752990723, 0.9997336864471436, 2.999065637588501]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_021600.mp4 {"step": 21610, "actor_lr": 1.2329837963439699e-05, "archive_windows": 100000, "env_steps": 21610, "total_transitions": 88514560, "num_steps_per_env": 1, "wm_loss": 0.5628160834312439, "actor_loss": -8.873734474182129, "critic_loss": 0.02615564502775669, "reward": 0.07175355404615402, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2274002730846405, 0.15823623538017273, 0.2587345242500305], "policy_updates": 21510, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 590.519293772, "contact_bce": 0.3336595296859741, "contact_force_loss": 0.03279820457100868, "terrain_level_mean": 2.79931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9987282752990723, 0.9997336864471436, 2.999065637588501]} {"step": 21620, "actor_lr": 1.2306386271742953e-05, "archive_windows": 100000, "env_steps": 21620, "total_transitions": 88555520, "num_steps_per_env": 1, "wm_loss": 0.5310230851173401, "actor_loss": -8.861393928527832, "critic_loss": 0.018781280145049095, "reward": 0.07207226008176804, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22726655006408691, 0.15849538147449493, 0.2567221522331238], "policy_updates": 21520, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 594.182324524, "contact_bce": 0.3350057601928711, "contact_force_loss": 0.033386196941137314, "terrain_level_mean": 2.79931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9987282752990723, 0.9997336864471436, 2.999065637588501]} {"step": 21630, "actor_lr": 1.2282954970223456e-05, "archive_windows": 100000, "env_steps": 21630, "total_transitions": 88596480, "num_steps_per_env": 1, "wm_loss": 0.5482732653617859, "actor_loss": -8.88211441040039, "critic_loss": 0.019464213401079178, "reward": 0.07201240211725235, "falls": 7, "interval_steps": 10, "velocity_mae": [0.22733327746391296, 0.15658354759216309, 0.25334087014198303], "policy_updates": 21530, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 597.8397082729999, "contact_bce": 0.3333629071712494, "contact_force_loss": 0.033775340765714645, "terrain_level_mean": 2.7998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9987282752990723, 0.9997336864471436, 2.999065637588501]} {"step": 21640, "actor_lr": 1.2259544084576469e-05, "archive_windows": 100000, "env_steps": 21640, "total_transitions": 88637440, "num_steps_per_env": 1, "wm_loss": 0.5209569334983826, "actor_loss": -8.883528709411621, "critic_loss": 0.03247375041246414, "reward": 0.07196949422359467, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23280613124370575, 0.15360602736473083, 0.2570902705192566], "policy_updates": 21540, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 601.497302794, "contact_bce": 0.32922127842903137, "contact_force_loss": 0.03282613679766655, "terrain_level_mean": 2.800048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} {"step": 21650, "actor_lr": 1.2236153640474927e-05, "archive_windows": 100000, "env_steps": 21650, "total_transitions": 88678400, "num_steps_per_env": 1, "wm_loss": 0.5298286080360413, "actor_loss": -8.903888702392578, "critic_loss": 0.020678207278251648, "reward": 0.07263272255659103, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22962668538093567, 0.15363934636116028, 0.2506537139415741], "policy_updates": 21550, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 605.174158524, "contact_bce": 0.337554931640625, "contact_force_loss": 0.033199165016412735, "terrain_level_mean": 2.801025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} {"step": 21660, "actor_lr": 1.221278366356931e-05, "archive_windows": 100000, "env_steps": 21660, "total_transitions": 88719360, "num_steps_per_env": 1, "wm_loss": 0.5142222046852112, "actor_loss": -8.872305870056152, "critic_loss": 0.028386278077960014, "reward": 0.07240374386310577, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23062114417552948, 0.15405984222888947, 0.2516022324562073], "policy_updates": 21560, "skipped_updates": 0, "invalid_env_resets": 3, "elapsed_s": 608.821514475, "contact_bce": 0.33556458353996277, "contact_force_loss": 0.03329916298389435, "terrain_level_mean": 2.802001953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} RECOVERY reset 1 invalid environments; first IDs=[1685] {"step": 21670, "actor_lr": 1.2189434179487652e-05, "archive_windows": 100000, "env_steps": 21670, "total_transitions": 88760320, "num_steps_per_env": 1, "wm_loss": 0.5857762098312378, "actor_loss": -8.895713806152344, "critic_loss": 0.02318284660577774, "reward": 0.07232024520635605, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22505871951580048, 0.1535046100616455, 0.2506532073020935], "policy_updates": 21570, "skipped_updates": 0, "invalid_env_resets": 4, "elapsed_s": 612.4893474979999, "contact_bce": 0.3330983519554138, "contact_force_loss": 0.0328836590051651, "terrain_level_mean": 2.80224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} {"step": 21680, "actor_lr": 1.2166105213835564e-05, "archive_windows": 100000, "env_steps": 21680, "total_transitions": 88801280, "num_steps_per_env": 1, "wm_loss": 0.5376907587051392, "actor_loss": -8.890924453735352, "critic_loss": 0.022548871114850044, "reward": 0.07178420573472977, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22925898432731628, 0.15377987921237946, 0.2540084421634674], "policy_updates": 21580, "skipped_updates": 0, "invalid_env_resets": 4, "elapsed_s": 616.153227995, "contact_bce": 0.3316681385040283, "contact_force_loss": 0.03316280245780945, "terrain_level_mean": 2.802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} {"step": 21690, "actor_lr": 1.2142796792196077e-05, "archive_windows": 100000, "env_steps": 21690, "total_transitions": 88842240, "num_steps_per_env": 1, "wm_loss": 0.5372653603553772, "actor_loss": -8.859346389770508, "critic_loss": 0.03750934451818466, "reward": 0.07226794958114624, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23254239559173584, 0.15332242846488953, 0.25154900550842285], "policy_updates": 21590, "skipped_updates": 0, "invalid_env_resets": 4, "elapsed_s": 619.800790916, "contact_bce": 0.3352418839931488, "contact_force_loss": 0.03259321302175522, "terrain_level_mean": 2.80224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} {"step": 21700, "actor_lr": 1.211950894012974e-05, "archive_windows": 100000, "env_steps": 21700, "total_transitions": 88883200, "num_steps_per_env": 1, "wm_loss": 0.5654330849647522, "actor_loss": -8.872261047363281, "critic_loss": 0.037054356187582016, "reward": 0.07233291864395142, "falls": 1, "interval_steps": 10, "velocity_mae": [0.22950434684753418, 0.15245582163333893, 0.25310662388801575], "policy_updates": 21600, "skipped_updates": 0, "invalid_env_resets": 4, "elapsed_s": 623.4957723829999, "contact_bce": 0.33027300238609314, "contact_force_loss": 0.03316507488489151, "terrain_level_mean": 2.802978515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} RECOVERY reset 1 invalid environments; first IDs=[576] {"step": 21710, "actor_lr": 1.2096241683174552e-05, "archive_windows": 100000, "env_steps": 21710, "total_transitions": 88924160, "num_steps_per_env": 1, "wm_loss": 0.549837052822113, "actor_loss": -8.877218246459961, "critic_loss": 0.031245721504092216, "reward": 0.07166367769241333, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23615117371082306, 0.15875226259231567, 0.2576974928379059], "policy_updates": 21610, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 627.1537842509999, "contact_bce": 0.3332163691520691, "contact_force_loss": 0.03316280245780945, "terrain_level_mean": 2.8037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9961209297180176, 0.9997336864471436, 2.999065637588501]} {"step": 21720, "actor_lr": 1.2072995046845908e-05, "archive_windows": 100000, "env_steps": 21720, "total_transitions": 88965120, "num_steps_per_env": 1, "wm_loss": 0.5606846809387207, "actor_loss": -8.839995384216309, "critic_loss": 0.020349446684122086, "reward": 0.07113970816135406, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23759151995182037, 0.16027595102787018, 0.25696849822998047], "policy_updates": 21620, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 630.818030731, "contact_bce": 0.3325553834438324, "contact_force_loss": 0.033534176647663116, "terrain_level_mean": 2.8046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.999065637588501]} {"step": 21730, "actor_lr": 1.2049769056636595e-05, "archive_windows": 100000, "env_steps": 21730, "total_transitions": 89006080, "num_steps_per_env": 1, "wm_loss": 0.5642165541648865, "actor_loss": -8.890876770019531, "critic_loss": 0.01310038287192583, "reward": 0.07076095789670944, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23608380556106567, 0.16057135164737701, 0.2562556862831116], "policy_updates": 21630, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 634.508326006, "contact_bce": 0.3375159800052643, "contact_force_loss": 0.03384460136294365, "terrain_level_mean": 2.8056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.999065637588501]} {"step": 21740, "actor_lr": 1.2026563738016754e-05, "archive_windows": 100000, "env_steps": 21740, "total_transitions": 89047040, "num_steps_per_env": 1, "wm_loss": 0.5760431289672852, "actor_loss": -8.866365432739258, "critic_loss": 0.027959246188402176, "reward": 0.07101654261350632, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23188842833042145, 0.1601221263408661, 0.2565266788005829], "policy_updates": 21640, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 638.151387, "contact_bce": 0.3366846740245819, "contact_force_loss": 0.033102404326200485, "terrain_level_mean": 2.804443359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.999065637588501]} {"step": 21750, "actor_lr": 1.2003379116433869e-05, "archive_windows": 100000, "env_steps": 21750, "total_transitions": 89088000, "num_steps_per_env": 1, "wm_loss": 0.5908821821212769, "actor_loss": -8.90226936340332, "critic_loss": 0.018310684710741043, "reward": 0.07158032059669495, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23113691806793213, 0.15844212472438812, 0.2569703161716461], "policy_updates": 21650, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 641.808397544, "contact_bce": 0.3300885856151581, "contact_force_loss": 0.0337524339556694, "terrain_level_mean": 2.81982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.9990296363830566]} {"step": 21760, "actor_lr": 1.1980215217312713e-05, "archive_windows": 100000, "env_steps": 21760, "total_transitions": 89128960, "num_steps_per_env": 1, "wm_loss": 0.532453715801239, "actor_loss": -8.87730598449707, "critic_loss": 0.01969965733587742, "reward": 0.0689215287566185, "falls": 3, "interval_steps": 10, "velocity_mae": [0.3112839460372925, 0.15226100385189056, 0.2773207426071167], "policy_updates": 21660, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 645.454407419, "contact_bce": 0.33446526527404785, "contact_force_loss": 0.032698243856430054, "terrain_level_mean": 2.8212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.9990296363830566]} {"step": 21770, "actor_lr": 1.1957072066055337e-05, "archive_windows": 100000, "env_steps": 21770, "total_transitions": 89169920, "num_steps_per_env": 1, "wm_loss": 0.5134503245353699, "actor_loss": -8.870817184448242, "critic_loss": 0.02477996051311493, "reward": 0.07362818717956543, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22453510761260986, 0.1469947248697281, 0.23999620974063873], "policy_updates": 21670, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 649.116596478, "contact_bce": 0.3319743275642395, "contact_force_loss": 0.032363876700401306, "terrain_level_mean": 2.822021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.9990296363830566]} {"step": 21780, "actor_lr": 1.1933949688041063e-05, "archive_windows": 100000, "env_steps": 21780, "total_transitions": 89210880, "num_steps_per_env": 1, "wm_loss": 0.5577218532562256, "actor_loss": -8.865870475769043, "critic_loss": 0.03403821587562561, "reward": 0.07433750480413437, "falls": 0, "interval_steps": 10, "velocity_mae": [0.20513689517974854, 0.1407684087753296, 0.23598788678646088], "policy_updates": 21680, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 652.7665979029999, "contact_bce": 0.3366091549396515, "contact_force_loss": 0.03314514830708504, "terrain_level_mean": 2.822509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.9990296363830566]} {"step": 21790, "actor_lr": 1.1910848108626403e-05, "archive_windows": 100000, "env_steps": 21790, "total_transitions": 89251840, "num_steps_per_env": 1, "wm_loss": 0.5208294987678528, "actor_loss": -8.874252319335938, "critic_loss": 0.02379022352397442, "reward": 0.07438083738088608, "falls": 3, "interval_steps": 10, "velocity_mae": [0.20169128477573395, 0.13747800886631012, 0.23562556505203247], "policy_updates": 21690, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 656.417809411, "contact_bce": 0.33327850699424744, "contact_force_loss": 0.0329802930355072, "terrain_level_mean": 2.82275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9977970123291016, 0.9997336864471436, 2.9990296363830566]} {"step": 21800, "actor_lr": 1.188776735314507e-05, "archive_windows": 100000, "env_steps": 21800, "total_transitions": 89292800, "num_steps_per_env": 1, "wm_loss": 0.5290259122848511, "actor_loss": -8.889764785766602, "critic_loss": 0.019711706787347794, "reward": 0.07376119494438171, "falls": 1, "interval_steps": 10, "velocity_mae": [0.20874030888080597, 0.14165042340755463, 0.24258509278297424], "policy_updates": 21700, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 660.0630442099999, "contact_bce": 0.3365541100502014, "contact_force_loss": 0.033076588064432144, "terrain_level_mean": 2.822998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9977970123291016, 0.9994989633560181, 2.9990296363830566]} {"step": 21810, "actor_lr": 1.1864707446907942e-05, "archive_windows": 100000, "env_steps": 21810, "total_transitions": 89333760, "num_steps_per_env": 1, "wm_loss": 0.5323041081428528, "actor_loss": -8.871671676635742, "critic_loss": 0.02242721989750862, "reward": 0.07313274592161179, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2237372100353241, 0.14701807498931885, 0.24658264219760895], "policy_updates": 21710, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 663.730104294, "contact_bce": 0.3335033357143402, "contact_force_loss": 0.033113498240709305, "terrain_level_mean": 2.822509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.9977970123291016, 0.9994989633560181, 2.9990296363830566]} {"step": 21820, "actor_lr": 1.1841668415203036e-05, "archive_windows": 100000, "env_steps": 21820, "total_transitions": 89374720, "num_steps_per_env": 1, "wm_loss": 0.5104513764381409, "actor_loss": -8.874114990234375, "critic_loss": 0.024297786876559258, "reward": 0.07271845638751984, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23197990655899048, 0.14943236112594604, 0.2493007481098175], "policy_updates": 21720, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 667.377795711, "contact_bce": 0.33126816153526306, "contact_force_loss": 0.03278558328747749, "terrain_level_mean": 2.82275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9977970123291016, 0.9994989633560181, 2.9990296363830566]} {"step": 21830, "actor_lr": 1.1818650283295464e-05, "archive_windows": 100000, "env_steps": 21830, "total_transitions": 89415680, "num_steps_per_env": 1, "wm_loss": 0.535104513168335, "actor_loss": -8.866674423217773, "critic_loss": 0.0211233701556921, "reward": 0.07258676737546921, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23202961683273315, 0.15233144164085388, 0.2481389045715332], "policy_updates": 21730, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 671.037185324, "contact_bce": 0.32846611738204956, "contact_force_loss": 0.03325808793306351, "terrain_level_mean": 2.82275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9977970123291016, 0.9994989633560181, 2.9990296363830566]} {"step": 21840, "actor_lr": 1.1795653076427454e-05, "archive_windows": 100000, "env_steps": 21840, "total_transitions": 89456640, "num_steps_per_env": 1, "wm_loss": 0.5398855805397034, "actor_loss": -8.882596969604492, "critic_loss": 0.028741730377078056, "reward": 0.07242544740438461, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23482751846313477, 0.15365928411483765, 0.24894626438617706], "policy_updates": 21740, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 674.69333906, "contact_bce": 0.32700616121292114, "contact_force_loss": 0.03249594569206238, "terrain_level_mean": 2.82275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9964065551757812, 0.9994989633560181, 2.9990296363830566]} {"step": 21850, "actor_lr": 1.1772676819818254e-05, "archive_windows": 100000, "env_steps": 21850, "total_transitions": 89497600, "num_steps_per_env": 1, "wm_loss": 0.5850735306739807, "actor_loss": -8.864212036132812, "critic_loss": 0.02176511660218239, "reward": 0.07234209030866623, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2360140085220337, 0.15592733025550842, 0.2524367868900299], "policy_updates": 21750, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 678.360745654, "contact_bce": 0.33102935552597046, "contact_force_loss": 0.033022891730070114, "terrain_level_mean": 2.822998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9964065551757812, 0.9994989633560181, 2.9990296363830566]} {"step": 21860, "actor_lr": 1.1749721538664124e-05, "archive_windows": 100000, "env_steps": 21860, "total_transitions": 89538560, "num_steps_per_env": 1, "wm_loss": 0.5245779156684875, "actor_loss": -8.890626907348633, "critic_loss": 0.02318522147834301, "reward": 0.07205652445554733, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23946721851825714, 0.15797151625156403, 0.2533247768878937], "policy_updates": 21760, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 682.0126411589999, "contact_bce": 0.33303070068359375, "contact_force_loss": 0.033160753548145294, "terrain_level_mean": 2.82275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9964065551757812, 0.9994989633560181, 2.9990296363830566]} {"step": 21870, "actor_lr": 1.1726787258138372e-05, "archive_windows": 100000, "env_steps": 21870, "total_transitions": 89579520, "num_steps_per_env": 1, "wm_loss": 0.5447075366973877, "actor_loss": -8.86706829071045, "critic_loss": 0.021464234218001366, "reward": 0.0718601867556572, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2461952418088913, 0.1605975478887558, 0.2527639865875244], "policy_updates": 21770, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 685.6702253249999, "contact_bce": 0.3326646387577057, "contact_force_loss": 0.033404603600502014, "terrain_level_mean": 2.822021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9979757070541382, 0.9994989633560181, 2.9990296363830566]} {"step": 21880, "actor_lr": 1.1703874003391237e-05, "archive_windows": 100000, "env_steps": 21880, "total_transitions": 89620480, "num_steps_per_env": 1, "wm_loss": 0.5464324355125427, "actor_loss": -8.807632446289062, "critic_loss": 0.02726762555539608, "reward": 0.07150088250637054, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2485618144273758, 0.15696461498737335, 0.2533155381679535], "policy_updates": 21780, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 689.3368357549999, "contact_bce": 0.3280502259731293, "contact_force_loss": 0.03204704076051712, "terrain_level_mean": 2.821044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9979757070541382, 0.9994989633560181, 2.9990296363830566]} {"step": 21890, "actor_lr": 1.1680981799549907e-05, "archive_windows": 100000, "env_steps": 21890, "total_transitions": 89661440, "num_steps_per_env": 1, "wm_loss": 0.5318174958229065, "actor_loss": -8.864479064941406, "critic_loss": 0.020446548238396645, "reward": 0.07114853709936142, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24955885112285614, 0.1567063182592392, 0.25525963306427], "policy_updates": 21790, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 692.9950223359999, "contact_bce": 0.327101469039917, "contact_force_loss": 0.03226959705352783, "terrain_level_mean": 2.82080078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9979757070541382, 0.9994989633560181, 2.9990296363830566]} {"step": 21900, "actor_lr": 1.1658110671718513e-05, "archive_windows": 100000, "env_steps": 21900, "total_transitions": 89702400, "num_steps_per_env": 1, "wm_loss": 0.5083205699920654, "actor_loss": -8.901264190673828, "critic_loss": 0.024074168875813484, "reward": 0.07085888087749481, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2518001198768616, 0.15698908269405365, 0.25887754559516907], "policy_updates": 21800, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 696.655363183, "contact_bce": 0.3232383131980896, "contact_force_loss": 0.03211250528693199, "terrain_level_mean": 2.820556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9979757070541382, 0.9994510412216187, 2.9990296363830566]} {"step": 21910, "actor_lr": 1.1635260644978028e-05, "archive_windows": 100000, "env_steps": 21910, "total_transitions": 89743360, "num_steps_per_env": 1, "wm_loss": 0.5464603900909424, "actor_loss": -8.861681938171387, "critic_loss": 0.020267615094780922, "reward": 0.07068441063165665, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25708988308906555, 0.15862004458904266, 0.25977063179016113], "policy_updates": 21810, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 700.323735966, "contact_bce": 0.3326137363910675, "contact_force_loss": 0.03410479798913002, "terrain_level_mean": 2.821044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9979757070541382, 0.9994510412216187, 2.9990296363830566]} {"step": 21920, "actor_lr": 1.1612431744386305e-05, "archive_windows": 100000, "env_steps": 21920, "total_transitions": 89784320, "num_steps_per_env": 1, "wm_loss": 0.60451740026474, "actor_loss": -8.902368545532227, "critic_loss": 0.021685432642698288, "reward": 0.07057295739650726, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25915369391441345, 0.16240276396274567, 0.2595714032649994], "policy_updates": 21820, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 703.972163834, "contact_bce": 0.33132898807525635, "contact_force_loss": 0.03398437052965164, "terrain_level_mean": 2.82177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9979757070541382, 0.9994510412216187, 2.9990296363830566]} {"step": 21930, "actor_lr": 1.158962399497805e-05, "archive_windows": 100000, "env_steps": 21930, "total_transitions": 89825280, "num_steps_per_env": 1, "wm_loss": 0.5445070266723633, "actor_loss": -8.886772155761719, "critic_loss": 0.020712334662675858, "reward": 0.07052723318338394, "falls": 3, "interval_steps": 10, "velocity_mae": [0.26035577058792114, 0.1619866043329239, 0.2632160186767578], "policy_updates": 21830, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 707.631225083, "contact_bce": 0.3269161283969879, "contact_force_loss": 0.032296087592840195, "terrain_level_mean": 2.822509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9979757070541382, 0.9994510412216187, 2.9990296363830566]} {"step": 21940, "actor_lr": 1.1566837421764752e-05, "archive_windows": 100000, "env_steps": 21940, "total_transitions": 89866240, "num_steps_per_env": 1, "wm_loss": 0.562393069267273, "actor_loss": -8.841584205627441, "critic_loss": 0.02434982918202877, "reward": 0.07009563595056534, "falls": 3, "interval_steps": 10, "velocity_mae": [0.26055535674095154, 0.16206561028957367, 0.26331475377082825], "policy_updates": 21840, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 711.283164222, "contact_bce": 0.333881676197052, "contact_force_loss": 0.033950500190258026, "terrain_level_mean": 2.8232421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 21950, "actor_lr": 1.154407204973468e-05, "archive_windows": 100000, "env_steps": 21950, "total_transitions": 89907200, "num_steps_per_env": 1, "wm_loss": 0.5800477266311646, "actor_loss": -8.866720199584961, "critic_loss": 0.01984008587896824, "reward": 0.07021667808294296, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2596413791179657, 0.16134141385555267, 0.26149171590805054], "policy_updates": 21850, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 714.938599867, "contact_bce": 0.33252307772636414, "contact_force_loss": 0.03340066969394684, "terrain_level_mean": 2.82421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 21960, "actor_lr": 1.1521327903852854e-05, "archive_windows": 100000, "env_steps": 21960, "total_transitions": 89948160, "num_steps_per_env": 1, "wm_loss": 0.5611996054649353, "actor_loss": -8.816308975219727, "critic_loss": 0.021946126595139503, "reward": 0.06986171752214432, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2605157792568207, 0.15939058363437653, 0.26049908995628357], "policy_updates": 21860, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 718.606216936, "contact_bce": 0.33213508129119873, "contact_force_loss": 0.033825021237134933, "terrain_level_mean": 2.824462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 21970, "actor_lr": 1.149860500906102e-05, "archive_windows": 100000, "env_steps": 21970, "total_transitions": 89989120, "num_steps_per_env": 1, "wm_loss": 0.5713237524032593, "actor_loss": -8.900917053222656, "critic_loss": 0.015477997250854969, "reward": 0.07017844915390015, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25808900594711304, 0.15755045413970947, 0.2618255913257599], "policy_updates": 21870, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 722.34219716, "contact_bce": 0.33121493458747864, "contact_force_loss": 0.03361763805150986, "terrain_level_mean": 2.824951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 21980, "actor_lr": 1.1475903390277611e-05, "archive_windows": 100000, "env_steps": 21980, "total_transitions": 90030080, "num_steps_per_env": 1, "wm_loss": 0.5197646021842957, "actor_loss": -8.802238464355469, "critic_loss": 0.036009881645441055, "reward": 0.07054178416728973, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2561125159263611, 0.15593740344047546, 0.2632330656051636], "policy_updates": 21880, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 726.104628261, "contact_bce": 0.32747820019721985, "contact_force_loss": 0.03223726898431778, "terrain_level_mean": 2.826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 21990, "actor_lr": 1.1453223072397751e-05, "archive_windows": 100000, "env_steps": 21990, "total_transitions": 90071040, "num_steps_per_env": 1, "wm_loss": 0.5702361464500427, "actor_loss": -8.859525680541992, "critic_loss": 0.01734243519604206, "reward": 0.07023745030164719, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24953065812587738, 0.15376564860343933, 0.26056867837905884], "policy_updates": 21890, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 729.846175613, "contact_bce": 0.33297455310821533, "contact_force_loss": 0.03406699001789093, "terrain_level_mean": 2.824462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 22000, "actor_lr": 1.1430564080293179e-05, "archive_windows": 100000, "env_steps": 22000, "total_transitions": 90112000, "num_steps_per_env": 1, "wm_loss": 0.5636152029037476, "actor_loss": -8.882015228271484, "critic_loss": 0.02536819316446781, "reward": 0.06990833580493927, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2511095106601715, 0.1574033498764038, 0.2620786726474762], "policy_updates": 21900, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 733.555296862, "contact_bce": 0.3311384916305542, "contact_force_loss": 0.03332780301570892, "terrain_level_mean": 2.8251953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 22010, "actor_lr": 1.1407926438812263e-05, "archive_windows": 100000, "env_steps": 22010, "total_transitions": 90152960, "num_steps_per_env": 1, "wm_loss": 0.5339162349700928, "actor_loss": -8.91162109375, "critic_loss": 0.015214427374303341, "reward": 0.07009526342153549, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2490663081407547, 0.15886512398719788, 0.2597792148590088], "policy_updates": 21910, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 737.344585791, "contact_bce": 0.3397018611431122, "contact_force_loss": 0.03342529386281967, "terrain_level_mean": 2.825439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9979757070541382, 0.9993426203727722, 2.9996814727783203]} {"step": 22020, "actor_lr": 1.1385310172779949e-05, "archive_windows": 100000, "env_steps": 22020, "total_transitions": 90193920, "num_steps_per_env": 1, "wm_loss": 0.5751631855964661, "actor_loss": -8.878061294555664, "critic_loss": 0.023572534322738647, "reward": 0.07035839557647705, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24684196710586548, 0.15783467888832092, 0.2587893605232239], "policy_updates": 21920, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 740.999483777, "contact_bce": 0.33845990896224976, "contact_force_loss": 0.034093305468559265, "terrain_level_mean": 2.825439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9995687007904053, 0.9993426203727722, 2.9996814727783203]} {"step": 22030, "actor_lr": 1.1362715306997745e-05, "archive_windows": 100000, "env_steps": 22030, "total_transitions": 90234880, "num_steps_per_env": 1, "wm_loss": 0.550550639629364, "actor_loss": -8.873299598693848, "critic_loss": 0.01860344596207142, "reward": 0.0699751228094101, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24459268152713776, 0.15981319546699524, 0.26159167289733887], "policy_updates": 21930, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 744.65034444, "contact_bce": 0.33005067706108093, "contact_force_loss": 0.03378058597445488, "terrain_level_mean": 2.825439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22040, "actor_lr": 1.1340141866243687e-05, "archive_windows": 100000, "env_steps": 22040, "total_transitions": 90275840, "num_steps_per_env": 1, "wm_loss": 0.5551465749740601, "actor_loss": -8.910379409790039, "critic_loss": 0.02171088568866253, "reward": 0.07049906253814697, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24207797646522522, 0.16000770032405853, 0.25698521733283997], "policy_updates": 21940, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 748.542916316, "contact_bce": 0.33464300632476807, "contact_force_loss": 0.03324221819639206, "terrain_level_mean": 2.825439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22050, "actor_lr": 1.1317589875272334e-05, "archive_windows": 100000, "env_steps": 22050, "total_transitions": 90316800, "num_steps_per_env": 1, "wm_loss": 0.5477944016456604, "actor_loss": -8.839479446411133, "critic_loss": 0.031046194955706596, "reward": 0.07085108011960983, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23803101480007172, 0.15794320404529572, 0.25812801718711853], "policy_updates": 21950, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 752.073093346, "contact_bce": 0.3299976885318756, "contact_force_loss": 0.032579220831394196, "terrain_level_mean": 2.824951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22060, "actor_lr": 1.1295059358814702e-05, "archive_windows": 100000, "env_steps": 22060, "total_transitions": 90357760, "num_steps_per_env": 1, "wm_loss": 0.508902370929718, "actor_loss": -8.857772827148438, "critic_loss": 0.02920401655137539, "reward": 0.07084952294826508, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24078430235385895, 0.15677016973495483, 0.25994017720222473], "policy_updates": 21960, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 755.599601677, "contact_bce": 0.329578697681427, "contact_force_loss": 0.03293028846383095, "terrain_level_mean": 2.824462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22070, "actor_lr": 1.1272550341578266e-05, "archive_windows": 100000, "env_steps": 22070, "total_transitions": 90398720, "num_steps_per_env": 1, "wm_loss": 0.5184822082519531, "actor_loss": -8.851177215576172, "critic_loss": 0.01899108849465847, "reward": 0.0709749087691307, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24200639128684998, 0.15579815208911896, 0.2606324553489685], "policy_updates": 21970, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 759.1293252759999, "contact_bce": 0.3351772129535675, "contact_force_loss": 0.034154731780290604, "terrain_level_mean": 2.824951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22080, "actor_lr": 1.125006284824692e-05, "archive_windows": 100000, "env_steps": 22080, "total_transitions": 90439680, "num_steps_per_env": 1, "wm_loss": 0.5748890042304993, "actor_loss": -8.859079360961914, "critic_loss": 0.02686269022524357, "reward": 0.0714125782251358, "falls": 3, "interval_steps": 10, "velocity_mae": [0.241456538438797, 0.15375171601772308, 0.253434419631958], "policy_updates": 21980, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 762.6543163389999, "contact_bce": 0.33028820157051086, "contact_force_loss": 0.03423042595386505, "terrain_level_mean": 2.825439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22090, "actor_lr": 1.1227596903480962e-05, "archive_windows": 100000, "env_steps": 22090, "total_transitions": 90480640, "num_steps_per_env": 1, "wm_loss": 0.548510730266571, "actor_loss": -8.895292282104492, "critic_loss": 0.025742357596755028, "reward": 0.07158894836902618, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23895540833473206, 0.1563178300857544, 0.2509816884994507], "policy_updates": 21990, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 766.1515227159999, "contact_bce": 0.3310243487358093, "contact_force_loss": 0.03342573717236519, "terrain_level_mean": 2.824951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22100, "actor_lr": 1.1205152531917044e-05, "archive_windows": 100000, "env_steps": 22100, "total_transitions": 90521600, "num_steps_per_env": 1, "wm_loss": 0.561639130115509, "actor_loss": -8.823899269104004, "critic_loss": 0.02203301712870598, "reward": 0.07129599153995514, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23754151165485382, 0.15837977826595306, 0.2572478950023651], "policy_updates": 22000, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 769.689860462, "contact_bce": 0.32828864455223083, "contact_force_loss": 0.033490054309368134, "terrain_level_mean": 2.825927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22110, "actor_lr": 1.1182729758168185e-05, "archive_windows": 100000, "env_steps": 22110, "total_transitions": 90562560, "num_steps_per_env": 1, "wm_loss": 0.6091053485870361, "actor_loss": -8.88530158996582, "critic_loss": 0.023881986737251282, "reward": 0.07081310451030731, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24107950925827026, 0.1596652716398239, 0.2616483271121979], "policy_updates": 22010, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 773.2493663939999, "contact_bce": 0.3361102044582367, "contact_force_loss": 0.03442840278148651, "terrain_level_mean": 2.828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9995687007904053, 0.9975225329399109, 2.9996814727783203]} {"step": 22120, "actor_lr": 1.1160328606823714e-05, "archive_windows": 100000, "env_steps": 22120, "total_transitions": 90603520, "num_steps_per_env": 1, "wm_loss": 0.5738791823387146, "actor_loss": -8.845248222351074, "critic_loss": 0.023906085640192032, "reward": 0.07063639163970947, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24642397463321686, 0.16029775142669678, 0.2590614855289459], "policy_updates": 22020, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 776.780627538, "contact_bce": 0.33433887362480164, "contact_force_loss": 0.03363572433590889, "terrain_level_mean": 2.828857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9995687007904053, 0.9974446296691895, 2.9997200965881348]} {"step": 22130, "actor_lr": 1.1137949102449209e-05, "archive_windows": 100000, "env_steps": 22130, "total_transitions": 90644480, "num_steps_per_env": 1, "wm_loss": 0.5819763541221619, "actor_loss": -8.801499366760254, "critic_loss": 0.03585996851325035, "reward": 0.07095319777727127, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2443023920059204, 0.16030529141426086, 0.2598092257976532], "policy_updates": 22030, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 780.3432955019999, "contact_bce": 0.32971805334091187, "contact_force_loss": 0.03374118357896805, "terrain_level_mean": 2.828857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9995687007904053, 0.9974446296691895, 2.9997200965881348]} {"step": 22140, "actor_lr": 1.1115591269586563e-05, "archive_windows": 100000, "env_steps": 22140, "total_transitions": 90685440, "num_steps_per_env": 1, "wm_loss": 0.5781527757644653, "actor_loss": -8.86355972290039, "critic_loss": 0.020559128373861313, "reward": 0.07086124271154404, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24462750554084778, 0.1595442295074463, 0.2608706057071686], "policy_updates": 22040, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 783.849867849, "contact_bce": 0.33627423644065857, "contact_force_loss": 0.034989211708307266, "terrain_level_mean": 2.827880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9995687007904053, 0.9974446296691895, 2.9997200965881348]} {"step": 22150, "actor_lr": 1.109325513275388e-05, "archive_windows": 100000, "env_steps": 22150, "total_transitions": 90726400, "num_steps_per_env": 1, "wm_loss": 0.5819578766822815, "actor_loss": -8.831663131713867, "critic_loss": 0.017623210325837135, "reward": 0.07105819135904312, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24374991655349731, 0.15778233110904694, 0.26028957962989807], "policy_updates": 22050, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 787.3513468699999, "contact_bce": 0.34179240465164185, "contact_force_loss": 0.03427432104945183, "terrain_level_mean": 2.826416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9995687007904053, 0.9974373579025269, 2.9997200965881348]} {"step": 22160, "actor_lr": 1.107094071644546e-05, "archive_windows": 100000, "env_steps": 22160, "total_transitions": 90767360, "num_steps_per_env": 1, "wm_loss": 0.5282375812530518, "actor_loss": -8.881103515625, "critic_loss": 0.017893627285957336, "reward": 0.07109241187572479, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2369430512189865, 0.1563320755958557, 0.25860366225242615], "policy_updates": 22060, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 790.887378214, "contact_bce": 0.3260648548603058, "contact_force_loss": 0.03298525884747505, "terrain_level_mean": 2.825927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9995687007904053, 0.9974373579025269, 2.9997200965881348]} {"step": 22170, "actor_lr": 1.1048648045131812e-05, "archive_windows": 100000, "env_steps": 22170, "total_transitions": 90808320, "num_steps_per_env": 1, "wm_loss": 0.552065908908844, "actor_loss": -8.839374542236328, "critic_loss": 0.026499027386307716, "reward": 0.0712636336684227, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23568908870220184, 0.1562414914369583, 0.2599784731864929], "policy_updates": 22070, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 794.388724078, "contact_bce": 0.33151617646217346, "contact_force_loss": 0.033212047070264816, "terrain_level_mean": 2.82666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9995687007904053, 0.9974373579025269, 2.9997200965881348]} {"step": 22180, "actor_lr": 1.1026377143259586e-05, "archive_windows": 100000, "env_steps": 22180, "total_transitions": 90849280, "num_steps_per_env": 1, "wm_loss": 0.5723682045936584, "actor_loss": -8.86706829071045, "critic_loss": 0.020460639148950577, "reward": 0.07121863216161728, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23728534579277039, 0.1549755185842514, 0.253061980009079], "policy_updates": 22080, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 797.898812752, "contact_bce": 0.32868918776512146, "contact_force_loss": 0.03320986405014992, "terrain_level_mean": 2.827392578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9995687007904053, 0.9974373579025269, 2.9997200965881348]} {"step": 22190, "actor_lr": 1.1004128035251531e-05, "archive_windows": 100000, "env_steps": 22190, "total_transitions": 90890240, "num_steps_per_env": 1, "wm_loss": 0.5752139687538147, "actor_loss": -8.855467796325684, "critic_loss": 0.023856138810515404, "reward": 0.07103953510522842, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23378263413906097, 0.15550488233566284, 0.2547379434108734], "policy_updates": 22090, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 801.410526185, "contact_bce": 0.33364465832710266, "contact_force_loss": 0.03406853973865509, "terrain_level_mean": 2.82763671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9995687007904053, 0.9974373579025269, 2.9997200965881348]} {"step": 22200, "actor_lr": 1.0981900745506547e-05, "archive_windows": 100000, "env_steps": 22200, "total_transitions": 90931200, "num_steps_per_env": 1, "wm_loss": 0.5448755621910095, "actor_loss": -8.8562650680542, "critic_loss": 0.02557249739766121, "reward": 0.07100197672843933, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23871822655200958, 0.15509434044361115, 0.2548009157180786], "policy_updates": 22100, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 804.926697127, "contact_bce": 0.33419549465179443, "contact_force_loss": 0.03417341411113739, "terrain_level_mean": 2.828369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9995687007904053, 0.9974373579025269, 2.9997200965881348]} {"step": 22210, "actor_lr": 1.0959695298399574e-05, "archive_windows": 100000, "env_steps": 22210, "total_transitions": 90972160, "num_steps_per_env": 1, "wm_loss": 0.5385048985481262, "actor_loss": -8.814148902893066, "critic_loss": 0.023280039429664612, "reward": 0.07106709480285645, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24210220575332642, 0.15540815889835358, 0.25695958733558655], "policy_updates": 22110, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 808.42953016, "contact_bce": 0.32728075981140137, "contact_force_loss": 0.03337940201163292, "terrain_level_mean": 2.828857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9995687007904053, 0.9974373579025269, 2.9997200965881348]} {"step": 22220, "actor_lr": 1.0937511718281601e-05, "archive_windows": 100000, "env_steps": 22220, "total_transitions": 91013120, "num_steps_per_env": 1, "wm_loss": 0.5459247827529907, "actor_loss": -8.838464736938477, "critic_loss": 0.030432207509875298, "reward": 0.07095722109079361, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2387993484735489, 0.15753565728664398, 0.2586199939250946], "policy_updates": 22120, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 811.9354973879999, "contact_bce": 0.3313949406147003, "contact_force_loss": 0.033387087285518646, "terrain_level_mean": 2.829345703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9995687007904053, 0.9987346529960632, 2.9997200965881348]} {"step": 22230, "actor_lr": 1.0915350029479663e-05, "archive_windows": 100000, "env_steps": 22230, "total_transitions": 91054080, "num_steps_per_env": 1, "wm_loss": 0.5382451415061951, "actor_loss": -8.839603424072266, "critic_loss": 0.025094931945204735, "reward": 0.07097091525793076, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23436228930950165, 0.15696671605110168, 0.2590492069721222], "policy_updates": 22130, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 815.434599017, "contact_bce": 0.3274794816970825, "contact_force_loss": 0.03239238262176514, "terrain_level_mean": 2.829833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9995687007904053, 0.9991379976272583, 2.9997200965881348]} {"step": 22240, "actor_lr": 1.0893210256296752e-05, "archive_windows": 100000, "env_steps": 22240, "total_transitions": 91095040, "num_steps_per_env": 1, "wm_loss": 0.569230318069458, "actor_loss": -8.869464874267578, "critic_loss": 0.017964040860533714, "reward": 0.07074805349111557, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23705428838729858, 0.15470464527606964, 0.25960293412208557], "policy_updates": 22140, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 818.95037136, "contact_bce": 0.33579781651496887, "contact_force_loss": 0.03407949209213257, "terrain_level_mean": 2.82958984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9995687007904053, 0.9991379976272583, 2.9997200965881348]} {"step": 22250, "actor_lr": 1.0871092423011837e-05, "archive_windows": 100000, "env_steps": 22250, "total_transitions": 91136000, "num_steps_per_env": 1, "wm_loss": 0.5680007338523865, "actor_loss": -8.879016876220703, "critic_loss": 0.022151492536067963, "reward": 0.07061757892370224, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2394407093524933, 0.15417246520519257, 0.2584488093852997], "policy_updates": 22150, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 822.453108777, "contact_bce": 0.33393678069114685, "contact_force_loss": 0.03375852853059769, "terrain_level_mean": 2.83056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9995687007904053, 0.9991379976272583, 2.9997200965881348]} {"step": 22260, "actor_lr": 1.0848996553879852e-05, "archive_windows": 100000, "env_steps": 22260, "total_transitions": 91176960, "num_steps_per_env": 1, "wm_loss": 0.57391756772995, "actor_loss": -8.879280090332031, "critic_loss": 0.02125677838921547, "reward": 0.07056861370801926, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23895609378814697, 0.1554775983095169, 0.25728631019592285], "policy_updates": 22160, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 825.956625936, "contact_bce": 0.32701852917671204, "contact_force_loss": 0.03407463803887367, "terrain_level_mean": 2.83154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9995687007904053, 0.9991415739059448, 2.9997200965881348]} {"step": 22270, "actor_lr": 1.0826922673131621e-05, "archive_windows": 100000, "env_steps": 22270, "total_transitions": 91217920, "num_steps_per_env": 1, "wm_loss": 0.5520803332328796, "actor_loss": -8.84121322631836, "critic_loss": 0.02157331071794033, "reward": 0.07080792635679245, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23810945451259613, 0.15618333220481873, 0.25480833649635315], "policy_updates": 22170, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 829.4656739420001, "contact_bce": 0.3340856730937958, "contact_force_loss": 0.033517539501190186, "terrain_level_mean": 2.8310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9995687007904053, 0.9991415739059448, 2.9997200965881348]} {"step": 22280, "actor_lr": 1.0804870804973858e-05, "archive_windows": 100000, "env_steps": 22280, "total_transitions": 91258880, "num_steps_per_env": 1, "wm_loss": 0.5505515933036804, "actor_loss": -8.874443054199219, "critic_loss": 0.021250687539577484, "reward": 0.07094832509756088, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24160778522491455, 0.15644866228103638, 0.25504687428474426], "policy_updates": 22180, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 832.9767679400001, "contact_bce": 0.3301144242286682, "contact_force_loss": 0.03290986269712448, "terrain_level_mean": 2.83154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9995687007904053, 0.9991415739059448, 2.9997200965881348]} {"step": 22290, "actor_lr": 1.0782840973589145e-05, "archive_windows": 100000, "env_steps": 22290, "total_transitions": 91299840, "num_steps_per_env": 1, "wm_loss": 0.533441424369812, "actor_loss": -8.872542381286621, "critic_loss": 0.02117091976106167, "reward": 0.07089082151651382, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2399863451719284, 0.15485991537570953, 0.25885146856307983], "policy_updates": 22190, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 836.472929741, "contact_bce": 0.33550816774368286, "contact_force_loss": 0.033260539174079895, "terrain_level_mean": 2.831787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9995687007904053, 0.9991415739059448, 2.9997200965881348]} {"step": 22300, "actor_lr": 1.0760833203135888e-05, "archive_windows": 100000, "env_steps": 22300, "total_transitions": 91340800, "num_steps_per_env": 1, "wm_loss": 0.5693034529685974, "actor_loss": -8.779064178466797, "critic_loss": 0.029576295986771584, "reward": 0.0709410086274147, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2402535378932953, 0.15909028053283691, 0.2600298225879669], "policy_updates": 22200, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 839.960679895, "contact_bce": 0.33561423420906067, "contact_force_loss": 0.03364931419491768, "terrain_level_mean": 2.8330078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9995687007904053, 0.9991415739059448, 2.9997200965881348]} {"step": 22310, "actor_lr": 1.0738847517748296e-05, "archive_windows": 100000, "env_steps": 22310, "total_transitions": 91381760, "num_steps_per_env": 1, "wm_loss": 0.587784469127655, "actor_loss": -8.811163902282715, "critic_loss": 0.028160935267806053, "reward": 0.0702516958117485, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24352893233299255, 0.16078031063079834, 0.26316753029823303], "policy_updates": 22210, "skipped_updates": 0, "invalid_env_resets": 5, "elapsed_s": 843.472599999, "contact_bce": 0.3383951783180237, "contact_force_loss": 0.033819179981946945, "terrain_level_mean": 2.833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.997374415397644, 0.9998135566711426, 2.9997200965881348]} RECOVERY reset 1 invalid environments; first IDs=[885] {"step": 22320, "actor_lr": 1.0716883941536392e-05, "archive_windows": 100000, "env_steps": 22320, "total_transitions": 91422720, "num_steps_per_env": 1, "wm_loss": 0.5747750401496887, "actor_loss": -8.81117057800293, "critic_loss": 0.025569966062903404, "reward": 0.06979003548622131, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24255405366420746, 0.16078421473503113, 0.2604515552520752], "policy_updates": 22220, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 846.9987283249999, "contact_bce": 0.3382672071456909, "contact_force_loss": 0.03375259414315224, "terrain_level_mean": 2.833251953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9990822076797485, 0.9998135566711426, 2.9997200965881348]} {"step": 22330, "actor_lr": 1.0694942498585919e-05, "archive_windows": 100000, "env_steps": 22330, "total_transitions": 91463680, "num_steps_per_env": 1, "wm_loss": 0.5504937767982483, "actor_loss": -8.840839385986328, "critic_loss": 0.021644987165927887, "reward": 0.07023975998163223, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23923757672309875, 0.16036343574523926, 0.2595941424369812], "policy_updates": 22230, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 850.504638219, "contact_bce": 0.33671003580093384, "contact_force_loss": 0.03405467048287392, "terrain_level_mean": 2.832763671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.995068073272705, 0.9998135566711426, 2.9997200965881348]} {"step": 22340, "actor_lr": 1.0673023212958354e-05, "archive_windows": 100000, "env_steps": 22340, "total_transitions": 91504640, "num_steps_per_env": 1, "wm_loss": 0.5495460629463196, "actor_loss": -8.834074020385742, "critic_loss": 0.022895509377121925, "reward": 0.07057338207960129, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24109423160552979, 0.1589396446943283, 0.2594757080078125], "policy_updates": 22240, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 854.011461897, "contact_bce": 0.3314542770385742, "contact_force_loss": 0.0331423319876194, "terrain_level_mean": 2.8330078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.995068073272705, 0.9998135566711426, 2.9997200965881348]} {"step": 22350, "actor_lr": 1.0651126108690893e-05, "archive_windows": 100000, "env_steps": 22350, "total_transitions": 91545600, "num_steps_per_env": 1, "wm_loss": 0.5598459243774414, "actor_loss": -8.820751190185547, "critic_loss": 0.024208003655076027, "reward": 0.07062967866659164, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23738324642181396, 0.15794861316680908, 0.2573939859867096], "policy_updates": 22250, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 857.514916831, "contact_bce": 0.3368697762489319, "contact_force_loss": 0.03387503698468208, "terrain_level_mean": 2.834716796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.995068073272705, 0.9998135566711426, 2.9997200965881348]} {"step": 22360, "actor_lr": 1.0629251209796386e-05, "archive_windows": 100000, "env_steps": 22360, "total_transitions": 91586560, "num_steps_per_env": 1, "wm_loss": 0.554379403591156, "actor_loss": -8.863882064819336, "critic_loss": 0.017449328675866127, "reward": 0.07086846232414246, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2374521940946579, 0.1575280725955963, 0.26197153329849243], "policy_updates": 22260, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 861.0125685649999, "contact_bce": 0.3327295184135437, "contact_force_loss": 0.033204592764377594, "terrain_level_mean": 2.83544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.995068073272705, 0.9998135566711426, 2.9997200965881348]} {"step": 22370, "actor_lr": 1.0607398540263332e-05, "archive_windows": 100000, "env_steps": 22370, "total_transitions": 91627520, "num_steps_per_env": 1, "wm_loss": 0.5662627816200256, "actor_loss": -8.825613021850586, "critic_loss": 0.031112486496567726, "reward": 0.07081868499517441, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24054449796676636, 0.15675179660320282, 0.2576915919780731], "policy_updates": 22270, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 864.505969812, "contact_bce": 0.3357110023498535, "contact_force_loss": 0.03329044580459595, "terrain_level_mean": 2.83642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.995068073272705, 0.9998135566711426, 2.9997200965881348]} {"step": 22380, "actor_lr": 1.0585568124055888e-05, "archive_windows": 100000, "env_steps": 22380, "total_transitions": 91668480, "num_steps_per_env": 1, "wm_loss": 0.6196893453598022, "actor_loss": -8.848262786865234, "critic_loss": 0.02761891856789589, "reward": 0.07078150659799576, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24196650087833405, 0.15815715491771698, 0.25683730840682983], "policy_updates": 22280, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 868.0025842690001, "contact_bce": 0.3422083258628845, "contact_force_loss": 0.035051390528678894, "terrain_level_mean": 2.83642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9927493333816528, 0.9998135566711426, 2.9997200965881348]} {"step": 22390, "actor_lr": 1.056375998511377e-05, "archive_windows": 100000, "env_steps": 22390, "total_transitions": 91709440, "num_steps_per_env": 1, "wm_loss": 0.5414518713951111, "actor_loss": -8.852665901184082, "critic_loss": 0.020257798954844475, "reward": 0.07071886211633682, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23943382501602173, 0.15538792312145233, 0.2582675516605377], "policy_updates": 22290, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 871.516043688, "contact_bce": 0.3279304802417755, "contact_force_loss": 0.03351857140660286, "terrain_level_mean": 2.835693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9927493333816528, 0.9998135566711426, 2.9997200965881348]} {"step": 22400, "actor_lr": 1.0541974147352273e-05, "archive_windows": 100000, "env_steps": 22400, "total_transitions": 91750400, "num_steps_per_env": 1, "wm_loss": 0.5356417298316956, "actor_loss": -8.827859878540039, "critic_loss": 0.022122899070382118, "reward": 0.0707550048828125, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23707328736782074, 0.1533833146095276, 0.2561778724193573], "policy_updates": 22300, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 875.026408158, "contact_bce": 0.33566462993621826, "contact_force_loss": 0.03362570330500603, "terrain_level_mean": 2.836669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9927493333816528, 0.9998135566711426, 2.9997200965881348]} {"step": 22410, "actor_lr": 1.0520210634662243e-05, "archive_windows": 100000, "env_steps": 22410, "total_transitions": 91791360, "num_steps_per_env": 1, "wm_loss": 0.5846506953239441, "actor_loss": -8.84010124206543, "critic_loss": 0.02569296956062317, "reward": 0.07047080993652344, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23401601612567902, 0.15351468324661255, 0.25903233885765076], "policy_updates": 22310, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 878.5287606789999, "contact_bce": 0.3357534110546112, "contact_force_loss": 0.03401585668325424, "terrain_level_mean": 2.836669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9927493333816528, 0.9998135566711426, 2.9997200965881348]} {"step": 22420, "actor_lr": 1.0498469470910039e-05, "archive_windows": 100000, "env_steps": 22420, "total_transitions": 91832320, "num_steps_per_env": 1, "wm_loss": 0.5591180324554443, "actor_loss": -8.84442138671875, "critic_loss": 0.03129810839891434, "reward": 0.07072532922029495, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23237985372543335, 0.15820752084255219, 0.2554655969142914], "policy_updates": 22320, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 882.0409002709999, "contact_bce": 0.33838385343551636, "contact_force_loss": 0.0348314493894577, "terrain_level_mean": 2.836669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9927493333816528, 0.9998135566711426, 2.9997200965881348]} {"step": 22430, "actor_lr": 1.0476750679937502e-05, "archive_windows": 100000, "env_steps": 22430, "total_transitions": 91873280, "num_steps_per_env": 1, "wm_loss": 0.547275722026825, "actor_loss": -8.861729621887207, "critic_loss": 0.01974983885884285, "reward": 0.07110241800546646, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22927360236644745, 0.1563088744878769, 0.2563520073890686], "policy_updates": 22330, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 885.5508019339999, "contact_bce": 0.33208757638931274, "contact_force_loss": 0.033484525978565216, "terrain_level_mean": 2.83642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9927493333816528, 0.9998135566711426, 2.9997200965881348]} {"step": 22440, "actor_lr": 1.045505428556197e-05, "archive_windows": 100000, "env_steps": 22440, "total_transitions": 91914240, "num_steps_per_env": 1, "wm_loss": 0.5663816332817078, "actor_loss": -8.82005500793457, "critic_loss": 0.027075234800577164, "reward": 0.07053065299987793, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23430819809436798, 0.15738679468631744, 0.2571304440498352], "policy_updates": 22340, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 889.0587396719999, "contact_bce": 0.3376711308956146, "contact_force_loss": 0.03435514494776726, "terrain_level_mean": 2.835693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9939377307891846, 0.9998135566711426, 2.9997200965881348]} {"step": 22450, "actor_lr": 1.04333803115762e-05, "archive_windows": 100000, "env_steps": 22450, "total_transitions": 91955200, "num_steps_per_env": 1, "wm_loss": 0.5744627118110657, "actor_loss": -8.859448432922363, "critic_loss": 0.019758887588977814, "reward": 0.06997707486152649, "falls": 2, "interval_steps": 10, "velocity_mae": [0.238429456949234, 0.1577431559562683, 0.25969818234443665], "policy_updates": 22350, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 892.582375977, "contact_bce": 0.3344912827014923, "contact_force_loss": 0.03414342552423477, "terrain_level_mean": 2.83740234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9939377307891846, 0.9998135566711426, 2.9997200965881348]} {"step": 22460, "actor_lr": 1.041172878174833e-05, "archive_windows": 100000, "env_steps": 22460, "total_transitions": 91996160, "num_steps_per_env": 1, "wm_loss": 0.5727512836456299, "actor_loss": -8.873754501342773, "critic_loss": 0.022627105936408043, "reward": 0.07044153660535812, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23530766367912292, 0.1590183526277542, 0.25565823912620544], "policy_updates": 22360, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 896.084277365, "contact_bce": 0.341977596282959, "contact_force_loss": 0.03422597050666809, "terrain_level_mean": 2.837158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331787109375, "command_abs_max": [1.9939377307891846, 0.9998135566711426, 2.9990041255950928]} {"step": 22470, "actor_lr": 1.0390099719821949e-05, "archive_windows": 100000, "env_steps": 22470, "total_transitions": 92037120, "num_steps_per_env": 1, "wm_loss": 0.5888383984565735, "actor_loss": -8.889558792114258, "critic_loss": 0.020222634077072144, "reward": 0.07080767303705215, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23544929921627045, 0.15814073383808136, 0.25728723406791687], "policy_updates": 22370, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 899.599294298, "contact_bce": 0.33495059609413147, "contact_force_loss": 0.033794037997722626, "terrain_level_mean": 2.83837890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9939377307891846, 0.9998135566711426, 2.9990041255950928]} {"step": 22480, "actor_lr": 1.0368493149515965e-05, "archive_windows": 100000, "env_steps": 22480, "total_transitions": 92078080, "num_steps_per_env": 1, "wm_loss": 0.5092318654060364, "actor_loss": -8.843681335449219, "critic_loss": 0.027174605056643486, "reward": 0.07049436867237091, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23607024550437927, 0.15673406422138214, 0.2589362561702728], "policy_updates": 22380, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 903.114337996, "contact_bce": 0.3295232355594635, "contact_force_loss": 0.03320527821779251, "terrain_level_mean": 2.839111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9939377307891846, 0.9998135566711426, 2.9990041255950928]} {"step": 22490, "actor_lr": 1.0346909094524622e-05, "archive_windows": 100000, "env_steps": 22490, "total_transitions": 92119040, "num_steps_per_env": 1, "wm_loss": 0.564033031463623, "actor_loss": -8.826652526855469, "critic_loss": 0.026005461812019348, "reward": 0.07090135663747787, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2353152483701706, 0.15900294482707977, 0.25744202733039856], "policy_updates": 22390, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 906.615002913, "contact_bce": 0.3371414542198181, "contact_force_loss": 0.03426264598965645, "terrain_level_mean": 2.840087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9927493333816528, 0.9998135566711426, 2.9990041255950928]} {"step": 22500, "actor_lr": 1.0325347578517512e-05, "archive_windows": 100000, "env_steps": 22500, "total_transitions": 92160000, "num_steps_per_env": 1, "wm_loss": 0.5345152616500854, "actor_loss": -8.832328796386719, "critic_loss": 0.020261408761143684, "reward": 0.07099469751119614, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2381948083639145, 0.15958641469478607, 0.25953730940818787], "policy_updates": 22400, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 910.121785961, "contact_bce": 0.337458074092865, "contact_force_loss": 0.03431951254606247, "terrain_level_mean": 2.84033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9927493333816528, 0.9985809326171875, 2.9990041255950928]} {"step": 22510, "actor_lr": 1.0303808625139451e-05, "archive_windows": 100000, "env_steps": 22510, "total_transitions": 92200960, "num_steps_per_env": 1, "wm_loss": 0.5871614813804626, "actor_loss": -8.833595275878906, "critic_loss": 0.019630642607808113, "reward": 0.07069575041532516, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24412287771701813, 0.1601094901561737, 0.2581492066383362], "policy_updates": 22410, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 913.652035575, "contact_bce": 0.34495797753334045, "contact_force_loss": 0.034658998250961304, "terrain_level_mean": 2.84326171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9927493333816528, 0.9985809326171875, 2.9990041255950928]} {"step": 22520, "actor_lr": 1.0282292258010545e-05, "archive_windows": 100000, "env_steps": 22520, "total_transitions": 92241920, "num_steps_per_env": 1, "wm_loss": 0.5677562952041626, "actor_loss": -8.846908569335938, "critic_loss": 0.020181972533464432, "reward": 0.07104944437742233, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24077872931957245, 0.16003316640853882, 0.2567974328994751], "policy_updates": 22420, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 917.169648033, "contact_bce": 0.34210923314094543, "contact_force_loss": 0.034870415925979614, "terrain_level_mean": 2.8447265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.991055965423584, 0.9985809326171875, 2.9990041255950928]} {"step": 22530, "actor_lr": 1.0260798500726142e-05, "archive_windows": 100000, "env_steps": 22530, "total_transitions": 92282880, "num_steps_per_env": 1, "wm_loss": 0.5435763001441956, "actor_loss": -8.87973403930664, "critic_loss": 0.02250382862985134, "reward": 0.07123928517103195, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23773682117462158, 0.15878288447856903, 0.2598252296447754], "policy_updates": 22430, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 920.9446625289999, "contact_bce": 0.330091655254364, "contact_force_loss": 0.032436635345220566, "terrain_level_mean": 2.843994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.991055965423584, 0.9985809326171875, 2.9990041255950928]} {"step": 22540, "actor_lr": 1.0239327376856777e-05, "archive_windows": 100000, "env_steps": 22540, "total_transitions": 92323840, "num_steps_per_env": 1, "wm_loss": 0.5829399228096008, "actor_loss": -8.82290267944336, "critic_loss": 0.02192249894142151, "reward": 0.07108238339424133, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2425345927476883, 0.15826719999313354, 0.2619747519493103], "policy_updates": 22440, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 924.4562078160001, "contact_bce": 0.32748690247535706, "contact_force_loss": 0.03394168242812157, "terrain_level_mean": 2.84521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.991055965423584, 0.9985809326171875, 2.9990041255950928]} {"step": 22550, "actor_lr": 1.0217878909948172e-05, "archive_windows": 100000, "env_steps": 22550, "total_transitions": 92364800, "num_steps_per_env": 1, "wm_loss": 0.5910061597824097, "actor_loss": -8.86336898803711, "critic_loss": 0.020512020215392113, "reward": 0.07146268337965012, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24125638604164124, 0.15850454568862915, 0.2559298276901245], "policy_updates": 22450, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 927.9566974129999, "contact_bce": 0.33182328939437866, "contact_force_loss": 0.03368878737092018, "terrain_level_mean": 2.845458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.991055965423584, 0.9985809326171875, 2.9990041255950928]} {"step": 22560, "actor_lr": 1.0196453123521198e-05, "archive_windows": 100000, "env_steps": 22560, "total_transitions": 92405760, "num_steps_per_env": 1, "wm_loss": 0.55442214012146, "actor_loss": -8.86528205871582, "critic_loss": 0.023700391873717308, "reward": 0.07114975899457932, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23941852152347565, 0.15807653963565826, 0.255673348903656], "policy_updates": 22460, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 931.464272714, "contact_bce": 0.32910993695259094, "contact_force_loss": 0.033287663012742996, "terrain_level_mean": 2.8447265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9994497299194336, 0.9985809326171875, 2.9990041255950928]} {"step": 22570, "actor_lr": 1.0175050041071855e-05, "archive_windows": 100000, "env_steps": 22570, "total_transitions": 92446720, "num_steps_per_env": 1, "wm_loss": 0.5289968848228455, "actor_loss": -8.86742877960205, "critic_loss": 0.019463425502181053, "reward": 0.07127247005701065, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23743639886379242, 0.15814632177352905, 0.2570362687110901], "policy_updates": 22470, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 934.9736186910001, "contact_bce": 0.3337516784667969, "contact_force_loss": 0.03374546393752098, "terrain_level_mean": 2.845458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9994497299194336, 0.9985809326171875, 2.9990041255950928]} {"step": 22580, "actor_lr": 1.0153669686071238e-05, "archive_windows": 100000, "env_steps": 22580, "total_transitions": 92487680, "num_steps_per_env": 1, "wm_loss": 0.5485339760780334, "actor_loss": -8.864952087402344, "critic_loss": 0.017673542723059654, "reward": 0.0709221139550209, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23553815484046936, 0.16210442781448364, 0.26006099581718445], "policy_updates": 22480, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 938.4793076099999, "contact_bce": 0.3322223424911499, "contact_force_loss": 0.03407455235719681, "terrain_level_mean": 2.845947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9955406188964844]} {"step": 22590, "actor_lr": 1.0132312081965551e-05, "archive_windows": 100000, "env_steps": 22590, "total_transitions": 92528640, "num_steps_per_env": 1, "wm_loss": 0.5611009001731873, "actor_loss": -8.86794376373291, "critic_loss": 0.019439561292529106, "reward": 0.07045136392116547, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23946182429790497, 0.16205503046512604, 0.25842583179473877], "policy_updates": 22490, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 942.01921987, "contact_bce": 0.3346841037273407, "contact_force_loss": 0.03354939818382263, "terrain_level_mean": 2.8447265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22600, "actor_lr": 1.0110977252176015e-05, "archive_windows": 100000, "env_steps": 22600, "total_transitions": 92569600, "num_steps_per_env": 1, "wm_loss": 0.5731875896453857, "actor_loss": -8.853376388549805, "critic_loss": 0.021644556894898415, "reward": 0.07038445770740509, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24050173163414001, 0.1619449108839035, 0.25494542717933655], "policy_updates": 22500, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 945.517464039, "contact_bce": 0.3395869731903076, "contact_force_loss": 0.0338757187128067, "terrain_level_mean": 2.8447265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22610, "actor_lr": 1.0089665220098886e-05, "archive_windows": 100000, "env_steps": 22610, "total_transitions": 92610560, "num_steps_per_env": 1, "wm_loss": 0.5462680459022522, "actor_loss": -8.862390518188477, "critic_loss": 0.02063717506825924, "reward": 0.07080487161874771, "falls": 10, "interval_steps": 10, "velocity_mae": [0.23793993890285492, 0.15950527787208557, 0.25189271569252014], "policy_updates": 22510, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 949.0175481360001, "contact_bce": 0.32909560203552246, "contact_force_loss": 0.0333954319357872, "terrain_level_mean": 2.844482421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22620, "actor_lr": 1.0068376009105417e-05, "archive_windows": 100000, "env_steps": 22620, "total_transitions": 92651520, "num_steps_per_env": 1, "wm_loss": 0.6069245338439941, "actor_loss": -8.84485149383545, "critic_loss": 0.017804661765694618, "reward": 0.07129163295030594, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23530054092407227, 0.15630973875522614, 0.25318408012390137], "policy_updates": 22520, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 952.525620771, "contact_bce": 0.329200804233551, "contact_force_loss": 0.03436756879091263, "terrain_level_mean": 2.84619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22630, "actor_lr": 1.0047109642541838e-05, "archive_windows": 100000, "env_steps": 22630, "total_transitions": 92692480, "num_steps_per_env": 1, "wm_loss": 0.5582732558250427, "actor_loss": -8.895156860351562, "critic_loss": 0.021666888147592545, "reward": 0.07159426063299179, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23335444927215576, 0.15126153826713562, 0.24838322401046753], "policy_updates": 22530, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 956.033141368, "contact_bce": 0.32969579100608826, "contact_force_loss": 0.03380492702126503, "terrain_level_mean": 2.847412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22640, "actor_lr": 1.0025866143729326e-05, "archive_windows": 100000, "env_steps": 22640, "total_transitions": 92733440, "num_steps_per_env": 1, "wm_loss": 0.5475723743438721, "actor_loss": -8.83336067199707, "critic_loss": 0.021665016189217567, "reward": 0.07181277126073837, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23015671968460083, 0.15275318920612335, 0.2510764002799988], "policy_updates": 22540, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 959.539649233, "contact_bce": 0.33699512481689453, "contact_force_loss": 0.03426448628306389, "terrain_level_mean": 2.84716796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22650, "actor_lr": 1.000464553596399e-05, "archive_windows": 100000, "env_steps": 22650, "total_transitions": 92774400, "num_steps_per_env": 1, "wm_loss": 0.5572952628135681, "actor_loss": -8.876852989196777, "critic_loss": 0.023386893793940544, "reward": 0.07180704176425934, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23187105357646942, 0.15142664313316345, 0.25174054503440857], "policy_updates": 22550, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 963.048575983, "contact_bce": 0.33201807737350464, "contact_force_loss": 0.033824529498815536, "terrain_level_mean": 2.847900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22660, "actor_lr": 9.983447842516829e-06, "archive_windows": 100000, "env_steps": 22660, "total_transitions": 92815360, "num_steps_per_env": 1, "wm_loss": 0.5429222583770752, "actor_loss": -8.847871780395508, "critic_loss": 0.02122754231095314, "reward": 0.07174232602119446, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23180630803108215, 0.15213163197040558, 0.254452109336853], "policy_updates": 22560, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 966.550869646, "contact_bce": 0.33416488766670227, "contact_force_loss": 0.03372618928551674, "terrain_level_mean": 2.84814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22670, "actor_lr": 9.962273086633707e-06, "archive_windows": 100000, "env_steps": 22670, "total_transitions": 92856320, "num_steps_per_env": 1, "wm_loss": 0.54115229845047, "actor_loss": -8.850526809692383, "critic_loss": 0.01704450324177742, "reward": 0.07170852273702621, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23383751511573792, 0.154338076710701, 0.25822365283966064], "policy_updates": 22570, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 970.0501011509999, "contact_bce": 0.3358286917209625, "contact_force_loss": 0.03431985154747963, "terrain_level_mean": 2.84912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22680, "actor_lr": 9.941121291535342e-06, "archive_windows": 100000, "env_steps": 22680, "total_transitions": 92897280, "num_steps_per_env": 1, "wm_loss": 0.5053839683532715, "actor_loss": -8.866201400756836, "critic_loss": 0.013987049460411072, "reward": 0.07152463495731354, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23262080550193787, 0.1560298502445221, 0.2609294652938843], "policy_updates": 22580, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 973.549158915, "contact_bce": 0.338856965303421, "contact_force_loss": 0.03325864300131798, "terrain_level_mean": 2.849609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.9935903549194336]} {"step": 22690, "actor_lr": 9.919992480417267e-06, "archive_windows": 100000, "env_steps": 22690, "total_transitions": 92938240, "num_steps_per_env": 1, "wm_loss": 0.5252936482429504, "actor_loss": -8.83768081665039, "critic_loss": 0.027808865532279015, "reward": 0.07116459310054779, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23658312857151031, 0.1579386442899704, 0.25921356678009033], "policy_updates": 22590, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 977.046794704, "contact_bce": 0.33286532759666443, "contact_force_loss": 0.0333891324698925, "terrain_level_mean": 2.848388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.996466875076294]} Warning: EPA horizon = 24 isn't large enough. {"step": 22700, "actor_lr": 9.89888667644981e-06, "archive_windows": 100000, "env_steps": 22700, "total_transitions": 92979200, "num_steps_per_env": 1, "wm_loss": 0.5235798358917236, "actor_loss": -8.809377670288086, "critic_loss": 0.02275191806256771, "reward": 0.07128027826547623, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23495221138000488, 0.15683898329734802, 0.259511798620224], "policy_updates": 22600, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 980.5712273400001, "contact_bce": 0.33287474513053894, "contact_force_loss": 0.03328666836023331, "terrain_level_mean": 2.849365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.996466875076294]} {"step": 22710, "actor_lr": 9.87780390277809e-06, "archive_windows": 100000, "env_steps": 22710, "total_transitions": 93020160, "num_steps_per_env": 1, "wm_loss": 0.5522103905677795, "actor_loss": -8.850411415100098, "critic_loss": 0.024568483233451843, "reward": 0.07138494402170181, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2354867160320282, 0.15670575201511383, 0.2545592486858368], "policy_updates": 22610, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 984.087923784, "contact_bce": 0.33628687262535095, "contact_force_loss": 0.033646974712610245, "terrain_level_mean": 2.848388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9994497299194336, 0.9969348907470703, 2.996466875076294]} {"step": 22720, "actor_lr": 9.856744182521953e-06, "archive_windows": 100000, "env_steps": 22720, "total_transitions": 93061120, "num_steps_per_env": 1, "wm_loss": 0.5573391318321228, "actor_loss": -8.86526107788086, "critic_loss": 0.02379763498902321, "reward": 0.07127250730991364, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23408883810043335, 0.15756985545158386, 0.251733660697937], "policy_updates": 22620, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 987.6016873120001, "contact_bce": 0.3269191086292267, "contact_force_loss": 0.032862063497304916, "terrain_level_mean": 2.84912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9994497299194336, 0.9996669292449951, 2.996466875076294]} {"step": 22730, "actor_lr": 9.835707538775935e-06, "archive_windows": 100000, "env_steps": 22730, "total_transitions": 93102080, "num_steps_per_env": 1, "wm_loss": 0.5268630385398865, "actor_loss": -8.816825866699219, "critic_loss": 0.025573132559657097, "reward": 0.07088669389486313, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23770470917224884, 0.15681304037570953, 0.2544434070587158], "policy_updates": 22630, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 991.12216613, "contact_bce": 0.3259448707103729, "contact_force_loss": 0.03231979161500931, "terrain_level_mean": 2.848876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9994497299194336, 0.9996669292449951, 2.996466875076294]} {"step": 22740, "actor_lr": 9.814693994609328e-06, "archive_windows": 100000, "env_steps": 22740, "total_transitions": 93143040, "num_steps_per_env": 1, "wm_loss": 0.5555733442306519, "actor_loss": -8.892242431640625, "critic_loss": 0.016861435025930405, "reward": 0.07071366161108017, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2349158078432083, 0.15772220492362976, 0.2560744285583496], "policy_updates": 22640, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 994.6298009199999, "contact_bce": 0.3341315984725952, "contact_force_loss": 0.03362569957971573, "terrain_level_mean": 2.85009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9994337558746338, 0.9996669292449951, 2.9991114139556885]} {"step": 22750, "actor_lr": 9.793703573066043e-06, "archive_windows": 100000, "env_steps": 22750, "total_transitions": 93184000, "num_steps_per_env": 1, "wm_loss": 0.49143338203430176, "actor_loss": -8.856411933898926, "critic_loss": 0.028534963726997375, "reward": 0.07110103219747543, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2296697497367859, 0.15620587766170502, 0.25765660405158997], "policy_updates": 22650, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 998.138681478, "contact_bce": 0.33133262395858765, "contact_force_loss": 0.03254749998450279, "terrain_level_mean": 2.850341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9994337558746338, 0.9996669292449951, 2.9991114139556885]} {"step": 22760, "actor_lr": 9.772736297164646e-06, "archive_windows": 100000, "env_steps": 22760, "total_transitions": 93224960, "num_steps_per_env": 1, "wm_loss": 0.5607118010520935, "actor_loss": -8.884382247924805, "critic_loss": 0.020447995513677597, "reward": 0.07159769535064697, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23258079588413239, 0.15473636984825134, 0.2547910511493683], "policy_updates": 22660, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1001.6675924069999, "contact_bce": 0.33828654885292053, "contact_force_loss": 0.03422735258936882, "terrain_level_mean": 2.851806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9994337558746338, 0.9996669292449951, 2.9991114139556885]} {"step": 22770, "actor_lr": 9.751792189898353e-06, "archive_windows": 100000, "env_steps": 22770, "total_transitions": 93265920, "num_steps_per_env": 1, "wm_loss": 0.5261291861534119, "actor_loss": -8.853446006774902, "critic_loss": 0.02428712323307991, "reward": 0.07222076505422592, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23268577456474304, 0.15493467450141907, 0.2537704110145569], "policy_updates": 22670, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1005.1789062229999, "contact_bce": 0.3276407718658447, "contact_force_loss": 0.03262641653418541, "terrain_level_mean": 2.85205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9994337558746338, 0.9996669292449951, 2.9991114139556885]} {"step": 22780, "actor_lr": 9.730871274234919e-06, "archive_windows": 100000, "env_steps": 22780, "total_transitions": 93306880, "num_steps_per_env": 1, "wm_loss": 0.5349767208099365, "actor_loss": -8.847586631774902, "critic_loss": 0.023931702598929405, "reward": 0.07181165367364883, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23287607729434967, 0.15739087760448456, 0.25170645117759705], "policy_updates": 22680, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1008.677904238, "contact_bce": 0.3332005441188812, "contact_force_loss": 0.03383248671889305, "terrain_level_mean": 2.85205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9994337558746338, 0.9996669292449951, 2.9991114139556885]} {"step": 22790, "actor_lr": 9.70997357311669e-06, "archive_windows": 100000, "env_steps": 22790, "total_transitions": 93347840, "num_steps_per_env": 1, "wm_loss": 0.5729237794876099, "actor_loss": -8.836065292358398, "critic_loss": 0.023154301568865776, "reward": 0.07174403965473175, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23203840851783752, 0.16024242341518402, 0.2532520890235901], "policy_updates": 22690, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1012.1962488519999, "contact_bce": 0.3354690968990326, "contact_force_loss": 0.03380618244409561, "terrain_level_mean": 2.85302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9974453449249268, 0.9996669292449951, 2.9991114139556885]} {"step": 22800, "actor_lr": 9.689099109460581e-06, "archive_windows": 100000, "env_steps": 22800, "total_transitions": 93388800, "num_steps_per_env": 1, "wm_loss": 0.5606122016906738, "actor_loss": -8.892333030700684, "critic_loss": 0.014735656790435314, "reward": 0.07159417122602463, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23570555448532104, 0.1598706990480423, 0.25442785024642944], "policy_updates": 22700, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1015.720774133, "contact_bce": 0.3311949074268341, "contact_force_loss": 0.03336968645453453, "terrain_level_mean": 2.853271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9974453449249268, 0.9996669292449951, 2.9991114139556885]} {"step": 22810, "actor_lr": 9.668247906157985e-06, "archive_windows": 100000, "env_steps": 22810, "total_transitions": 93429760, "num_steps_per_env": 1, "wm_loss": 0.5086736083030701, "actor_loss": -8.87933349609375, "critic_loss": 0.019396021962165833, "reward": 0.07119282335042953, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2379142940044403, 0.16007307171821594, 0.25813329219818115], "policy_updates": 22710, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1019.2423236999999, "contact_bce": 0.32972240447998047, "contact_force_loss": 0.03316139429807663, "terrain_level_mean": 2.85400390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9974453449249268, 0.9996669292449951, 2.9991114139556885]} {"step": 22820, "actor_lr": 9.64741998607481e-06, "archive_windows": 100000, "env_steps": 22820, "total_transitions": 93470720, "num_steps_per_env": 1, "wm_loss": 0.5433658957481384, "actor_loss": -8.836343765258789, "critic_loss": 0.022963983938097954, "reward": 0.07139522582292557, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23640719056129456, 0.16095833480358124, 0.25365713238716125], "policy_updates": 22720, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1022.7618049859999, "contact_bce": 0.3283228576183319, "contact_force_loss": 0.03330707177519798, "terrain_level_mean": 2.854248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9974453449249268, 0.9996669292449951, 2.9991114139556885]} {"step": 22830, "actor_lr": 9.626615372051419e-06, "archive_windows": 100000, "env_steps": 22830, "total_transitions": 93511680, "num_steps_per_env": 1, "wm_loss": 0.5231636762619019, "actor_loss": -8.853713035583496, "critic_loss": 0.023696141317486763, "reward": 0.07079537957906723, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2354261875152588, 0.16580358147621155, 0.25533419847488403], "policy_updates": 22730, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1026.277385328, "contact_bce": 0.33143097162246704, "contact_force_loss": 0.0330781415104866, "terrain_level_mean": 2.855712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9969701766967773, 0.9978954195976257, 2.9991114139556885]} {"step": 22840, "actor_lr": 9.605834086902623e-06, "archive_windows": 100000, "env_steps": 22840, "total_transitions": 93552640, "num_steps_per_env": 1, "wm_loss": 0.5285723209381104, "actor_loss": -8.867268562316895, "critic_loss": 0.018407994881272316, "reward": 0.07076777517795563, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24054935574531555, 0.16779178380966187, 0.26195764541625977], "policy_updates": 22740, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1029.791038062, "contact_bce": 0.32813960313796997, "contact_force_loss": 0.033012934029102325, "terrain_level_mean": 2.8564453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9969701766967773, 0.9978954195976257, 2.9991114139556885]} {"step": 22850, "actor_lr": 9.58507615341764e-06, "archive_windows": 100000, "env_steps": 22850, "total_transitions": 93593600, "num_steps_per_env": 1, "wm_loss": 0.5255446434020996, "actor_loss": -8.853053092956543, "critic_loss": 0.019035743549466133, "reward": 0.0706048235297203, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24207846820354462, 0.16504794359207153, 0.2607104778289795], "policy_updates": 22750, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1033.316230397, "contact_bce": 0.33555638790130615, "contact_force_loss": 0.033902280032634735, "terrain_level_mean": 2.85546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9969701766967773, 0.9978954195976257, 2.9991114139556885]} {"step": 22860, "actor_lr": 9.56434159436011e-06, "archive_windows": 100000, "env_steps": 22860, "total_transitions": 93634560, "num_steps_per_env": 1, "wm_loss": 0.5298246741294861, "actor_loss": -8.84600830078125, "critic_loss": 0.032163385301828384, "reward": 0.07111889123916626, "falls": 7, "interval_steps": 10, "velocity_mae": [0.237269788980484, 0.16080458462238312, 0.25818586349487305], "policy_updates": 22760, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1036.8356189370002, "contact_bce": 0.3330911099910736, "contact_force_loss": 0.03240549564361572, "terrain_level_mean": 2.85546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9969701766967773, 0.9978954195976257, 2.9991114139556885]} {"step": 22870, "actor_lr": 9.54363043246801e-06, "archive_windows": 100000, "env_steps": 22870, "total_transitions": 93675520, "num_steps_per_env": 1, "wm_loss": 0.5423686504364014, "actor_loss": -8.829511642456055, "critic_loss": 0.02838773839175701, "reward": 0.07136431336402893, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2346780151128769, 0.1588665097951889, 0.25260964035987854], "policy_updates": 22770, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1040.354153444, "contact_bce": 0.33315449953079224, "contact_force_loss": 0.03271278366446495, "terrain_level_mean": 2.85498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.9969701766967773, 0.9978954195976257, 2.9991114139556885]} {"step": 22880, "actor_lr": 9.522942690453664e-06, "archive_windows": 100000, "env_steps": 22880, "total_transitions": 93716480, "num_steps_per_env": 1, "wm_loss": 0.5258204340934753, "actor_loss": -8.892788887023926, "critic_loss": 0.02137688547372818, "reward": 0.07137085497379303, "falls": 11, "interval_steps": 10, "velocity_mae": [0.23140764236450195, 0.15869931876659393, 0.25206252932548523], "policy_updates": 22780, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1043.873731523, "contact_bce": 0.3379565179347992, "contact_force_loss": 0.03441447392106056, "terrain_level_mean": 2.85400390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9969701766967773, 0.9978954195976257, 2.9991114139556885]} {"step": 22890, "actor_lr": 9.502278391003726e-06, "archive_windows": 100000, "env_steps": 22890, "total_transitions": 93757440, "num_steps_per_env": 1, "wm_loss": 0.5464592576026917, "actor_loss": -8.833035469055176, "critic_loss": 0.015702251344919205, "reward": 0.07159128785133362, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2291412055492401, 0.1578897088766098, 0.24902458488941193], "policy_updates": 22790, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1047.4002684040001, "contact_bce": 0.3297317624092102, "contact_force_loss": 0.03321176394820213, "terrain_level_mean": 2.8544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9954464435577393, 0.9999374151229858, 2.9991114139556885]} {"step": 22900, "actor_lr": 9.481637556779122e-06, "archive_windows": 100000, "env_steps": 22900, "total_transitions": 93798400, "num_steps_per_env": 1, "wm_loss": 0.5523337125778198, "actor_loss": -8.879560470581055, "critic_loss": 0.028824198991060257, "reward": 0.07134389132261276, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22906024754047394, 0.16079004108905792, 0.2540249824523926], "policy_updates": 22800, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1050.924044178, "contact_bce": 0.33163487911224365, "contact_force_loss": 0.03345627337694168, "terrain_level_mean": 2.854248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9954464435577393, 0.9999374151229858, 2.9991114139556885]} {"step": 22910, "actor_lr": 9.461020210415059e-06, "archive_windows": 100000, "env_steps": 22910, "total_transitions": 93839360, "num_steps_per_env": 1, "wm_loss": 0.5157909393310547, "actor_loss": -8.851608276367188, "critic_loss": 0.02301856316626072, "reward": 0.07102513313293457, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23205652832984924, 0.16057708859443665, 0.2579175531864166], "policy_updates": 22810, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1054.44127578, "contact_bce": 0.3295784890651703, "contact_force_loss": 0.03285573795437813, "terrain_level_mean": 2.854736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9954464435577393, 0.9999374151229858, 2.9991114139556885]} {"step": 22920, "actor_lr": 9.440426374521e-06, "archive_windows": 100000, "env_steps": 22920, "total_transitions": 93880320, "num_steps_per_env": 1, "wm_loss": 0.5265761613845825, "actor_loss": -8.831720352172852, "critic_loss": 0.025914613157510757, "reward": 0.07121384888887405, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23156708478927612, 0.1612180471420288, 0.25773006677627563], "policy_updates": 22820, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1057.9606212200001, "contact_bce": 0.3336896002292633, "contact_force_loss": 0.03395945206284523, "terrain_level_mean": 2.8564453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9954464435577393, 0.9999374151229858, 2.9991114139556885]} {"step": 22930, "actor_lr": 9.4198560716806e-06, "archive_windows": 100000, "env_steps": 22930, "total_transitions": 93921280, "num_steps_per_env": 1, "wm_loss": 0.5211980938911438, "actor_loss": -8.896448135375977, "critic_loss": 0.012969660572707653, "reward": 0.07148298621177673, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23336541652679443, 0.16061964631080627, 0.2577276825904846], "policy_updates": 22830, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1061.481325743, "contact_bce": 0.32850778102874756, "contact_force_loss": 0.0333273708820343, "terrain_level_mean": 2.858154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9954464435577393, 0.9999374151229858, 2.9991114139556885]} {"step": 22940, "actor_lr": 9.39930932445172e-06, "archive_windows": 100000, "env_steps": 22940, "total_transitions": 93962240, "num_steps_per_env": 1, "wm_loss": 0.5518972873687744, "actor_loss": -8.858818054199219, "critic_loss": 0.02373812347650528, "reward": 0.07142036408185959, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23310039937496185, 0.16165831685066223, 0.2559798061847687], "policy_updates": 22840, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1065.006067401, "contact_bce": 0.3309052586555481, "contact_force_loss": 0.033749938011169434, "terrain_level_mean": 2.86083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9954464435577393, 0.9999374151229858, 2.9991114139556885]} {"step": 22950, "actor_lr": 9.378786155366386e-06, "archive_windows": 100000, "env_steps": 22950, "total_transitions": 94003200, "num_steps_per_env": 1, "wm_loss": 0.5197094678878784, "actor_loss": -8.922107696533203, "critic_loss": 0.014714265242218971, "reward": 0.0712885856628418, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22928541898727417, 0.15961948037147522, 0.2578916847705841], "policy_updates": 22850, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1068.523540502, "contact_bce": 0.3296050429344177, "contact_force_loss": 0.033364128321409225, "terrain_level_mean": 2.861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} {"step": 22960, "actor_lr": 9.35828658693077e-06, "archive_windows": 100000, "env_steps": 22960, "total_transitions": 94044160, "num_steps_per_env": 1, "wm_loss": 0.5565578937530518, "actor_loss": -8.860208511352539, "critic_loss": 0.019271567463874817, "reward": 0.07143368571996689, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22728580236434937, 0.16005009412765503, 0.2534928023815155], "policy_updates": 22860, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1072.0503821490001, "contact_bce": 0.3338228464126587, "contact_force_loss": 0.0335053913295269, "terrain_level_mean": 2.863037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} {"step": 22970, "actor_lr": 9.337810641625155e-06, "archive_windows": 100000, "env_steps": 22970, "total_transitions": 94085120, "num_steps_per_env": 1, "wm_loss": 0.5251594185829163, "actor_loss": -8.837841033935547, "critic_loss": 0.020784279331564903, "reward": 0.07132984697818756, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22743555903434753, 0.15973767638206482, 0.25327980518341064], "policy_updates": 22870, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1075.567377074, "contact_bce": 0.32467231154441833, "contact_force_loss": 0.03256286680698395, "terrain_level_mean": 2.8623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} {"step": 22980, "actor_lr": 9.317358341903943e-06, "archive_windows": 100000, "env_steps": 22980, "total_transitions": 94126080, "num_steps_per_env": 1, "wm_loss": 0.555310070514679, "actor_loss": -8.90658950805664, "critic_loss": 0.021246913820505142, "reward": 0.071100614964962, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22781799733638763, 0.16090542078018188, 0.2565586268901825], "policy_updates": 22880, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1079.0832985710001, "contact_bce": 0.3336923122406006, "contact_force_loss": 0.03394865244626999, "terrain_level_mean": 2.86083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} {"step": 22990, "actor_lr": 9.29692971019559e-06, "archive_windows": 100000, "env_steps": 22990, "total_transitions": 94167040, "num_steps_per_env": 1, "wm_loss": 0.5124161243438721, "actor_loss": -8.859846115112305, "critic_loss": 0.019261283800005913, "reward": 0.0713118240237236, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2310790717601776, 0.16059309244155884, 0.25716984272003174], "policy_updates": 22890, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1082.5796653260002, "contact_bce": 0.33101412653923035, "contact_force_loss": 0.033210061490535736, "terrain_level_mean": 2.861083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} Warning: EPA horizon = 24 isn't large enough. {"step": 23000, "actor_lr": 9.276524768902565e-06, "archive_windows": 100000, "env_steps": 23000, "total_transitions": 94208000, "num_steps_per_env": 1, "wm_loss": 0.5314813852310181, "actor_loss": -8.837993621826172, "critic_loss": 0.02561083249747753, "reward": 0.0706326887011528, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23429898917675018, 0.16232043504714966, 0.25338035821914673], "policy_updates": 22900, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1086.075886309, "contact_bce": 0.32318729162216187, "contact_force_loss": 0.0317581444978714, "terrain_level_mean": 2.85986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} {"step": 23010, "actor_lr": 9.256143540401413e-06, "archive_windows": 100000, "env_steps": 23010, "total_transitions": 94248960, "num_steps_per_env": 1, "wm_loss": 0.49843740463256836, "actor_loss": -8.876814842224121, "critic_loss": 0.016889343038201332, "reward": 0.07013129442930222, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23818956315517426, 0.16133694350719452, 0.25884097814559937], "policy_updates": 22910, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1089.6120284130002, "contact_bce": 0.3302207887172699, "contact_force_loss": 0.03248710185289383, "terrain_level_mean": 2.859619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} {"step": 23020, "actor_lr": 9.235786047042649e-06, "archive_windows": 100000, "env_steps": 23020, "total_transitions": 94289920, "num_steps_per_env": 1, "wm_loss": 0.5394066572189331, "actor_loss": -8.867485046386719, "critic_loss": 0.0178819689899683, "reward": 0.0706513449549675, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24230097234249115, 0.16091538965702057, 0.2570924162864685], "policy_updates": 22920, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1093.3656680820002, "contact_bce": 0.32996320724487305, "contact_force_loss": 0.03291210159659386, "terrain_level_mean": 2.8603515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9991114139556885]} {"step": 23030, "actor_lr": 9.215452311150752e-06, "archive_windows": 100000, "env_steps": 23030, "total_transitions": 94330880, "num_steps_per_env": 1, "wm_loss": 0.5265933871269226, "actor_loss": -8.83346176147461, "critic_loss": 0.02251221053302288, "reward": 0.07021499425172806, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2428877353668213, 0.160752072930336, 0.2550225257873535], "policy_updates": 22930, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1096.877947007, "contact_bce": 0.328538715839386, "contact_force_loss": 0.033281516283750534, "terrain_level_mean": 2.859619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9998035430908203]} {"step": 23040, "actor_lr": 9.19514235502416e-06, "archive_windows": 100000, "env_steps": 23040, "total_transitions": 94371840, "num_steps_per_env": 1, "wm_loss": 0.5523726940155029, "actor_loss": -8.89237117767334, "critic_loss": 0.01717430353164673, "reward": 0.07071791589260101, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23584550619125366, 0.15914194285869598, 0.2558242678642273], "policy_updates": 22940, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1100.3971285100001, "contact_bce": 0.3341391384601593, "contact_force_loss": 0.033217936754226685, "terrain_level_mean": 2.85986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9998035430908203]} {"step": 23050, "actor_lr": 9.174856200935233e-06, "archive_windows": 100000, "env_steps": 23050, "total_transitions": 94412800, "num_steps_per_env": 1, "wm_loss": 0.5452935099601746, "actor_loss": -8.850239753723145, "critic_loss": 0.02357622981071472, "reward": 0.07026699185371399, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23169757425785065, 0.15974022448062897, 0.2588981091976166], "policy_updates": 22950, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1103.9193962460001, "contact_bce": 0.3276425302028656, "contact_force_loss": 0.033066291362047195, "terrain_level_mean": 2.85986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9998035430908203]} {"step": 23060, "actor_lr": 9.154593871130221e-06, "archive_windows": 100000, "env_steps": 23060, "total_transitions": 94453760, "num_steps_per_env": 1, "wm_loss": 0.5349992513656616, "actor_loss": -8.828651428222656, "critic_loss": 0.022216269746422768, "reward": 0.07006553560495377, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2322613000869751, 0.15824589133262634, 0.2580628991127014], "policy_updates": 22960, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1107.444271135, "contact_bce": 0.3360806405544281, "contact_force_loss": 0.03449986129999161, "terrain_level_mean": 2.859619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9998289346694946, 0.9999374151229858, 2.9998035430908203]} {"step": 23070, "actor_lr": 9.134355387829246e-06, "archive_windows": 100000, "env_steps": 23070, "total_transitions": 94494720, "num_steps_per_env": 1, "wm_loss": 0.518696665763855, "actor_loss": -8.865296363830566, "critic_loss": 0.026256872341036797, "reward": 0.06974084675312042, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23353873193264008, 0.16117021441459656, 0.26505136489868164], "policy_updates": 22970, "skipped_updates": 0, "invalid_env_resets": 6, "elapsed_s": 1110.9749192890001, "contact_bce": 0.3295654356479645, "contact_force_loss": 0.0333859883248806, "terrain_level_mean": 2.860107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9937760829925537, 0.9999374151229858, 2.9998035430908203]} RECOVERY reset 1 invalid environments; first IDs=[557] {"step": 23080, "actor_lr": 9.11414077322631e-06, "archive_windows": 100000, "env_steps": 23080, "total_transitions": 94535680, "num_steps_per_env": 1, "wm_loss": 0.5765433311462402, "actor_loss": -8.924057960510254, "critic_loss": 0.017317375168204308, "reward": 0.07060164213180542, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23513129353523254, 0.1635524183511734, 0.25757381319999695], "policy_updates": 22980, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1114.526231493, "contact_bce": 0.33311647176742554, "contact_force_loss": 0.033943936228752136, "terrain_level_mean": 2.860107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.996741771697998, 0.9999374151229858, 2.9998035430908203]} {"step": 23090, "actor_lr": 9.093950049489197e-06, "archive_windows": 100000, "env_steps": 23090, "total_transitions": 94576640, "num_steps_per_env": 1, "wm_loss": 0.5361583232879639, "actor_loss": -8.86449146270752, "critic_loss": 0.02349788136780262, "reward": 0.07007823884487152, "falls": 12, "interval_steps": 10, "velocity_mae": [0.2384679615497589, 0.16335228085517883, 0.2571592628955841], "policy_updates": 22990, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1118.0443604670002, "contact_bce": 0.33258938789367676, "contact_force_loss": 0.03345451503992081, "terrain_level_mean": 2.859619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.996741771697998, 0.9999374151229858, 2.9998035430908203]} {"step": 23100, "actor_lr": 9.07378323875952e-06, "archive_windows": 100000, "env_steps": 23100, "total_transitions": 94617600, "num_steps_per_env": 1, "wm_loss": 0.5220614671707153, "actor_loss": -8.8060884475708, "critic_loss": 0.01986328698694706, "reward": 0.07068517059087753, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2402401715517044, 0.16088390350341797, 0.26033878326416016], "policy_updates": 23000, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1121.562227884, "contact_bce": 0.3340337872505188, "contact_force_loss": 0.033775415271520615, "terrain_level_mean": 2.85986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.996741771697998, 0.9999374151229858, 2.9998035430908203]} {"step": 23110, "actor_lr": 9.053640363152657e-06, "archive_windows": 100000, "env_steps": 23110, "total_transitions": 94658560, "num_steps_per_env": 1, "wm_loss": 0.5238520503044128, "actor_loss": -8.82962703704834, "critic_loss": 0.014608892612159252, "reward": 0.0708068236708641, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24103140830993652, 0.15908771753311157, 0.25928112864494324], "policy_updates": 23010, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1125.085411628, "contact_bce": 0.3328334093093872, "contact_force_loss": 0.033027924597263336, "terrain_level_mean": 2.860595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.996741771697998, 0.9975876808166504, 2.9998035430908203]} {"step": 23120, "actor_lr": 9.033521444757737e-06, "archive_windows": 100000, "env_steps": 23120, "total_transitions": 94699520, "num_steps_per_env": 1, "wm_loss": 0.5172333121299744, "actor_loss": -8.844215393066406, "critic_loss": 0.02181140147149563, "reward": 0.07093183696269989, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23872488737106323, 0.16045941412448883, 0.2571466565132141], "policy_updates": 23020, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1128.594069957, "contact_bce": 0.3301721513271332, "contact_force_loss": 0.03304881229996681, "terrain_level_mean": 2.86181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.996741771697998, 0.9975876808166504, 2.9998035430908203]} {"step": 23130, "actor_lr": 9.013426505637617e-06, "archive_windows": 100000, "env_steps": 23130, "total_transitions": 94740480, "num_steps_per_env": 1, "wm_loss": 0.5575241446495056, "actor_loss": -8.848665237426758, "critic_loss": 0.021836867555975914, "reward": 0.07103434950113297, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23681828379631042, 0.15960784256458282, 0.2577325999736786], "policy_updates": 23030, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1132.105120657, "contact_bce": 0.33008211851119995, "contact_force_loss": 0.032942868769168854, "terrain_level_mean": 2.861572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.996741771697998, 0.9975876808166504, 2.9998035430908203]} {"step": 23140, "actor_lr": 8.99335556782888e-06, "archive_windows": 100000, "env_steps": 23140, "total_transitions": 94781440, "num_steps_per_env": 1, "wm_loss": 0.5003407597541809, "actor_loss": -8.86792278289795, "critic_loss": 0.02455739676952362, "reward": 0.07098127901554108, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23798519372940063, 0.15846149623394012, 0.25717276334762573], "policy_updates": 23040, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1135.625992293, "contact_bce": 0.3337646722793579, "contact_force_loss": 0.03328659012913704, "terrain_level_mean": 2.862548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.996741771697998, 0.9975876808166504, 2.9998035430908203]} {"step": 23150, "actor_lr": 8.973308653341755e-06, "archive_windows": 100000, "env_steps": 23150, "total_transitions": 94822400, "num_steps_per_env": 1, "wm_loss": 0.5179689526557922, "actor_loss": -8.86603832244873, "critic_loss": 0.022736594080924988, "reward": 0.07109539955854416, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23591887950897217, 0.16094061732292175, 0.259913831949234], "policy_updates": 23050, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1139.127286133, "contact_bce": 0.33152005076408386, "contact_force_loss": 0.03318461403250694, "terrain_level_mean": 2.8623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.996741771697998, 0.9975876808166504, 2.9998035430908203]} {"step": 23160, "actor_lr": 8.953285784160146e-06, "archive_windows": 100000, "env_steps": 23160, "total_transitions": 94863360, "num_steps_per_env": 1, "wm_loss": 0.5317621231079102, "actor_loss": -8.863969802856445, "critic_loss": 0.020281683653593063, "reward": 0.07110993564128876, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23481030762195587, 0.16225306689739227, 0.26200070977211], "policy_updates": 23060, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1142.645103384, "contact_bce": 0.33541586995124817, "contact_force_loss": 0.03300812840461731, "terrain_level_mean": 2.862060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.996741771697998, 0.99699866771698, 2.9998035430908203]} {"step": 23170, "actor_lr": 8.933286982241584e-06, "archive_windows": 100000, "env_steps": 23170, "total_transitions": 94904320, "num_steps_per_env": 1, "wm_loss": 0.5415142178535461, "actor_loss": -8.822125434875488, "critic_loss": 0.022795401513576508, "reward": 0.07064462453126907, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2328687310218811, 0.16057854890823364, 0.2615884244441986], "policy_updates": 23070, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1146.160280384, "contact_bce": 0.3254671096801758, "contact_force_loss": 0.03277742490172386, "terrain_level_mean": 2.863037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.996741771697998, 0.99699866771698, 2.9998035430908203]} {"step": 23180, "actor_lr": 8.913312269517206e-06, "archive_windows": 100000, "env_steps": 23180, "total_transitions": 94945280, "num_steps_per_env": 1, "wm_loss": 0.5346550941467285, "actor_loss": -8.872916221618652, "critic_loss": 0.029970917850732803, "reward": 0.07033716142177582, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23286102712154388, 0.15846571326255798, 0.2590946853160858], "policy_updates": 23080, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1149.679098899, "contact_bce": 0.32502394914627075, "contact_force_loss": 0.033183347433805466, "terrain_level_mean": 2.864501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.996741771697998, 0.9972668886184692, 2.9998035430908203]} {"step": 23190, "actor_lr": 8.89336166789173e-06, "archive_windows": 100000, "env_steps": 23190, "total_transitions": 94986240, "num_steps_per_env": 1, "wm_loss": 0.5230563879013062, "actor_loss": -8.853710174560547, "critic_loss": 0.024068640545010567, "reward": 0.07058173418045044, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23011958599090576, 0.15735922753810883, 0.2544916570186615], "policy_updates": 23090, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1153.2022618190001, "contact_bce": 0.3262040913105011, "contact_force_loss": 0.03329255059361458, "terrain_level_mean": 2.865478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.996741771697998, 0.9972668886184692, 2.9998035430908203]} {"step": 23200, "actor_lr": 8.873435199243447e-06, "archive_windows": 100000, "env_steps": 23200, "total_transitions": 95027200, "num_steps_per_env": 1, "wm_loss": 0.5386614799499512, "actor_loss": -8.850447654724121, "critic_loss": 0.0172408539801836, "reward": 0.07064227014780045, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23498395085334778, 0.15664178133010864, 0.256969153881073], "policy_updates": 23100, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1156.730340134, "contact_bce": 0.3342823088169098, "contact_force_loss": 0.03397083654999733, "terrain_level_mean": 2.866455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.996741771697998, 0.9972668886184692, 2.9998035430908203]} {"step": 23210, "actor_lr": 8.853532885424175e-06, "archive_windows": 100000, "env_steps": 23210, "total_transitions": 95068160, "num_steps_per_env": 1, "wm_loss": 0.5150389671325684, "actor_loss": -8.818889617919922, "critic_loss": 0.022601744160056114, "reward": 0.07043956965208054, "falls": 11, "interval_steps": 10, "velocity_mae": [0.24179042875766754, 0.1589737981557846, 0.2563292384147644], "policy_updates": 23110, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1160.252572872, "contact_bce": 0.32569584250450134, "contact_force_loss": 0.03240019455552101, "terrain_level_mean": 2.86669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.996741771697998, 0.9972668886184692, 2.9998035430908203]} {"step": 23220, "actor_lr": 8.833654748259216e-06, "archive_windows": 100000, "env_steps": 23220, "total_transitions": 95109120, "num_steps_per_env": 1, "wm_loss": 0.5444589257240295, "actor_loss": -8.894721984863281, "critic_loss": 0.021904585883021355, "reward": 0.0704682394862175, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2417144626379013, 0.15924072265625, 0.25763848423957825], "policy_updates": 23120, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1163.7738763070001, "contact_bce": 0.3339138925075531, "contact_force_loss": 0.03327333182096481, "terrain_level_mean": 2.867919921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.996741771697998, 0.9972668886184692, 2.9998035430908203]} {"step": 23230, "actor_lr": 8.813800809547416e-06, "archive_windows": 100000, "env_steps": 23230, "total_transitions": 95150080, "num_steps_per_env": 1, "wm_loss": 0.5617246627807617, "actor_loss": -8.855400085449219, "critic_loss": 0.028367359191179276, "reward": 0.07022974640130997, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24119023978710175, 0.15957011282444, 0.26230886578559875], "policy_updates": 23130, "skipped_updates": 0, "invalid_env_resets": 7, "elapsed_s": 1167.297692888, "contact_bce": 0.3317491114139557, "contact_force_loss": 0.03356623649597168, "terrain_level_mean": 2.866943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.996741771697998, 0.9973265528678894, 2.997002601623535]} RECOVERY reset 1 invalid environments; first IDs=[1979] {"step": 23240, "actor_lr": 8.793971091061037e-06, "archive_windows": 100000, "env_steps": 23240, "total_transitions": 95191040, "num_steps_per_env": 1, "wm_loss": 0.5591928362846375, "actor_loss": -8.821117401123047, "critic_loss": 0.01969074085354805, "reward": 0.07093879580497742, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2386063039302826, 0.15595220029354095, 0.2591637372970581], "policy_updates": 23140, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1170.8347268100001, "contact_bce": 0.32904523611068726, "contact_force_loss": 0.03366527333855629, "terrain_level_mean": 2.866455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.996741771697998, 0.9973265528678894, 2.997002601623535]} {"step": 23250, "actor_lr": 8.77416561454579e-06, "archive_windows": 100000, "env_steps": 23250, "total_transitions": 95232000, "num_steps_per_env": 1, "wm_loss": 0.5195306539535522, "actor_loss": -8.89635181427002, "critic_loss": 0.01713523454964161, "reward": 0.07069973647594452, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23662200570106506, 0.15564677119255066, 0.2581540048122406], "policy_updates": 23150, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1174.358505867, "contact_bce": 0.3272831439971924, "contact_force_loss": 0.03323405608534813, "terrain_level_mean": 2.86669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.996741771697998, 0.9973265528678894, 2.997002601623535]} {"step": 23260, "actor_lr": 8.754384401720837e-06, "archive_windows": 100000, "env_steps": 23260, "total_transitions": 95272960, "num_steps_per_env": 1, "wm_loss": 0.5243496894836426, "actor_loss": -8.842178344726562, "critic_loss": 0.029660901054739952, "reward": 0.07137055695056915, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2355128973722458, 0.15490202605724335, 0.25969555974006653], "policy_updates": 23160, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1177.8802107860001, "contact_bce": 0.33219656348228455, "contact_force_loss": 0.0324307419359684, "terrain_level_mean": 2.867431640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9955520629882812, 0.9973265528678894, 2.996671438217163]} {"step": 23270, "actor_lr": 8.734627474278674e-06, "archive_windows": 100000, "env_steps": 23270, "total_transitions": 95313920, "num_steps_per_env": 1, "wm_loss": 0.5548444986343384, "actor_loss": -8.845926284790039, "critic_loss": 0.022912023589015007, "reward": 0.0716414824128151, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23591020703315735, 0.1545792669057846, 0.25750014185905457], "policy_updates": 23170, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1181.3984146700002, "contact_bce": 0.33255085349082947, "contact_force_loss": 0.03340304642915726, "terrain_level_mean": 2.868408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9955520629882812, 0.9973265528678894, 2.996671438217163]} {"step": 23280, "actor_lr": 8.714894853885195e-06, "archive_windows": 100000, "env_steps": 23280, "total_transitions": 95354880, "num_steps_per_env": 1, "wm_loss": 0.5451514720916748, "actor_loss": -8.847902297973633, "critic_loss": 0.020677244290709496, "reward": 0.07118199020624161, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23355326056480408, 0.156283438205719, 0.25952354073524475], "policy_updates": 23180, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1184.913928225, "contact_bce": 0.3279702365398407, "contact_force_loss": 0.0323561429977417, "terrain_level_mean": 2.869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9955520629882812, 0.9973265528678894, 2.996671438217163]} {"step": 23290, "actor_lr": 8.695186562179656e-06, "archive_windows": 100000, "env_steps": 23290, "total_transitions": 95395840, "num_steps_per_env": 1, "wm_loss": 0.5435461401939392, "actor_loss": -8.853421211242676, "critic_loss": 0.021741217002272606, "reward": 0.07094525545835495, "falls": 7, "interval_steps": 10, "velocity_mae": [0.22917884588241577, 0.15783143043518066, 0.25877243280410767], "policy_updates": 23190, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1188.427459509, "contact_bce": 0.3306278586387634, "contact_force_loss": 0.032989900559186935, "terrain_level_mean": 2.86865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9955520629882812, 0.9989945888519287, 2.996671438217163]} {"step": 23300, "actor_lr": 8.675502620774608e-06, "archive_windows": 100000, "env_steps": 23300, "total_transitions": 95436800, "num_steps_per_env": 1, "wm_loss": 0.534649133682251, "actor_loss": -8.857586860656738, "critic_loss": 0.02156434766948223, "reward": 0.07086636871099472, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22924049198627472, 0.15736141800880432, 0.25672993063926697], "policy_updates": 23200, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1192.033034307, "contact_bce": 0.3300664722919464, "contact_force_loss": 0.03267499804496765, "terrain_level_mean": 2.868408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9955520629882812, 0.9989945888519287, 2.996671438217163]} {"step": 23310, "actor_lr": 8.655843051255904e-06, "archive_windows": 100000, "env_steps": 23310, "total_transitions": 95477760, "num_steps_per_env": 1, "wm_loss": 0.5321378707885742, "actor_loss": -8.832345962524414, "critic_loss": 0.023344097658991814, "reward": 0.07096078246831894, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22870369255542755, 0.1558229625225067, 0.2556089460849762], "policy_updates": 23210, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1195.5564295430001, "contact_bce": 0.33031827211380005, "contact_force_loss": 0.032701924443244934, "terrain_level_mean": 2.86767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9955520629882812, 0.9989945888519287, 2.996671438217163]} {"step": 23320, "actor_lr": 8.636207875182672e-06, "archive_windows": 100000, "env_steps": 23320, "total_transitions": 95518720, "num_steps_per_env": 1, "wm_loss": 0.5166364908218384, "actor_loss": -8.84303092956543, "critic_loss": 0.02677285112440586, "reward": 0.07124964892864227, "falls": 8, "interval_steps": 10, "velocity_mae": [0.22872962057590485, 0.15704157948493958, 0.2559734284877777], "policy_updates": 23220, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1199.0701678980001, "contact_bce": 0.33100733160972595, "contact_force_loss": 0.032445166260004044, "terrain_level_mean": 2.866943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.996671438217163]} {"step": 23330, "actor_lr": 8.61659711408729e-06, "archive_windows": 100000, "env_steps": 23330, "total_transitions": 95559680, "num_steps_per_env": 1, "wm_loss": 0.5625765323638916, "actor_loss": -8.85544204711914, "critic_loss": 0.0266741756349802, "reward": 0.0712321549654007, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22922448813915253, 0.15924589335918427, 0.25729382038116455], "policy_updates": 23230, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1202.586084941, "contact_bce": 0.3296801447868347, "contact_force_loss": 0.03292934596538544, "terrain_level_mean": 2.8681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.996671438217163]} {"step": 23340, "actor_lr": 8.597010789475356e-06, "archive_windows": 100000, "env_steps": 23340, "total_transitions": 95600640, "num_steps_per_env": 1, "wm_loss": 0.5497230887413025, "actor_loss": -8.865442276000977, "critic_loss": 0.024655794724822044, "reward": 0.0709313452243805, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2301509976387024, 0.15998618304729462, 0.2591404914855957], "policy_updates": 23240, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1206.0944752980001, "contact_bce": 0.33140042424201965, "contact_force_loss": 0.0340777225792408, "terrain_level_mean": 2.869384765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.9960196018218994]} {"step": 23350, "actor_lr": 8.57744892282569e-06, "archive_windows": 100000, "env_steps": 23350, "total_transitions": 95641600, "num_steps_per_env": 1, "wm_loss": 0.535815954208374, "actor_loss": -8.810859680175781, "critic_loss": 0.0256096962839365, "reward": 0.0712694302201271, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23444484174251556, 0.15922187268733978, 0.25714144110679626], "policy_updates": 23250, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1209.684640054, "contact_bce": 0.32585984468460083, "contact_force_loss": 0.032929159700870514, "terrain_level_mean": 2.8701171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.9960196018218994]} {"step": 23360, "actor_lr": 8.557911535590273e-06, "archive_windows": 100000, "env_steps": 23360, "total_transitions": 95682560, "num_steps_per_env": 1, "wm_loss": 0.5428730249404907, "actor_loss": -8.797235488891602, "critic_loss": 0.027581771835684776, "reward": 0.07129868119955063, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2347707599401474, 0.16045354306697845, 0.26320865750312805], "policy_updates": 23260, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1213.2102177470001, "contact_bce": 0.3346155881881714, "contact_force_loss": 0.034650471061468124, "terrain_level_mean": 2.87158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.9960196018218994]} {"step": 23370, "actor_lr": 8.538398649194244e-06, "archive_windows": 100000, "env_steps": 23370, "total_transitions": 95723520, "num_steps_per_env": 1, "wm_loss": 0.5157275795936584, "actor_loss": -8.84770393371582, "critic_loss": 0.018789945170283318, "reward": 0.0714830607175827, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2347884625196457, 0.15920329093933105, 0.2595292925834656], "policy_updates": 23270, "skipped_updates": 0, "invalid_env_resets": 8, "elapsed_s": 1216.7273799700001, "contact_bce": 0.3327808380126953, "contact_force_loss": 0.03344340994954109, "terrain_level_mean": 2.872802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.9960196018218994]} RECOVERY reset 1 invalid environments; first IDs=[1313] {"step": 23380, "actor_lr": 8.518910285035873e-06, "archive_windows": 100000, "env_steps": 23380, "total_transitions": 95764480, "num_steps_per_env": 1, "wm_loss": 0.5052773952484131, "actor_loss": -8.887802124023438, "critic_loss": 0.017936918884515762, "reward": 0.07092181593179703, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2369973510503769, 0.15852001309394836, 0.25705486536026], "policy_updates": 23280, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1220.254947078, "contact_bce": 0.3299770951271057, "contact_force_loss": 0.032328806817531586, "terrain_level_mean": 2.873291015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.9960196018218994]} {"step": 23390, "actor_lr": 8.499446464486544e-06, "archive_windows": 100000, "env_steps": 23390, "total_transitions": 95805440, "num_steps_per_env": 1, "wm_loss": 0.5614765882492065, "actor_loss": -8.881587028503418, "critic_loss": 0.029352007433772087, "reward": 0.07121657580137253, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23578011989593506, 0.15548773109912872, 0.25343653559684753], "policy_updates": 23290, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1223.783619799, "contact_bce": 0.3365080952644348, "contact_force_loss": 0.034436728805303574, "terrain_level_mean": 2.87451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.998771905899048]} {"step": 23400, "actor_lr": 8.480007208890713e-06, "archive_windows": 100000, "env_steps": 23400, "total_transitions": 95846400, "num_steps_per_env": 1, "wm_loss": 0.5586780905723572, "actor_loss": -8.854026794433594, "critic_loss": 0.030946915969252586, "reward": 0.0716233178973198, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23492300510406494, 0.1550663560628891, 0.2528320550918579], "policy_updates": 23300, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1227.301190789, "contact_bce": 0.32340481877326965, "contact_force_loss": 0.0333406999707222, "terrain_level_mean": 2.8740234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.998771905899048]} {"step": 23410, "actor_lr": 8.460592539565925e-06, "archive_windows": 100000, "env_steps": 23410, "total_transitions": 95887360, "num_steps_per_env": 1, "wm_loss": 0.4968818724155426, "actor_loss": -8.833250045776367, "critic_loss": 0.02600148692727089, "reward": 0.07143191248178482, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23648801445960999, 0.15615801513195038, 0.2529335916042328], "policy_updates": 23310, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1230.967294433, "contact_bce": 0.33000245690345764, "contact_force_loss": 0.03343936428427696, "terrain_level_mean": 2.873291015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.998771905899048]} {"step": 23420, "actor_lr": 8.44120247780273e-06, "archive_windows": 100000, "env_steps": 23420, "total_transitions": 95928320, "num_steps_per_env": 1, "wm_loss": 0.6075976490974426, "actor_loss": -8.856541633605957, "critic_loss": 0.020539766177535057, "reward": 0.07147867977619171, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23546333611011505, 0.1566433161497116, 0.25240254402160645], "policy_updates": 23320, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1234.582656862, "contact_bce": 0.32949337363243103, "contact_force_loss": 0.03370652720332146, "terrain_level_mean": 2.874267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9961212873458862, 0.9989945888519287, 2.998771905899048]} {"step": 23430, "actor_lr": 8.42183704486472e-06, "archive_windows": 100000, "env_steps": 23430, "total_transitions": 95969280, "num_steps_per_env": 1, "wm_loss": 0.5329914093017578, "actor_loss": -8.8667631149292, "critic_loss": 0.024079792201519012, "reward": 0.07111086696386337, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23567597568035126, 0.1549212634563446, 0.25906723737716675], "policy_updates": 23330, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1238.1494068440002, "contact_bce": 0.3303166329860687, "contact_force_loss": 0.03331735357642174, "terrain_level_mean": 2.87451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9961212873458862, 0.9973265528678894, 2.998771905899048]} {"step": 23440, "actor_lr": 8.40249626198846e-06, "archive_windows": 100000, "env_steps": 23440, "total_transitions": 96010240, "num_steps_per_env": 1, "wm_loss": 0.5894312262535095, "actor_loss": -8.847002029418945, "critic_loss": 0.021132545545697212, "reward": 0.07049062103033066, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24055589735507965, 0.15665502846240997, 0.25866711139678955], "policy_updates": 23340, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1241.673928097, "contact_bce": 0.32756271958351135, "contact_force_loss": 0.034112486988306046, "terrain_level_mean": 2.87548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9961212873458862, 0.9973265528678894, 2.998771905899048]} {"step": 23450, "actor_lr": 8.38318015038349e-06, "archive_windows": 100000, "env_steps": 23450, "total_transitions": 96051200, "num_steps_per_env": 1, "wm_loss": 0.5158186554908752, "actor_loss": -8.842490196228027, "critic_loss": 0.02982737496495247, "reward": 0.07045768946409225, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24313588440418243, 0.15596649050712585, 0.2580205202102661], "policy_updates": 23350, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1245.195659312, "contact_bce": 0.3332759737968445, "contact_force_loss": 0.03319815173745155, "terrain_level_mean": 2.875732421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9961212873458862, 0.9973265528678894, 2.998771905899048]} {"step": 23460, "actor_lr": 8.363888731232285e-06, "archive_windows": 100000, "env_steps": 23460, "total_transitions": 96092160, "num_steps_per_env": 1, "wm_loss": 0.5684675574302673, "actor_loss": -8.881629943847656, "critic_loss": 0.0220140740275383, "reward": 0.07052025943994522, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24172604084014893, 0.15649956464767456, 0.2565361559391022], "policy_updates": 23360, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1248.730559176, "contact_bce": 0.3303593397140503, "contact_force_loss": 0.0342118963599205, "terrain_level_mean": 2.875732421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9961212873458862, 0.9973265528678894, 2.998771905899048]} {"step": 23470, "actor_lr": 8.344622025690272e-06, "archive_windows": 100000, "env_steps": 23470, "total_transitions": 96133120, "num_steps_per_env": 1, "wm_loss": 0.5393734574317932, "actor_loss": -8.875387191772461, "critic_loss": 0.023685483261942863, "reward": 0.07088101655244827, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23859639465808868, 0.1558864414691925, 0.25588762760162354], "policy_updates": 23370, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1252.2692857470001, "contact_bce": 0.32903391122817993, "contact_force_loss": 0.03314819559454918, "terrain_level_mean": 2.875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9991347789764404, 0.9973265528678894, 2.998771905899048]} {"step": 23480, "actor_lr": 8.325380054885755e-06, "archive_windows": 100000, "env_steps": 23480, "total_transitions": 96174080, "num_steps_per_env": 1, "wm_loss": 0.5856433510780334, "actor_loss": -8.859382629394531, "critic_loss": 0.01863234117627144, "reward": 0.07109703868627548, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23966942727565765, 0.1577664613723755, 0.25580891966819763], "policy_updates": 23380, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1255.7915995160001, "contact_bce": 0.32481130957603455, "contact_force_loss": 0.03282642737030983, "terrain_level_mean": 2.876220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9991347789764404, 0.9973265528678894, 2.998771905899048]} {"step": 23490, "actor_lr": 8.306162839919888e-06, "archive_windows": 100000, "env_steps": 23490, "total_transitions": 96215040, "num_steps_per_env": 1, "wm_loss": 0.5400862693786621, "actor_loss": -8.876771926879883, "critic_loss": 0.018100908026099205, "reward": 0.07103940099477768, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2420051097869873, 0.15904481709003448, 0.2552548944950104], "policy_updates": 23390, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1259.308370339, "contact_bce": 0.32928118109703064, "contact_force_loss": 0.033172376453876495, "terrain_level_mean": 2.87548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9991347789764404, 0.9973265528678894, 2.998771905899048]} {"step": 23500, "actor_lr": 8.286970401866728e-06, "archive_windows": 100000, "env_steps": 23500, "total_transitions": 96256000, "num_steps_per_env": 1, "wm_loss": 0.552446186542511, "actor_loss": -8.802913665771484, "critic_loss": 0.02707948163151741, "reward": 0.07107429206371307, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23826704919338226, 0.15810051560401917, 0.25322815775871277], "policy_updates": 23400, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1262.834233434, "contact_bce": 0.33301490545272827, "contact_force_loss": 0.033515579998493195, "terrain_level_mean": 2.883544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9991347789764404, 0.9986423254013062, 2.998771905899048]} {"step": 23510, "actor_lr": 8.267802761773128e-06, "archive_windows": 100000, "env_steps": 23510, "total_transitions": 96296960, "num_steps_per_env": 1, "wm_loss": 0.5574589371681213, "actor_loss": -8.817498207092285, "critic_loss": 0.024529878050088882, "reward": 0.06976235657930374, "falls": 4, "interval_steps": 10, "velocity_mae": [0.268899530172348, 0.1523221731185913, 0.26341500878334045], "policy_updates": 23410, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1266.370505364, "contact_bce": 0.3337704837322235, "contact_force_loss": 0.03392152115702629, "terrain_level_mean": 2.884033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9980523586273193, 0.9986423254013062, 2.998771905899048]} {"step": 23520, "actor_lr": 8.248659940658749e-06, "archive_windows": 100000, "env_steps": 23520, "total_transitions": 96337920, "num_steps_per_env": 1, "wm_loss": 0.5394996404647827, "actor_loss": -8.857278823852539, "critic_loss": 0.02494162507355213, "reward": 0.07222511619329453, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23121649026870728, 0.15089280903339386, 0.2479609102010727], "policy_updates": 23420, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1270.125799697, "contact_bce": 0.32314205169677734, "contact_force_loss": 0.033072907477617264, "terrain_level_mean": 2.885009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9980523586273193, 0.9986423254013062, 2.998771905899048]} {"step": 23530, "actor_lr": 8.229541959516067e-06, "archive_windows": 100000, "env_steps": 23530, "total_transitions": 96378880, "num_steps_per_env": 1, "wm_loss": 0.5218889117240906, "actor_loss": -8.886367797851562, "critic_loss": 0.018782248720526695, "reward": 0.07271327823400497, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2219475507736206, 0.14588236808776855, 0.244679257273674], "policy_updates": 23430, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1273.6389192890001, "contact_bce": 0.32863500714302063, "contact_force_loss": 0.0324854776263237, "terrain_level_mean": 2.885498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9980523586273193, 0.9986423254013062, 2.998771905899048]} {"step": 23540, "actor_lr": 8.210448839310263e-06, "archive_windows": 100000, "env_steps": 23540, "total_transitions": 96419840, "num_steps_per_env": 1, "wm_loss": 0.5661647915840149, "actor_loss": -8.861804962158203, "critic_loss": 0.022149844095110893, "reward": 0.07245832681655884, "falls": 6, "interval_steps": 10, "velocity_mae": [0.22203633189201355, 0.1433466225862503, 0.24409990012645721], "policy_updates": 23440, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1277.1546750470002, "contact_bce": 0.32720544934272766, "contact_force_loss": 0.03378884121775627, "terrain_level_mean": 2.885498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9980523586273193, 0.9986423254013062, 2.998771905899048]} {"step": 23550, "actor_lr": 8.19138060097929e-06, "archive_windows": 100000, "env_steps": 23550, "total_transitions": 96460800, "num_steps_per_env": 1, "wm_loss": 0.5310198664665222, "actor_loss": -8.862832069396973, "critic_loss": 0.028044143691658974, "reward": 0.07182084023952484, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22291463613510132, 0.1440519541501999, 0.24637047946453094], "policy_updates": 23450, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1280.6685671, "contact_bce": 0.33003073930740356, "contact_force_loss": 0.03304988145828247, "terrain_level_mean": 2.886474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332275390625, "command_abs_max": [1.9980523586273193, 0.9986423254013062, 2.998771905899048]} {"step": 23560, "actor_lr": 8.17233726543382e-06, "archive_windows": 100000, "env_steps": 23560, "total_transitions": 96501760, "num_steps_per_env": 1, "wm_loss": 0.5268499851226807, "actor_loss": -8.86141586303711, "critic_loss": 0.020486360415816307, "reward": 0.07154429703950882, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22604936361312866, 0.14679592847824097, 0.2519925534725189], "policy_updates": 23460, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1284.17455032, "contact_bce": 0.33029884099960327, "contact_force_loss": 0.033146195113658905, "terrain_level_mean": 2.88671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9980523586273193, 0.9986423254013062, 2.9989755153656006]} {"step": 23570, "actor_lr": 8.153318853557203e-06, "archive_windows": 100000, "env_steps": 23570, "total_transitions": 96542720, "num_steps_per_env": 1, "wm_loss": 0.5319713950157166, "actor_loss": -8.87337875366211, "critic_loss": 0.021680215373635292, "reward": 0.07188964635133743, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23118220269680023, 0.1455034762620926, 0.25128310918807983], "policy_updates": 23470, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1287.7014882120002, "contact_bce": 0.3264525234699249, "contact_force_loss": 0.03325843811035156, "terrain_level_mean": 2.8876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23580, "actor_lr": 8.134325386205454e-06, "archive_windows": 100000, "env_steps": 23580, "total_transitions": 96583680, "num_steps_per_env": 1, "wm_loss": 0.5366138219833374, "actor_loss": -8.879239082336426, "critic_loss": 0.023085257038474083, "reward": 0.07189156860113144, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2302841991186142, 0.14556476473808289, 0.24731509387493134], "policy_updates": 23480, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1291.1990333840001, "contact_bce": 0.325031578540802, "contact_force_loss": 0.03293997421860695, "terrain_level_mean": 2.887451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23590, "actor_lr": 8.115356884207246e-06, "archive_windows": 100000, "env_steps": 23590, "total_transitions": 96624640, "num_steps_per_env": 1, "wm_loss": 0.511069655418396, "actor_loss": -8.846510887145996, "critic_loss": 0.017441486939787865, "reward": 0.07151543349027634, "falls": 6, "interval_steps": 10, "velocity_mae": [0.22986871004104614, 0.14595046639442444, 0.2451624870300293], "policy_updates": 23490, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1294.6994630660001, "contact_bce": 0.32381772994995117, "contact_force_loss": 0.032464027404785156, "terrain_level_mean": 2.886474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23600, "actor_lr": 8.096413368363858e-06, "archive_windows": 100000, "env_steps": 23600, "total_transitions": 96665600, "num_steps_per_env": 1, "wm_loss": 0.5901042222976685, "actor_loss": -8.8738431930542, "critic_loss": 0.02110370807349682, "reward": 0.07190969586372375, "falls": 1, "interval_steps": 10, "velocity_mae": [0.229230135679245, 0.1438874751329422, 0.24330438673496246], "policy_updates": 23500, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1298.216205461, "contact_bce": 0.3239538371562958, "contact_force_loss": 0.03363611176609993, "terrain_level_mean": 2.88720703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23610, "actor_lr": 8.077494859449178e-06, "archive_windows": 100000, "env_steps": 23610, "total_transitions": 96706560, "num_steps_per_env": 1, "wm_loss": 0.5060964226722717, "actor_loss": -8.819202423095703, "critic_loss": 0.027795320376753807, "reward": 0.07152346521615982, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2307508885860443, 0.14576202630996704, 0.2519906163215637], "policy_updates": 23510, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1301.732886424, "contact_bce": 0.32738661766052246, "contact_force_loss": 0.032222021371126175, "terrain_level_mean": 2.88623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327880859375, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23620, "actor_lr": 8.058601378209683e-06, "archive_windows": 100000, "env_steps": 23620, "total_transitions": 96747520, "num_steps_per_env": 1, "wm_loss": 0.5233315229415894, "actor_loss": -8.883365631103516, "critic_loss": 0.02253304421901703, "reward": 0.07106589525938034, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23294828832149506, 0.14884614944458008, 0.2541068196296692], "policy_updates": 23520, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1305.227696249, "contact_bce": 0.32877033948898315, "contact_force_loss": 0.03343936800956726, "terrain_level_mean": 2.886474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330078125, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23630, "actor_lr": 8.039732945364382e-06, "archive_windows": 100000, "env_steps": 23630, "total_transitions": 96788480, "num_steps_per_env": 1, "wm_loss": 0.5471897125244141, "actor_loss": -8.897077560424805, "critic_loss": 0.02524627558887005, "reward": 0.07064508646726608, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23940397799015045, 0.15062183141708374, 0.25634893774986267], "policy_updates": 23530, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1308.752859745, "contact_bce": 0.32893282175064087, "contact_force_loss": 0.03384287655353546, "terrain_level_mean": 2.887939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3291015625, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23640, "actor_lr": 8.020889581604829e-06, "archive_windows": 100000, "env_steps": 23640, "total_transitions": 96829440, "num_steps_per_env": 1, "wm_loss": 0.5132439136505127, "actor_loss": -8.878140449523926, "critic_loss": 0.019314201548695564, "reward": 0.07052996009588242, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24420668184757233, 0.15157602727413177, 0.25784027576446533], "policy_updates": 23540, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1312.284372234, "contact_bce": 0.32965323328971863, "contact_force_loss": 0.03339482843875885, "terrain_level_mean": 2.888427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330322265625, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23650, "actor_lr": 8.002071307595076e-06, "archive_windows": 100000, "env_steps": 23650, "total_transitions": 96870400, "num_steps_per_env": 1, "wm_loss": 0.5442287921905518, "actor_loss": -8.832742691040039, "critic_loss": 0.021583043038845062, "reward": 0.07044915854930878, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2465686798095703, 0.1515427678823471, 0.25846239924430847], "policy_updates": 23550, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1315.811311674, "contact_bce": 0.3270512521266937, "contact_force_loss": 0.033907316625118256, "terrain_level_mean": 2.888427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23660, "actor_lr": 7.98327814397168e-06, "archive_windows": 100000, "env_steps": 23660, "total_transitions": 96911360, "num_steps_per_env": 1, "wm_loss": 0.5303385853767395, "actor_loss": -8.845882415771484, "critic_loss": 0.021109169349074364, "reward": 0.07039977610111237, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24755418300628662, 0.15051311254501343, 0.2557273209095001], "policy_updates": 23560, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1319.332187171, "contact_bce": 0.32738569378852844, "contact_force_loss": 0.03304169699549675, "terrain_level_mean": 2.888427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3310546875, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23670, "actor_lr": 7.96451011134363e-06, "archive_windows": 100000, "env_steps": 23670, "total_transitions": 96952320, "num_steps_per_env": 1, "wm_loss": 0.5098046660423279, "actor_loss": -8.905696868896484, "critic_loss": 0.01698017679154873, "reward": 0.07017403841018677, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24939389526844025, 0.15408743917942047, 0.25414368510246277], "policy_updates": 23570, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1322.845622558, "contact_bce": 0.32840651273727417, "contact_force_loss": 0.03312138468027115, "terrain_level_mean": 2.8876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23680, "actor_lr": 7.945767230292393e-06, "archive_windows": 100000, "env_steps": 23680, "total_transitions": 96993280, "num_steps_per_env": 1, "wm_loss": 0.5375402569770813, "actor_loss": -8.845582962036133, "critic_loss": 0.021396255120635033, "reward": 0.0703534260392189, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24529655277729034, 0.15582969784736633, 0.25579768419265747], "policy_updates": 23580, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1326.356629006, "contact_bce": 0.3242221176624298, "contact_force_loss": 0.03211807832121849, "terrain_level_mean": 2.88916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32763671875, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23690, "actor_lr": 7.92704952137183e-06, "archive_windows": 100000, "env_steps": 23690, "total_transitions": 97034240, "num_steps_per_env": 1, "wm_loss": 0.533317506313324, "actor_loss": -8.856258392333984, "critic_loss": 0.024357840418815613, "reward": 0.07054358720779419, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24372446537017822, 0.15500973165035248, 0.25605425238609314], "policy_updates": 23590, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1329.8740799500001, "contact_bce": 0.3262142241001129, "contact_force_loss": 0.03405740112066269, "terrain_level_mean": 2.889404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327392578125, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23700, "actor_lr": 7.908357005108206e-06, "archive_windows": 100000, "env_steps": 23700, "total_transitions": 97075200, "num_steps_per_env": 1, "wm_loss": 0.5249496698379517, "actor_loss": -8.846787452697754, "critic_loss": 0.028476083651185036, "reward": 0.07082471251487732, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24185049533843994, 0.15202458202838898, 0.2524871230125427], "policy_updates": 23600, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1333.3874579530002, "contact_bce": 0.32670098543167114, "contact_force_loss": 0.03351747989654541, "terrain_level_mean": 2.889892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329833984375, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23710, "actor_lr": 7.889689702000154e-06, "archive_windows": 100000, "env_steps": 23710, "total_transitions": 97116160, "num_steps_per_env": 1, "wm_loss": 0.5598868131637573, "actor_loss": -8.85795783996582, "critic_loss": 0.02587893418967724, "reward": 0.07072900980710983, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24294964969158173, 0.1515074372291565, 0.2546059191226959], "policy_updates": 23610, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1336.895164789, "contact_bce": 0.33197730779647827, "contact_force_loss": 0.034473974257707596, "terrain_level_mean": 2.890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23720, "actor_lr": 7.87104763251866e-06, "archive_windows": 100000, "env_steps": 23720, "total_transitions": 97157120, "num_steps_per_env": 1, "wm_loss": 0.502274215221405, "actor_loss": -8.890932083129883, "critic_loss": 0.022598987445235252, "reward": 0.07123402506113052, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2450973391532898, 0.1521032303571701, 0.2539840042591095], "policy_updates": 23620, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1340.416886469, "contact_bce": 0.3305332064628601, "contact_force_loss": 0.032816722989082336, "terrain_level_mean": 2.890869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330810546875, "command_abs_max": [1.9982962608337402, 0.9986423254013062, 2.9989755153656006]} {"step": 23730, "actor_lr": 7.852430817107034e-06, "archive_windows": 100000, "env_steps": 23730, "total_transitions": 97198080, "num_steps_per_env": 1, "wm_loss": 0.5048704147338867, "actor_loss": -8.859476089477539, "critic_loss": 0.020498139783740044, "reward": 0.07118318974971771, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24734683334827423, 0.1540180891752243, 0.25665056705474854], "policy_updates": 23630, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1343.9479811200001, "contact_bce": 0.3334811329841614, "contact_force_loss": 0.032906994223594666, "terrain_level_mean": 2.892333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9982962608337402, 0.9998511075973511, 2.9989755153656006]} {"step": 23740, "actor_lr": 7.83383927618091e-06, "archive_windows": 100000, "env_steps": 23740, "total_transitions": 97239040, "num_steps_per_env": 1, "wm_loss": 0.5234071612358093, "actor_loss": -8.879300117492676, "critic_loss": 0.024241039529442787, "reward": 0.07098585367202759, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24213255941867828, 0.15441139042377472, 0.2597454786300659], "policy_updates": 23640, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1347.460756937, "contact_bce": 0.32985201478004456, "contact_force_loss": 0.03266282007098198, "terrain_level_mean": 2.892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23750, "actor_lr": 7.815273030128194e-06, "archive_windows": 100000, "env_steps": 23750, "total_transitions": 97280000, "num_steps_per_env": 1, "wm_loss": 0.5376070737838745, "actor_loss": -8.844879150390625, "critic_loss": 0.022897198796272278, "reward": 0.07137962430715561, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24007192254066467, 0.15406768023967743, 0.2578957676887512], "policy_updates": 23650, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1350.981442688, "contact_bce": 0.3257889449596405, "contact_force_loss": 0.03299364075064659, "terrain_level_mean": 2.892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23760, "actor_lr": 7.796732099309025e-06, "archive_windows": 100000, "env_steps": 23760, "total_transitions": 97320960, "num_steps_per_env": 1, "wm_loss": 0.5199811458587646, "actor_loss": -8.86596393585205, "critic_loss": 0.023282906040549278, "reward": 0.07144748419523239, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2399713695049286, 0.15424023568630219, 0.25576403737068176], "policy_updates": 23660, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1354.4971164790002, "contact_bce": 0.3275561034679413, "contact_force_loss": 0.03302667289972305, "terrain_level_mean": 2.893798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23770, "actor_lr": 7.778216504055832e-06, "archive_windows": 100000, "env_steps": 23770, "total_transitions": 97361920, "num_steps_per_env": 1, "wm_loss": 0.4880751669406891, "actor_loss": -8.837881088256836, "critic_loss": 0.024799859151244164, "reward": 0.07119082659482956, "falls": 0, "interval_steps": 10, "velocity_mae": [0.2418530434370041, 0.1565147340297699, 0.26137641072273254], "policy_updates": 23670, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1358.0218271200001, "contact_bce": 0.3264366388320923, "contact_force_loss": 0.03236794471740723, "terrain_level_mean": 2.894775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23780, "actor_lr": 7.75972626467323e-06, "archive_windows": 100000, "env_steps": 23780, "total_transitions": 97402880, "num_steps_per_env": 1, "wm_loss": 0.510381817817688, "actor_loss": -8.84807300567627, "critic_loss": 0.023421287536621094, "reward": 0.07075557857751846, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2444651573896408, 0.15702269971370697, 0.261224627494812], "policy_updates": 23680, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1361.557496462, "contact_bce": 0.3255176246166229, "contact_force_loss": 0.03327327221632004, "terrain_level_mean": 2.895263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23790, "actor_lr": 7.74126140143802e-06, "archive_windows": 100000, "env_steps": 23790, "total_transitions": 97443840, "num_steps_per_env": 1, "wm_loss": 0.5219890475273132, "actor_loss": -8.93190860748291, "critic_loss": 0.016480637714266777, "reward": 0.0711992159485817, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23952311277389526, 0.15740543603897095, 0.25716477632522583], "policy_updates": 23690, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1365.070609139, "contact_bce": 0.3292813003063202, "contact_force_loss": 0.03307558223605156, "terrain_level_mean": 2.89501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23800, "actor_lr": 7.722821934599218e-06, "archive_windows": 100000, "env_steps": 23800, "total_transitions": 97484800, "num_steps_per_env": 1, "wm_loss": 0.5329299569129944, "actor_loss": -8.896988868713379, "critic_loss": 0.023468030616641045, "reward": 0.0711476132273674, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24183860421180725, 0.15456001460552216, 0.25121787190437317], "policy_updates": 23700, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1368.591355401, "contact_bce": 0.32896071672439575, "contact_force_loss": 0.03305770829319954, "terrain_level_mean": 2.8955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23810, "actor_lr": 7.704407884377933e-06, "archive_windows": 100000, "env_steps": 23810, "total_transitions": 97525760, "num_steps_per_env": 1, "wm_loss": 0.5023488998413086, "actor_loss": -8.897858619689941, "critic_loss": 0.020173991098999977, "reward": 0.0708308294415474, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2441084235906601, 0.15688985586166382, 0.2523703873157501], "policy_updates": 23710, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1372.109872536, "contact_bce": 0.33025282621383667, "contact_force_loss": 0.033240146934986115, "terrain_level_mean": 2.893798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23820, "actor_lr": 7.686019270967431e-06, "archive_windows": 100000, "env_steps": 23820, "total_transitions": 97566720, "num_steps_per_env": 1, "wm_loss": 0.5118328332901001, "actor_loss": -8.878687858581543, "critic_loss": 0.024456489831209183, "reward": 0.07068126648664474, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23804393410682678, 0.15746156871318817, 0.2540016770362854], "policy_updates": 23720, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1375.6323379570001, "contact_bce": 0.3259536921977997, "contact_force_loss": 0.0334077812731266, "terrain_level_mean": 2.89404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23830, "actor_lr": 7.667656114533096e-06, "archive_windows": 100000, "env_steps": 23830, "total_transitions": 97607680, "num_steps_per_env": 1, "wm_loss": 0.48490169644355774, "actor_loss": -8.850486755371094, "critic_loss": 0.022864192724227905, "reward": 0.07072671502828598, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2376859486103058, 0.15536202490329742, 0.2531687617301941], "policy_updates": 23730, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1379.1415310450002, "contact_bce": 0.3318445384502411, "contact_force_loss": 0.0329505018889904, "terrain_level_mean": 2.89453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23840, "actor_lr": 7.649318435212373e-06, "archive_windows": 100000, "env_steps": 23840, "total_transitions": 97648640, "num_steps_per_env": 1, "wm_loss": 0.5369086861610413, "actor_loss": -8.805889129638672, "critic_loss": 0.028016988188028336, "reward": 0.07044002413749695, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24120113253593445, 0.1583685278892517, 0.2590353786945343], "policy_updates": 23740, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1382.654994774, "contact_bce": 0.3277866840362549, "contact_force_loss": 0.03282342106103897, "terrain_level_mean": 2.894775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23850, "actor_lr": 7.631006253114773e-06, "archive_windows": 100000, "env_steps": 23850, "total_transitions": 97689600, "num_steps_per_env": 1, "wm_loss": 0.49065423011779785, "actor_loss": -8.858770370483398, "critic_loss": 0.01948375441133976, "reward": 0.07033982127904892, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24275663495063782, 0.15748515725135803, 0.25920724868774414], "policy_updates": 23750, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1386.1735127650002, "contact_bce": 0.3299710750579834, "contact_force_loss": 0.03273969516158104, "terrain_level_mean": 2.8935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329833984375, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23860, "actor_lr": 7.612719588321857e-06, "archive_windows": 100000, "env_steps": 23860, "total_transitions": 97730560, "num_steps_per_env": 1, "wm_loss": 0.5632286667823792, "actor_loss": -8.785811424255371, "critic_loss": 0.026464084163308144, "reward": 0.07093897461891174, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2437543421983719, 0.1566590517759323, 0.2576540410518646], "policy_updates": 23760, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1389.690360943, "contact_bce": 0.3280751407146454, "contact_force_loss": 0.033373378217220306, "terrain_level_mean": 2.893310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331787109375, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23870, "actor_lr": 7.5944584608871835e-06, "archive_windows": 100000, "env_steps": 23870, "total_transitions": 97771520, "num_steps_per_env": 1, "wm_loss": 0.5228033065795898, "actor_loss": -8.87997055053711, "critic_loss": 0.01635686680674553, "reward": 0.07116471976041794, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23921646177768707, 0.15783055126667023, 0.2554120123386383], "policy_updates": 23770, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1393.2129619940001, "contact_bce": 0.3331131041049957, "contact_force_loss": 0.03350343555212021, "terrain_level_mean": 2.893310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23880, "actor_lr": 7.5762228908363165e-06, "archive_windows": 100000, "env_steps": 23880, "total_transitions": 97812480, "num_steps_per_env": 1, "wm_loss": 0.5128549337387085, "actor_loss": -8.823107719421387, "critic_loss": 0.033991530537605286, "reward": 0.07110118120908737, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2405623197555542, 0.15978680551052094, 0.25563928484916687], "policy_updates": 23780, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1396.731979413, "contact_bce": 0.3273574113845825, "contact_force_loss": 0.03275985270738602, "terrain_level_mean": 2.8935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23890, "actor_lr": 7.558012898166815e-06, "archive_windows": 100000, "env_steps": 23890, "total_transitions": 97853440, "num_steps_per_env": 1, "wm_loss": 0.5493541955947876, "actor_loss": -8.897970199584961, "critic_loss": 0.02642745152115822, "reward": 0.07120418548583984, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2383514642715454, 0.15874600410461426, 0.26043686270713806], "policy_updates": 23790, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1400.26178583, "contact_bce": 0.3276797831058502, "contact_force_loss": 0.033846911042928696, "terrain_level_mean": 2.8935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23900, "actor_lr": 7.53982850284815e-06, "archive_windows": 100000, "env_steps": 23900, "total_transitions": 97894400, "num_steps_per_env": 1, "wm_loss": 0.5314697027206421, "actor_loss": -8.830936431884766, "critic_loss": 0.030194897204637527, "reward": 0.07112305611371994, "falls": 5, "interval_steps": 10, "velocity_mae": [0.240500807762146, 0.15773820877075195, 0.257717490196228], "policy_updates": 23800, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1403.778094917, "contact_bce": 0.33227092027664185, "contact_force_loss": 0.03363535925745964, "terrain_level_mean": 2.89306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9999771118164062, 0.9998511075973511, 2.9989755153656006]} {"step": 23910, "actor_lr": 7.521669724821748e-06, "archive_windows": 100000, "env_steps": 23910, "total_transitions": 97935360, "num_steps_per_env": 1, "wm_loss": 0.5241755843162537, "actor_loss": -8.877487182617188, "critic_loss": 0.025098076090216637, "reward": 0.07090416550636292, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24033746123313904, 0.15900035202503204, 0.25776994228363037], "policy_updates": 23810, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1407.3024042650002, "contact_bce": 0.3284549117088318, "contact_force_loss": 0.03367571905255318, "terrain_level_mean": 2.893310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.998786211013794, 0.9998511075973511, 2.9989755153656006]} {"step": 23920, "actor_lr": 7.503536584000935e-06, "archive_windows": 100000, "env_steps": 23920, "total_transitions": 97976320, "num_steps_per_env": 1, "wm_loss": 0.5253093838691711, "actor_loss": -8.88730239868164, "critic_loss": 0.02296552062034607, "reward": 0.07086081057786942, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2437097132205963, 0.15811344981193542, 0.2551088333129883], "policy_updates": 23820, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1410.8191147310001, "contact_bce": 0.33332282304763794, "contact_force_loss": 0.03358818590641022, "terrain_level_mean": 2.89404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.998786211013794, 0.9998511075973511, 2.9948699474334717]} {"step": 23930, "actor_lr": 7.48542910027092e-06, "archive_windows": 100000, "env_steps": 23930, "total_transitions": 98017280, "num_steps_per_env": 1, "wm_loss": 0.5121794939041138, "actor_loss": -8.889403343200684, "critic_loss": 0.019463129341602325, "reward": 0.07082246989011765, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24499838054180145, 0.1571110337972641, 0.25273239612579346], "policy_updates": 23830, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1414.3268815420001, "contact_bce": 0.32877475023269653, "contact_force_loss": 0.03298996388912201, "terrain_level_mean": 2.89404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.998786211013794, 0.9998511075973511, 2.9948699474334717]} {"step": 23940, "actor_lr": 7.467347293488771e-06, "archive_windows": 100000, "env_steps": 23940, "total_transitions": 98058240, "num_steps_per_env": 1, "wm_loss": 0.5047063231468201, "actor_loss": -8.890364646911621, "critic_loss": 0.02122526429593563, "reward": 0.07047437876462936, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2431996613740921, 0.15846019983291626, 0.25713929533958435], "policy_updates": 23840, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1417.8284065940002, "contact_bce": 0.3251183032989502, "contact_force_loss": 0.032818347215652466, "terrain_level_mean": 2.894287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332275390625, "command_abs_max": [1.998786211013794, 0.9998511075973511, 2.9948699474334717]} {"step": 23950, "actor_lr": 7.449291183483427e-06, "archive_windows": 100000, "env_steps": 23950, "total_transitions": 98099200, "num_steps_per_env": 1, "wm_loss": 0.49327823519706726, "actor_loss": -8.844261169433594, "critic_loss": 0.020123083144426346, "reward": 0.07100728154182434, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24019022285938263, 0.15927202999591827, 0.2511783838272095], "policy_updates": 23850, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1421.3313622590001, "contact_bce": 0.329879492521286, "contact_force_loss": 0.03263842314481735, "terrain_level_mean": 2.894775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.998786211013794, 0.9984800815582275, 2.9948699474334717]} {"step": 23960, "actor_lr": 7.431260790055615e-06, "archive_windows": 100000, "env_steps": 23960, "total_transitions": 98140160, "num_steps_per_env": 1, "wm_loss": 0.5043473839759827, "actor_loss": -8.860294342041016, "critic_loss": 0.02716275490820408, "reward": 0.0711197480559349, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23804046213626862, 0.1594545543193817, 0.2524399757385254], "policy_updates": 23860, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1424.8449034540001, "contact_bce": 0.3314147889614105, "contact_force_loss": 0.0337831974029541, "terrain_level_mean": 2.895751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.998786211013794, 0.9984800815582275, 2.994340658187866]} {"step": 23970, "actor_lr": 7.413256132977871e-06, "archive_windows": 100000, "env_steps": 23970, "total_transitions": 98181120, "num_steps_per_env": 1, "wm_loss": 0.5104143023490906, "actor_loss": -8.851316452026367, "critic_loss": 0.02436903677880764, "reward": 0.07102888077497482, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24104158580303192, 0.15761339664459229, 0.2521369457244873], "policy_updates": 23870, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1428.348002664, "contact_bce": 0.3307025730609894, "contact_force_loss": 0.033159300684928894, "terrain_level_mean": 2.896484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.998786211013794, 0.9984800815582275, 2.994340658187866]} {"step": 23980, "actor_lr": 7.395277231994514e-06, "archive_windows": 100000, "env_steps": 23980, "total_transitions": 98222080, "num_steps_per_env": 1, "wm_loss": 0.4984135031700134, "actor_loss": -8.848237991333008, "critic_loss": 0.019927864894270897, "reward": 0.07079776376485825, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24313588440418243, 0.15826527774333954, 0.2498108595609665], "policy_updates": 23880, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1431.863655502, "contact_bce": 0.33133408427238464, "contact_force_loss": 0.033339839428663254, "terrain_level_mean": 2.8955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.998786211013794, 0.9984800815582275, 2.994340658187866]} {"step": 23990, "actor_lr": 7.377324106821607e-06, "archive_windows": 100000, "env_steps": 23990, "total_transitions": 98263040, "num_steps_per_env": 1, "wm_loss": 0.504063069820404, "actor_loss": -8.9210205078125, "critic_loss": 0.017701219767332077, "reward": 0.07096588611602783, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23777052760124207, 0.158003568649292, 0.24984757602214813], "policy_updates": 23890, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1435.3761706080002, "contact_bce": 0.3291691839694977, "contact_force_loss": 0.03350071609020233, "terrain_level_mean": 2.896484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.998786211013794, 0.9984800815582275, 2.9967000484466553]} {"step": 24000, "actor_lr": 7.359396777146953e-06, "archive_windows": 100000, "env_steps": 24000, "total_transitions": 98304000, "num_steps_per_env": 1, "wm_loss": 0.517528235912323, "actor_loss": -8.812516212463379, "critic_loss": 0.021222366020083427, "reward": 0.07142762094736099, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23608583211898804, 0.1557726263999939, 0.2516762614250183], "policy_updates": 23900, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1438.8779344020002, "contact_bce": 0.32822269201278687, "contact_force_loss": 0.03283984214067459, "terrain_level_mean": 2.89794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.999105453491211, 0.9984800815582275, 2.9967000484466553]} {"step": 24010, "actor_lr": 7.341495262630072e-06, "archive_windows": 100000, "env_steps": 24010, "total_transitions": 98344960, "num_steps_per_env": 1, "wm_loss": 0.5195626616477966, "actor_loss": -8.892705917358398, "critic_loss": 0.01883910782635212, "reward": 0.07127976417541504, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2353397011756897, 0.15445123612880707, 0.25200894474983215], "policy_updates": 23910, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1442.431260244, "contact_bce": 0.3317168653011322, "contact_force_loss": 0.03338836133480072, "terrain_level_mean": 2.898193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.999105453491211, 0.9984800815582275, 2.9967000484466553]} {"step": 24020, "actor_lr": 7.323619582902179e-06, "archive_windows": 100000, "env_steps": 24020, "total_transitions": 98385920, "num_steps_per_env": 1, "wm_loss": 0.5221142768859863, "actor_loss": -8.878938674926758, "critic_loss": 0.027629924938082695, "reward": 0.07150624692440033, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2414693683385849, 0.15512414276599884, 0.25156036019325256], "policy_updates": 23920, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1446.211697394, "contact_bce": 0.3269287347793579, "contact_force_loss": 0.03313358500599861, "terrain_level_mean": 2.899658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24030, "actor_lr": 7.3057697575661194e-06, "archive_windows": 100000, "env_steps": 24030, "total_transitions": 98426880, "num_steps_per_env": 1, "wm_loss": 0.5262614488601685, "actor_loss": -8.832210540771484, "critic_loss": 0.021465742960572243, "reward": 0.07156213372945786, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24013899266719818, 0.15580864250659943, 0.2536688446998596], "policy_updates": 23930, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1449.7440106160002, "contact_bce": 0.3283878266811371, "contact_force_loss": 0.03324490413069725, "terrain_level_mean": 2.8984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24040, "actor_lr": 7.287945806196445e-06, "archive_windows": 100000, "env_steps": 24040, "total_transitions": 98467840, "num_steps_per_env": 1, "wm_loss": 0.5360404849052429, "actor_loss": -8.836700439453125, "critic_loss": 0.01906513050198555, "reward": 0.07121812552213669, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24137593805789948, 0.15445347130298615, 0.25820598006248474], "policy_updates": 23940, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1453.263068377, "contact_bce": 0.32655155658721924, "contact_force_loss": 0.0333002544939518, "terrain_level_mean": 2.8974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24050, "actor_lr": 7.270147748339288e-06, "archive_windows": 100000, "env_steps": 24050, "total_transitions": 98508800, "num_steps_per_env": 1, "wm_loss": 0.4944666922092438, "actor_loss": -8.87797737121582, "critic_loss": 0.02138921059668064, "reward": 0.07125940173864365, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2412170022726059, 0.15543623268604279, 0.258574903011322], "policy_updates": 23950, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1456.778994664, "contact_bce": 0.3309311866760254, "contact_force_loss": 0.0327901728451252, "terrain_level_mean": 2.8974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24060, "actor_lr": 7.252375603512398e-06, "archive_windows": 100000, "env_steps": 24060, "total_transitions": 98549760, "num_steps_per_env": 1, "wm_loss": 0.5213810801506042, "actor_loss": -8.879496574401855, "critic_loss": 0.016662241891026497, "reward": 0.07129497081041336, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23785729706287384, 0.1558048576116562, 0.25769707560539246], "policy_updates": 23960, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1460.29909788, "contact_bce": 0.3297547698020935, "contact_force_loss": 0.03439602628350258, "terrain_level_mean": 2.8974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24070, "actor_lr": 7.23462939120513e-06, "archive_windows": 100000, "env_steps": 24070, "total_transitions": 98590720, "num_steps_per_env": 1, "wm_loss": 0.5149933695793152, "actor_loss": -8.871196746826172, "critic_loss": 0.020902110263705254, "reward": 0.07109683007001877, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2382471263408661, 0.1531459540128708, 0.25604715943336487], "policy_updates": 23970, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1463.812703774, "contact_bce": 0.3338431417942047, "contact_force_loss": 0.033367689698934555, "terrain_level_mean": 2.898681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24080, "actor_lr": 7.2169091308783725e-06, "archive_windows": 100000, "env_steps": 24080, "total_transitions": 98631680, "num_steps_per_env": 1, "wm_loss": 0.507810652256012, "actor_loss": -8.906755447387695, "critic_loss": 0.0174969844520092, "reward": 0.07074716687202454, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23653526604175568, 0.1529172956943512, 0.2548496425151825], "policy_updates": 23980, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1467.329453039, "contact_bce": 0.331610769033432, "contact_force_loss": 0.033085018396377563, "terrain_level_mean": 2.900146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24090, "actor_lr": 7.199214841964549e-06, "archive_windows": 100000, "env_steps": 24090, "total_transitions": 98672640, "num_steps_per_env": 1, "wm_loss": 0.5279834270477295, "actor_loss": -8.858833312988281, "critic_loss": 0.02469353750348091, "reward": 0.0705665871500969, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23831883072853088, 0.15408527851104736, 0.2550385594367981], "policy_updates": 23990, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1470.8444191820001, "contact_bce": 0.32768866419792175, "contact_force_loss": 0.03306278586387634, "terrain_level_mean": 2.90087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24100, "actor_lr": 7.1815465438676325e-06, "archive_windows": 100000, "env_steps": 24100, "total_transitions": 98713600, "num_steps_per_env": 1, "wm_loss": 0.5257686972618103, "actor_loss": -8.883398056030273, "critic_loss": 0.02027229778468609, "reward": 0.07111847400665283, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2391856461763382, 0.1539606750011444, 0.25280970335006714], "policy_updates": 24000, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1474.3510972230001, "contact_bce": 0.3309304714202881, "contact_force_loss": 0.03344174474477768, "terrain_level_mean": 2.90234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24110, "actor_lr": 7.163904255963077e-06, "archive_windows": 100000, "env_steps": 24110, "total_transitions": 98754560, "num_steps_per_env": 1, "wm_loss": 0.5486048460006714, "actor_loss": -8.847593307495117, "critic_loss": 0.027359211817383766, "reward": 0.07112252712249756, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23549561202526093, 0.15532530844211578, 0.2537824213504791], "policy_updates": 24010, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1477.8565395940002, "contact_bce": 0.3327992260456085, "contact_force_loss": 0.03397158905863762, "terrain_level_mean": 2.902587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24120, "actor_lr": 7.146287997597802e-06, "archive_windows": 100000, "env_steps": 24120, "total_transitions": 98795520, "num_steps_per_env": 1, "wm_loss": 0.5000579953193665, "actor_loss": -8.849493026733398, "critic_loss": 0.019878912717103958, "reward": 0.07147330790758133, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23372536897659302, 0.15608160197734833, 0.25230544805526733], "policy_updates": 24020, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1481.387048499, "contact_bce": 0.3308396637439728, "contact_force_loss": 0.032762885093688965, "terrain_level_mean": 2.903076171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24130, "actor_lr": 7.128697788090222e-06, "archive_windows": 100000, "env_steps": 24130, "total_transitions": 98836480, "num_steps_per_env": 1, "wm_loss": 0.49529731273651123, "actor_loss": -8.821107864379883, "critic_loss": 0.02355760708451271, "reward": 0.07140284031629562, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24135570228099823, 0.15463536977767944, 0.25289908051490784], "policy_updates": 24030, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1484.892586705, "contact_bce": 0.332817941904068, "contact_force_loss": 0.03252696245908737, "terrain_level_mean": 2.903076171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24140, "actor_lr": 7.111133646730132e-06, "archive_windows": 100000, "env_steps": 24140, "total_transitions": 98877440, "num_steps_per_env": 1, "wm_loss": 0.4924219250679016, "actor_loss": -8.861732482910156, "critic_loss": 0.020170580595731735, "reward": 0.07152044028043747, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24060867726802826, 0.151805579662323, 0.2532062232494354], "policy_updates": 24040, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1488.391708516, "contact_bce": 0.33010903000831604, "contact_force_loss": 0.03331726789474487, "terrain_level_mean": 2.902099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35888671875, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24150, "actor_lr": 7.093595592778767e-06, "archive_windows": 100000, "env_steps": 24150, "total_transitions": 98918400, "num_steps_per_env": 1, "wm_loss": 0.49425458908081055, "actor_loss": -8.83974552154541, "critic_loss": 0.02719520404934883, "reward": 0.07115404307842255, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2403639554977417, 0.15101554989814758, 0.2511889934539795], "policy_updates": 24050, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1491.896422402, "contact_bce": 0.33014559745788574, "contact_force_loss": 0.03300832211971283, "terrain_level_mean": 2.9033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.362548828125, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24160, "actor_lr": 7.0760836454687715e-06, "archive_windows": 100000, "env_steps": 24160, "total_transitions": 98959360, "num_steps_per_env": 1, "wm_loss": 0.528085470199585, "actor_loss": -8.863815307617188, "critic_loss": 0.019556013867259026, "reward": 0.07084154337644577, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23673385381698608, 0.15231899917125702, 0.25200045108795166], "policy_updates": 24060, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1495.4009993060001, "contact_bce": 0.3326639235019684, "contact_force_loss": 0.03372977674007416, "terrain_level_mean": 2.90234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361083984375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24170, "actor_lr": 7.058597824004132e-06, "archive_windows": 100000, "env_steps": 24170, "total_transitions": 99000320, "num_steps_per_env": 1, "wm_loss": 0.5437769889831543, "actor_loss": -8.81298828125, "critic_loss": 0.020674491301178932, "reward": 0.07094766944646835, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23204198479652405, 0.15167611837387085, 0.24963369965553284], "policy_updates": 24070, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1498.906920843, "contact_bce": 0.33396968245506287, "contact_force_loss": 0.03356451541185379, "terrain_level_mean": 2.90283203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.360107421875, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24180, "actor_lr": 7.041138147560199e-06, "archive_windows": 100000, "env_steps": 24180, "total_transitions": 99041280, "num_steps_per_env": 1, "wm_loss": 0.49642714858055115, "actor_loss": -8.867359161376953, "critic_loss": 0.02390287257730961, "reward": 0.07091070711612701, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23263436555862427, 0.1506645232439041, 0.25487858057022095], "policy_updates": 24080, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1502.4076082410002, "contact_bce": 0.32688337564468384, "contact_force_loss": 0.03271593898534775, "terrain_level_mean": 2.90380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24190, "actor_lr": 7.023704635283645e-06, "archive_windows": 100000, "env_steps": 24190, "total_transitions": 99082240, "num_steps_per_env": 1, "wm_loss": 0.5208593010902405, "actor_loss": -8.858454704284668, "critic_loss": 0.016094861552119255, "reward": 0.07116366177797318, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23466193675994873, 0.1484944075345993, 0.25693657994270325], "policy_updates": 24090, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1505.9125643880002, "contact_bce": 0.33048632740974426, "contact_force_loss": 0.03338126465678215, "terrain_level_mean": 2.905517578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.9967000484466553]} {"step": 24200, "actor_lr": 7.006297306292454e-06, "archive_windows": 100000, "env_steps": 24200, "total_transitions": 99123200, "num_steps_per_env": 1, "wm_loss": 0.5219599604606628, "actor_loss": -8.856828689575195, "critic_loss": 0.026909977197647095, "reward": 0.0709867775440216, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23717567324638367, 0.15309706330299377, 0.25733670592308044], "policy_updates": 24100, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1509.4273334640002, "contact_bce": 0.3260859549045563, "contact_force_loss": 0.033913470804691315, "terrain_level_mean": 2.906005859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3583984375, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.997731924057007]} {"step": 24210, "actor_lr": 6.988916179675893e-06, "archive_windows": 100000, "env_steps": 24210, "total_transitions": 99164160, "num_steps_per_env": 1, "wm_loss": 0.5729789733886719, "actor_loss": -8.877153396606445, "critic_loss": 0.017156636342406273, "reward": 0.0708608627319336, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2390098124742508, 0.15467019379138947, 0.2580101788043976], "policy_updates": 24110, "skipped_updates": 0, "invalid_env_resets": 9, "elapsed_s": 1512.940627635, "contact_bce": 0.3270377814769745, "contact_force_loss": 0.034325793385505676, "terrain_level_mean": 2.906005859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.997731924057007]} RECOVERY reset 1 invalid environments; first IDs=[838] {"step": 24220, "actor_lr": 6.971561274494509e-06, "archive_windows": 100000, "env_steps": 24220, "total_transitions": 99205120, "num_steps_per_env": 1, "wm_loss": 0.5052198767662048, "actor_loss": -8.894927978515625, "critic_loss": 0.02116621844470501, "reward": 0.0709705501794815, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23905980587005615, 0.15295355021953583, 0.25898003578186035], "policy_updates": 24120, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1516.4734157960002, "contact_bce": 0.3272993862628937, "contact_force_loss": 0.033108439296483994, "terrain_level_mean": 2.905029296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.997731924057007]} {"step": 24230, "actor_lr": 6.9542326097800795e-06, "archive_windows": 100000, "env_steps": 24230, "total_transitions": 99246080, "num_steps_per_env": 1, "wm_loss": 0.5076190233230591, "actor_loss": -8.84591293334961, "critic_loss": 0.016104120761156082, "reward": 0.07092004269361496, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23391640186309814, 0.1510244607925415, 0.2543734610080719], "policy_updates": 24130, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1519.9755649390002, "contact_bce": 0.32861578464508057, "contact_force_loss": 0.03284216299653053, "terrain_level_mean": 2.905517578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36181640625, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.997731924057007]} {"step": 24240, "actor_lr": 6.936930204535605e-06, "archive_windows": 100000, "env_steps": 24240, "total_transitions": 99287040, "num_steps_per_env": 1, "wm_loss": 0.5094552040100098, "actor_loss": -8.839814186096191, "critic_loss": 0.027635881677269936, "reward": 0.07134654372930527, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23413799703121185, 0.15205985307693481, 0.25201842188835144], "policy_updates": 24140, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1523.4814796780001, "contact_bce": 0.32749179005622864, "contact_force_loss": 0.032854944467544556, "terrain_level_mean": 2.90625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36328125, "command_abs_max": [1.999701976776123, 0.9984800815582275, 2.997731924057007]} {"step": 24250, "actor_lr": 6.9196540777353e-06, "archive_windows": 100000, "env_steps": 24250, "total_transitions": 99328000, "num_steps_per_env": 1, "wm_loss": 0.5323660373687744, "actor_loss": -8.866458892822266, "critic_loss": 0.02638993225991726, "reward": 0.07104962319135666, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23624975979328156, 0.1554398387670517, 0.25476783514022827], "policy_updates": 24150, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1526.990705093, "contact_bce": 0.3304755985736847, "contact_force_loss": 0.03399626165628433, "terrain_level_mean": 2.90625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361083984375, "command_abs_max": [1.999701976776123, 0.999030590057373, 2.997731924057007]} {"step": 24260, "actor_lr": 6.902404248324552e-06, "archive_windows": 100000, "env_steps": 24260, "total_transitions": 99368960, "num_steps_per_env": 1, "wm_loss": 0.5181485414505005, "actor_loss": -8.890958786010742, "critic_loss": 0.020594188943505287, "reward": 0.07122965902090073, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2375248670578003, 0.15397244691848755, 0.253252238035202], "policy_updates": 24160, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1530.506344054, "contact_bce": 0.3338852822780609, "contact_force_loss": 0.03370937705039978, "terrain_level_mean": 2.9072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3603515625, "command_abs_max": [1.999701976776123, 0.999030590057373, 2.997731924057007]} {"step": 24270, "actor_lr": 6.885180735219919e-06, "archive_windows": 100000, "env_steps": 24270, "total_transitions": 99409920, "num_steps_per_env": 1, "wm_loss": 0.5287923812866211, "actor_loss": -8.854789733886719, "critic_loss": 0.022309506312012672, "reward": 0.07110408693552017, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23581121861934662, 0.15532562136650085, 0.25642919540405273], "policy_updates": 24170, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1534.02826841, "contact_bce": 0.32706576585769653, "contact_force_loss": 0.032927561551332474, "terrain_level_mean": 2.908935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.999701976776123, 0.999030590057373, 2.997731924057007]} {"step": 24280, "actor_lr": 6.86798355730908e-06, "archive_windows": 100000, "env_steps": 24280, "total_transitions": 99450880, "num_steps_per_env": 1, "wm_loss": 0.49766796827316284, "actor_loss": -8.85623836517334, "critic_loss": 0.020216718316078186, "reward": 0.07107959687709808, "falls": 0, "interval_steps": 10, "velocity_mae": [0.23385636508464813, 0.15456606447696686, 0.2521205544471741], "policy_updates": 24180, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1537.5443200930001, "contact_bce": 0.3255710303783417, "contact_force_loss": 0.03364432603120804, "terrain_level_mean": 2.91015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.999701976776123, 0.999030590057373, 2.997731924057007]} {"step": 24290, "actor_lr": 6.85081273345087e-06, "archive_windows": 100000, "env_steps": 24290, "total_transitions": 99491840, "num_steps_per_env": 1, "wm_loss": 0.526408314704895, "actor_loss": -8.82762336730957, "critic_loss": 0.02439970150589943, "reward": 0.07070385664701462, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2359815388917923, 0.15487749874591827, 0.25562724471092224], "policy_updates": 24190, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1541.0731779720002, "contact_bce": 0.3251585066318512, "contact_force_loss": 0.03349515423178673, "terrain_level_mean": 2.9091796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.999701976776123, 0.999030590057373, 2.997731924057007]} {"step": 24300, "actor_lr": 6.833668282475197e-06, "archive_windows": 100000, "env_steps": 24300, "total_transitions": 99532800, "num_steps_per_env": 1, "wm_loss": 0.5061514377593994, "actor_loss": -8.826725006103516, "critic_loss": 0.04096605256199837, "reward": 0.07116439193487167, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23670579493045807, 0.15296705067157745, 0.2543136775493622], "policy_updates": 24200, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1544.593337123, "contact_bce": 0.33121609687805176, "contact_force_loss": 0.03358549624681473, "terrain_level_mean": 2.909423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.999701976776123, 0.999030590057373, 2.997731924057007]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_024300.mp4 {"step": 24310, "actor_lr": 6.816550223183038e-06, "archive_windows": 100000, "env_steps": 24310, "total_transitions": 99573760, "num_steps_per_env": 1, "wm_loss": 0.5261231660842896, "actor_loss": -8.84506893157959, "critic_loss": 0.025644628331065178, "reward": 0.07133188843727112, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23739339411258698, 0.1535567343235016, 0.2535848319530487], "policy_updates": 24210, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1553.8665667070002, "contact_bce": 0.32391977310180664, "contact_force_loss": 0.032864928245544434, "terrain_level_mean": 2.909912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.999701976776123, 0.9997283220291138, 2.997731924057007]} {"step": 24320, "actor_lr": 6.799458574346462e-06, "archive_windows": 100000, "env_steps": 24320, "total_transitions": 99614720, "num_steps_per_env": 1, "wm_loss": 0.5074530839920044, "actor_loss": -8.877724647521973, "critic_loss": 0.023020340129733086, "reward": 0.07178047299385071, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2364911139011383, 0.15202903747558594, 0.2506747245788574], "policy_updates": 24220, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1557.391777081, "contact_bce": 0.3288627564907074, "contact_force_loss": 0.032997388392686844, "terrain_level_mean": 2.910888671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.999701976776123, 0.9997283220291138, 2.997731924057007]} {"step": 24330, "actor_lr": 6.782393354708553e-06, "archive_windows": 100000, "env_steps": 24330, "total_transitions": 99655680, "num_steps_per_env": 1, "wm_loss": 0.502628743648529, "actor_loss": -8.843619346618652, "critic_loss": 0.02306397259235382, "reward": 0.07128799706697464, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23811735212802887, 0.1531558632850647, 0.25525128841400146], "policy_updates": 24230, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1560.9125812690002, "contact_bce": 0.32638847827911377, "contact_force_loss": 0.032370567321777344, "terrain_level_mean": 2.91064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.999701976776123, 0.9997283220291138, 2.997731924057007]} {"step": 24340, "actor_lr": 6.765354582983405e-06, "archive_windows": 100000, "env_steps": 24340, "total_transitions": 99696640, "num_steps_per_env": 1, "wm_loss": 0.5038784146308899, "actor_loss": -8.802696228027344, "critic_loss": 0.041733190417289734, "reward": 0.07117438316345215, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24269622564315796, 0.15244628489017487, 0.25454050302505493], "policy_updates": 24240, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1564.506359611, "contact_bce": 0.3257351517677307, "contact_force_loss": 0.032183945178985596, "terrain_level_mean": 2.910888671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999701976776123, 0.9997283220291138, 2.997731924057007]} {"step": 24350, "actor_lr": 6.748342277856147e-06, "archive_windows": 100000, "env_steps": 24350, "total_transitions": 99737600, "num_steps_per_env": 1, "wm_loss": 0.5000408291816711, "actor_loss": -8.893705368041992, "critic_loss": 0.02478463016450405, "reward": 0.07120699435472488, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24241524934768677, 0.155533105134964, 0.25526174902915955], "policy_updates": 24250, "skipped_updates": 0, "invalid_env_resets": 10, "elapsed_s": 1568.1382810970001, "contact_bce": 0.3294486701488495, "contact_force_loss": 0.03284134715795517, "terrain_level_mean": 2.912353515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.999701976776123, 0.9997283220291138, 2.997731924057007]} RECOVERY reset 1 invalid environments; first IDs=[2919] {"step": 24360, "actor_lr": 6.731356457982829e-06, "archive_windows": 100000, "env_steps": 24360, "total_transitions": 99778560, "num_steps_per_env": 1, "wm_loss": 0.5510674118995667, "actor_loss": -8.883821487426758, "critic_loss": 0.021810371428728104, "reward": 0.07121681421995163, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24023179709911346, 0.1559830904006958, 0.2544238865375519], "policy_updates": 24260, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1571.797947428, "contact_bce": 0.3305080831050873, "contact_force_loss": 0.033779796212911606, "terrain_level_mean": 2.913330078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.999701976776123, 0.9997283220291138, 2.997731924057007]} {"step": 24370, "actor_lr": 6.714397141990493e-06, "archive_windows": 100000, "env_steps": 24370, "total_transitions": 99819520, "num_steps_per_env": 1, "wm_loss": 0.5099210739135742, "actor_loss": -8.87080192565918, "critic_loss": 0.02530265413224697, "reward": 0.07107865065336227, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2404940277338028, 0.15919695794582367, 0.256854772567749], "policy_updates": 24270, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1575.372963145, "contact_bce": 0.32768741250038147, "contact_force_loss": 0.033166926354169846, "terrain_level_mean": 2.911376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.999701976776123, 0.9997283220291138, 2.997731924057007]} {"step": 24380, "actor_lr": 6.697464348477119e-06, "archive_windows": 100000, "env_steps": 24380, "total_transitions": 99860480, "num_steps_per_env": 1, "wm_loss": 0.5091060996055603, "actor_loss": -8.851005554199219, "critic_loss": 0.017543509602546692, "reward": 0.0714196190237999, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2393854409456253, 0.16039574146270752, 0.2551625669002533], "policy_updates": 24280, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1578.91683171, "contact_bce": 0.3292126953601837, "contact_force_loss": 0.03273363038897514, "terrain_level_mean": 2.909912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9987080097198486, 0.9997283220291138, 2.997731924057007]} {"step": 24390, "actor_lr": 6.680558096011586e-06, "archive_windows": 100000, "env_steps": 24390, "total_transitions": 99901440, "num_steps_per_env": 1, "wm_loss": 0.5083034634590149, "actor_loss": -8.815398216247559, "critic_loss": 0.024832507595419884, "reward": 0.07156550139188766, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23914867639541626, 0.15819835662841797, 0.2575525939464569], "policy_updates": 24290, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1582.453070536, "contact_bce": 0.32564032077789307, "contact_force_loss": 0.03343623876571655, "terrain_level_mean": 2.909423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9987080097198486, 0.9997283220291138, 2.997731924057007]} {"step": 24400, "actor_lr": 6.663678403133668e-06, "archive_windows": 100000, "env_steps": 24400, "total_transitions": 99942400, "num_steps_per_env": 1, "wm_loss": 0.5293903350830078, "actor_loss": -8.844274520874023, "critic_loss": 0.024104440584778786, "reward": 0.07128936052322388, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24222126603126526, 0.1587972193956375, 0.25596654415130615], "policy_updates": 24300, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1586.0140027930001, "contact_bce": 0.3265700936317444, "contact_force_loss": 0.033816054463386536, "terrain_level_mean": 2.909912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9987080097198486, 0.9997283220291138, 2.997731924057007]} {"step": 24410, "actor_lr": 6.646825288354025e-06, "archive_windows": 100000, "env_steps": 24410, "total_transitions": 99983360, "num_steps_per_env": 1, "wm_loss": 0.5000911355018616, "actor_loss": -8.825119018554688, "critic_loss": 0.02382032386958599, "reward": 0.0711071640253067, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24065899848937988, 0.15754340589046478, 0.2574511766433716], "policy_updates": 24310, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1589.576041134, "contact_bce": 0.3195672631263733, "contact_force_loss": 0.031724072992801666, "terrain_level_mean": 2.9091796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} {"step": 24420, "actor_lr": 6.629998770154156e-06, "archive_windows": 100000, "env_steps": 24420, "total_transitions": 100024320, "num_steps_per_env": 1, "wm_loss": 0.48838987946510315, "actor_loss": -8.833343505859375, "critic_loss": 0.024539262056350708, "reward": 0.07089116424322128, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24049308896064758, 0.15765318274497986, 0.26069176197052], "policy_updates": 24320, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1593.113776528, "contact_bce": 0.3263418674468994, "contact_force_loss": 0.032477203756570816, "terrain_level_mean": 2.908935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} {"step": 24430, "actor_lr": 6.613198866986398e-06, "archive_windows": 100000, "env_steps": 24430, "total_transitions": 100065280, "num_steps_per_env": 1, "wm_loss": 0.5421789288520813, "actor_loss": -8.880475997924805, "critic_loss": 0.022068936377763748, "reward": 0.07102499902248383, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23953485488891602, 0.16096848249435425, 0.2597646713256836], "policy_updates": 24330, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1596.6474927900001, "contact_bce": 0.3322747051715851, "contact_force_loss": 0.03347918763756752, "terrain_level_mean": 2.90966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} {"step": 24440, "actor_lr": 6.596425597273919e-06, "archive_windows": 100000, "env_steps": 24440, "total_transitions": 100106240, "num_steps_per_env": 1, "wm_loss": 0.5154905319213867, "actor_loss": -8.894956588745117, "critic_loss": 0.022746732458472252, "reward": 0.07087630778551102, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2386644333600998, 0.1598249077796936, 0.26012128591537476], "policy_updates": 24340, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1600.1901784620002, "contact_bce": 0.3286573588848114, "contact_force_loss": 0.032929304987192154, "terrain_level_mean": 2.9091796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} {"step": 24450, "actor_lr": 6.579678979410662e-06, "archive_windows": 100000, "env_steps": 24450, "total_transitions": 100147200, "num_steps_per_env": 1, "wm_loss": 0.5110573768615723, "actor_loss": -8.840519905090332, "critic_loss": 0.023453662171959877, "reward": 0.07069481164216995, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2398151159286499, 0.1590319722890854, 0.25821128487586975], "policy_updates": 24350, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1603.721298314, "contact_bce": 0.321837455034256, "contact_force_loss": 0.03298880159854889, "terrain_level_mean": 2.9091796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} Warning: EPA horizon = 24 isn't large enough. {"step": 24460, "actor_lr": 6.562959031761341e-06, "archive_windows": 100000, "env_steps": 24460, "total_transitions": 100188160, "num_steps_per_env": 1, "wm_loss": 0.5295277237892151, "actor_loss": -8.831400871276855, "critic_loss": 0.025486022233963013, "reward": 0.07112818956375122, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23603780567646027, 0.15646369755268097, 0.2513268291950226], "policy_updates": 24360, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1607.23624799, "contact_bce": 0.3279101550579071, "contact_force_loss": 0.03313717618584633, "terrain_level_mean": 2.909912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} {"step": 24470, "actor_lr": 6.5462657726614305e-06, "archive_windows": 100000, "env_steps": 24470, "total_transitions": 100229120, "num_steps_per_env": 1, "wm_loss": 0.5274124145507812, "actor_loss": -8.86332893371582, "critic_loss": 0.018597211688756943, "reward": 0.07112958282232285, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23744167387485504, 0.15572910010814667, 0.2511290907859802], "policy_updates": 24370, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1610.760947059, "contact_bce": 0.32410743832588196, "contact_force_loss": 0.03258573263883591, "terrain_level_mean": 2.911376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} {"step": 24480, "actor_lr": 6.529599220417135e-06, "archive_windows": 100000, "env_steps": 24480, "total_transitions": 100270080, "num_steps_per_env": 1, "wm_loss": 0.5023813247680664, "actor_loss": -8.82958698272705, "critic_loss": 0.02857990376651287, "reward": 0.07099761068820953, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23736999928951263, 0.15813997387886047, 0.25128570199012756], "policy_updates": 24380, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1614.2676093530001, "contact_bce": 0.32904374599456787, "contact_force_loss": 0.03349488973617554, "terrain_level_mean": 2.911865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9967892169952393, 0.9997283220291138, 2.997731924057007]} {"step": 24490, "actor_lr": 6.512959393305371e-06, "archive_windows": 100000, "env_steps": 24490, "total_transitions": 100311040, "num_steps_per_env": 1, "wm_loss": 0.5242812037467957, "actor_loss": -8.88235092163086, "critic_loss": 0.02230219729244709, "reward": 0.07081425189971924, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24006496369838715, 0.15800906717777252, 0.2548214793205261], "policy_updates": 24390, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1617.807122206, "contact_bce": 0.32452288269996643, "contact_force_loss": 0.03277914598584175, "terrain_level_mean": 2.911865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.997649908065796, 0.9997283220291138, 2.997731924057007]} {"step": 24500, "actor_lr": 6.4963463095737565e-06, "archive_windows": 100000, "env_steps": 24500, "total_transitions": 100352000, "num_steps_per_env": 1, "wm_loss": 0.518595278263092, "actor_loss": -8.859333992004395, "critic_loss": 0.018956584855914116, "reward": 0.07046494632959366, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2379606068134308, 0.15674544870853424, 0.25691086053848267], "policy_updates": 24400, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1621.3288890850001, "contact_bce": 0.3255545496940613, "contact_force_loss": 0.03276059404015541, "terrain_level_mean": 2.91357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.997649908065796, 0.9993411302566528, 2.997731924057007]} {"step": 24510, "actor_lr": 6.4797599874405715e-06, "archive_windows": 100000, "env_steps": 24510, "total_transitions": 100392960, "num_steps_per_env": 1, "wm_loss": 0.5235282182693481, "actor_loss": -8.804945945739746, "critic_loss": 0.025971174240112305, "reward": 0.07063186168670654, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23794712126255035, 0.15574581921100616, 0.25379201769828796], "policy_updates": 24410, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1624.891126765, "contact_bce": 0.3289431035518646, "contact_force_loss": 0.03276889771223068, "terrain_level_mean": 2.9130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.997649908065796, 0.9993411302566528, 2.997731924057007]} {"step": 24520, "actor_lr": 6.463200445094749e-06, "archive_windows": 100000, "env_steps": 24520, "total_transitions": 100433920, "num_steps_per_env": 1, "wm_loss": 0.49668124318122864, "actor_loss": -8.82571792602539, "critic_loss": 0.028832385316491127, "reward": 0.07127109915018082, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23899129033088684, 0.15546482801437378, 0.2501310706138611], "policy_updates": 24420, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1628.68860509, "contact_bce": 0.32857546210289, "contact_force_loss": 0.03349493443965912, "terrain_level_mean": 2.914306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.997649908065796, 0.9993411302566528, 2.997464418411255]} {"step": 24530, "actor_lr": 6.446667700695859e-06, "archive_windows": 100000, "env_steps": 24530, "total_transitions": 100474880, "num_steps_per_env": 1, "wm_loss": 0.5354534387588501, "actor_loss": -8.852653503417969, "critic_loss": 0.028934448957443237, "reward": 0.0713929757475853, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2423221319913864, 0.15529191493988037, 0.2542411684989929], "policy_updates": 24430, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1632.205555685, "contact_bce": 0.3334481716156006, "contact_force_loss": 0.033678799867630005, "terrain_level_mean": 2.915771484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.997649908065796, 0.9993411302566528, 2.997464418411255]} {"step": 24540, "actor_lr": 6.430161772374084e-06, "archive_windows": 100000, "env_steps": 24540, "total_transitions": 100515840, "num_steps_per_env": 1, "wm_loss": 0.5259372591972351, "actor_loss": -8.837193489074707, "critic_loss": 0.02430023066699505, "reward": 0.07124310731887817, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24417240917682648, 0.15671512484550476, 0.25552478432655334], "policy_updates": 24440, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1635.7201346450001, "contact_bce": 0.3269844651222229, "contact_force_loss": 0.032582804560661316, "terrain_level_mean": 2.916748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.997649908065796, 0.9993411302566528, 2.997464418411255]} {"step": 24550, "actor_lr": 6.41368267823019e-06, "archive_windows": 100000, "env_steps": 24550, "total_transitions": 100556800, "num_steps_per_env": 1, "wm_loss": 0.5057621598243713, "actor_loss": -8.852839469909668, "critic_loss": 0.0187835730612278, "reward": 0.07110656797885895, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2418840229511261, 0.15597350895404816, 0.25554150342941284], "policy_updates": 24450, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1639.2345692840001, "contact_bce": 0.32933366298675537, "contact_force_loss": 0.032906871289014816, "terrain_level_mean": 2.916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.997649908065796, 0.9993411302566528, 2.997464418411255]} {"step": 24560, "actor_lr": 6.397230436335542e-06, "archive_windows": 100000, "env_steps": 24560, "total_transitions": 100597760, "num_steps_per_env": 1, "wm_loss": 0.5695585012435913, "actor_loss": -8.853199005126953, "critic_loss": 0.02224770002067089, "reward": 0.07092081755399704, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23985441029071808, 0.15719863772392273, 0.25694864988327026], "policy_updates": 24460, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1642.7596339640002, "contact_bce": 0.32485684752464294, "contact_force_loss": 0.033675383776426315, "terrain_level_mean": 2.91796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.997464418411255]} {"step": 24570, "actor_lr": 6.380805064732035e-06, "archive_windows": 100000, "env_steps": 24570, "total_transitions": 100638720, "num_steps_per_env": 1, "wm_loss": 0.5147171020507812, "actor_loss": -8.83055305480957, "critic_loss": 0.02737012878060341, "reward": 0.0711265429854393, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2358381450176239, 0.15791870653629303, 0.25491344928741455], "policy_updates": 24470, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1646.2798206710002, "contact_bce": 0.3258143663406372, "contact_force_loss": 0.03341076523065567, "terrain_level_mean": 2.91796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.997464418411255]} {"step": 24580, "actor_lr": 6.364406581432081e-06, "archive_windows": 100000, "env_steps": 24580, "total_transitions": 100679680, "num_steps_per_env": 1, "wm_loss": 0.47842416167259216, "actor_loss": -8.879247665405273, "critic_loss": 0.0173167884349823, "reward": 0.07021386921405792, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23908944427967072, 0.16234073042869568, 0.25480028986930847], "policy_updates": 24480, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1649.784704486, "contact_bce": 0.3196645677089691, "contact_force_loss": 0.03227106109261513, "terrain_level_mean": 2.917724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.997464418411255]} {"step": 24590, "actor_lr": 6.348035004418656e-06, "archive_windows": 100000, "env_steps": 24590, "total_transitions": 100720640, "num_steps_per_env": 1, "wm_loss": 0.522721529006958, "actor_loss": -8.862678527832031, "critic_loss": 0.02838088385760784, "reward": 0.07047590613365173, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24043048918247223, 0.15927013754844666, 0.2507440447807312], "policy_updates": 24490, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1653.308991325, "contact_bce": 0.33032700419425964, "contact_force_loss": 0.034655340015888214, "terrain_level_mean": 2.916748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.997464418411255]} {"step": 24600, "actor_lr": 6.331690351645187e-06, "archive_windows": 100000, "env_steps": 24600, "total_transitions": 100761600, "num_steps_per_env": 1, "wm_loss": 0.5082176327705383, "actor_loss": -8.812591552734375, "critic_loss": 0.0334477536380291, "reward": 0.07092135399580002, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23831221461296082, 0.16016699373722076, 0.2556048035621643], "policy_updates": 24500, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1656.82197648, "contact_bce": 0.3226293921470642, "contact_force_loss": 0.03257719427347183, "terrain_level_mean": 2.91796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.997464418411255]} {"step": 24610, "actor_lr": 6.315372641035587e-06, "archive_windows": 100000, "env_steps": 24610, "total_transitions": 100802560, "num_steps_per_env": 1, "wm_loss": 0.5181183218955994, "actor_loss": -8.862224578857422, "critic_loss": 0.01713690161705017, "reward": 0.0711289644241333, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24039122462272644, 0.16019366681575775, 0.25032132863998413], "policy_updates": 24510, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1660.3500067670002, "contact_bce": 0.3306374251842499, "contact_force_loss": 0.03328501433134079, "terrain_level_mean": 2.918212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.997464418411255]} {"step": 24620, "actor_lr": 6.299081890484247e-06, "archive_windows": 100000, "env_steps": 24620, "total_transitions": 100843520, "num_steps_per_env": 1, "wm_loss": 0.4733262360095978, "actor_loss": -8.894092559814453, "critic_loss": 0.024361902847886086, "reward": 0.07062868028879166, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24382352828979492, 0.16137832403182983, 0.2549305260181427], "policy_updates": 24520, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1663.872348265, "contact_bce": 0.325633704662323, "contact_force_loss": 0.0316975973546505, "terrain_level_mean": 2.91748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.997464418411255]} {"step": 24630, "actor_lr": 6.2828181178559494e-06, "archive_windows": 100000, "env_steps": 24630, "total_transitions": 100884480, "num_steps_per_env": 1, "wm_loss": 0.5290346145629883, "actor_loss": -8.86068058013916, "critic_loss": 0.016157666221261024, "reward": 0.07061871141195297, "falls": 5, "interval_steps": 10, "velocity_mae": [0.242695152759552, 0.1625397652387619, 0.25873836874961853], "policy_updates": 24530, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1667.4179061300001, "contact_bce": 0.3223336935043335, "contact_force_loss": 0.03310014307498932, "terrain_level_mean": 2.91748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.9947032928466797]} {"step": 24640, "actor_lr": 6.266581340985915e-06, "archive_windows": 100000, "env_steps": 24640, "total_transitions": 100925440, "num_steps_per_env": 1, "wm_loss": 0.5589993000030518, "actor_loss": -8.864620208740234, "critic_loss": 0.0170912966132164, "reward": 0.07098980993032455, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2421724945306778, 0.16373281180858612, 0.2569679319858551], "policy_updates": 24540, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1670.927643274, "contact_bce": 0.33050867915153503, "contact_force_loss": 0.03341802954673767, "terrain_level_mean": 2.91748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9987783432006836, 0.9993411302566528, 2.9947032928466797]} {"step": 24650, "actor_lr": 6.250371577679777e-06, "archive_windows": 100000, "env_steps": 24650, "total_transitions": 100966400, "num_steps_per_env": 1, "wm_loss": 0.5108226537704468, "actor_loss": -8.828258514404297, "critic_loss": 0.03460432589054108, "reward": 0.07049709558486938, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24180570244789124, 0.16320055723190308, 0.2580680251121521], "policy_updates": 24550, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1674.4304522950001, "contact_bce": 0.3197166621685028, "contact_force_loss": 0.03272128105163574, "terrain_level_mean": 2.918212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9983112812042236, 0.9993411302566528, 2.9947032928466797]} {"step": 24660, "actor_lr": 6.234188845713521e-06, "archive_windows": 100000, "env_steps": 24660, "total_transitions": 101007360, "num_steps_per_env": 1, "wm_loss": 0.5190837383270264, "actor_loss": -8.847965240478516, "critic_loss": 0.0165141299366951, "reward": 0.0701431855559349, "falls": 11, "interval_steps": 10, "velocity_mae": [0.23918922245502472, 0.16247428953647614, 0.2562556862831116], "policy_updates": 24560, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1677.9421845910001, "contact_bce": 0.32753708958625793, "contact_force_loss": 0.03376761078834534, "terrain_level_mean": 2.9169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9983112812042236, 0.9995356202125549, 2.9947032928466797]} {"step": 24670, "actor_lr": 6.218033162833494e-06, "archive_windows": 100000, "env_steps": 24670, "total_transitions": 101048320, "num_steps_per_env": 1, "wm_loss": 0.509081244468689, "actor_loss": -8.797445297241211, "critic_loss": 0.023749394342303276, "reward": 0.07090287655591965, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23987576365470886, 0.16085562109947205, 0.24739132821559906], "policy_updates": 24570, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1681.458392079, "contact_bce": 0.33276912569999695, "contact_force_loss": 0.03295579552650452, "terrain_level_mean": 2.916259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9983112812042236, 0.9995356202125549, 2.9974467754364014]} {"step": 24680, "actor_lr": 6.201904546756386e-06, "archive_windows": 100000, "env_steps": 24680, "total_transitions": 101089280, "num_steps_per_env": 1, "wm_loss": 0.5507706999778748, "actor_loss": -8.790437698364258, "critic_loss": 0.027515828609466553, "reward": 0.0714767798781395, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23567138612270355, 0.16098763048648834, 0.25057366490364075], "policy_updates": 24580, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1684.964898592, "contact_bce": 0.3282478451728821, "contact_force_loss": 0.034467171877622604, "terrain_level_mean": 2.9169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9983112812042236, 0.9995356202125549, 2.9974467754364014]} {"step": 24690, "actor_lr": 6.185803015169203e-06, "archive_windows": 100000, "env_steps": 24690, "total_transitions": 101130240, "num_steps_per_env": 1, "wm_loss": 0.5141271352767944, "actor_loss": -8.82160758972168, "critic_loss": 0.03361446410417557, "reward": 0.07105167955160141, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2390369325876236, 0.16110360622406006, 0.25646862387657166], "policy_updates": 24590, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1688.4684009900002, "contact_bce": 0.3246650695800781, "contact_force_loss": 0.03309263288974762, "terrain_level_mean": 2.91650390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.9974467754364014]} {"step": 24700, "actor_lr": 6.169728585729239e-06, "archive_windows": 100000, "env_steps": 24700, "total_transitions": 101171200, "num_steps_per_env": 1, "wm_loss": 0.5239796042442322, "actor_loss": -8.901390075683594, "critic_loss": 0.018356122076511383, "reward": 0.07138749957084656, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24029134213924408, 0.15782739222049713, 0.2509452998638153], "policy_updates": 24600, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1691.9932136070001, "contact_bce": 0.3323736786842346, "contact_force_loss": 0.03365807980298996, "terrain_level_mean": 2.918212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.9974467754364014]} {"step": 24710, "actor_lr": 6.153681276064089e-06, "archive_windows": 100000, "env_steps": 24710, "total_transitions": 101212160, "num_steps_per_env": 1, "wm_loss": 0.5251381397247314, "actor_loss": -8.819402694702148, "critic_loss": 0.027412692084908485, "reward": 0.07109840959310532, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23830628395080566, 0.15645745396614075, 0.25166699290275574], "policy_updates": 24610, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1695.529131184, "contact_bce": 0.3284674882888794, "contact_force_loss": 0.032887984067201614, "terrain_level_mean": 2.9189453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.9974467754364014]} {"step": 24720, "actor_lr": 6.137661103771593e-06, "archive_windows": 100000, "env_steps": 24720, "total_transitions": 101253120, "num_steps_per_env": 1, "wm_loss": 0.5115025639533997, "actor_loss": -8.792511940002441, "critic_loss": 0.03715228661894798, "reward": 0.07142992317676544, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2336810827255249, 0.15946441888809204, 0.2533244490623474], "policy_updates": 24620, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1699.0715190790002, "contact_bce": 0.32095441222190857, "contact_force_loss": 0.03222498297691345, "terrain_level_mean": 2.918212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.9974467754364014]} {"step": 24730, "actor_lr": 6.121668086419833e-06, "archive_windows": 100000, "env_steps": 24730, "total_transitions": 101294080, "num_steps_per_env": 1, "wm_loss": 0.499600887298584, "actor_loss": -8.856914520263672, "critic_loss": 0.021981490775942802, "reward": 0.07156474888324738, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23192943632602692, 0.15657620131969452, 0.25407901406288147], "policy_updates": 24630, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1702.5721204660001, "contact_bce": 0.32043692469596863, "contact_force_loss": 0.03191554546356201, "terrain_level_mean": 2.918701171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24740, "actor_lr": 6.105702241547111e-06, "archive_windows": 100000, "env_steps": 24740, "total_transitions": 101335040, "num_steps_per_env": 1, "wm_loss": 0.5262712240219116, "actor_loss": -8.861892700195312, "critic_loss": 0.029712963849306107, "reward": 0.07160407304763794, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23492099344730377, 0.1560637354850769, 0.25405657291412354], "policy_updates": 24640, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1706.073945561, "contact_bce": 0.32975631952285767, "contact_force_loss": 0.03357817232608795, "terrain_level_mean": 2.918701171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24750, "actor_lr": 6.0897635866619355e-06, "archive_windows": 100000, "env_steps": 24750, "total_transitions": 101376000, "num_steps_per_env": 1, "wm_loss": 0.4836757779121399, "actor_loss": -8.850341796875, "critic_loss": 0.0195202324539423, "reward": 0.07169085741043091, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24011121690273285, 0.1555456966161728, 0.25465694069862366], "policy_updates": 24650, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1709.583987332, "contact_bce": 0.3202245831489563, "contact_force_loss": 0.03239839896559715, "terrain_level_mean": 2.918701171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24760, "actor_lr": 6.07385213924299e-06, "archive_windows": 100000, "env_steps": 24760, "total_transitions": 101416960, "num_steps_per_env": 1, "wm_loss": 0.5493832230567932, "actor_loss": -8.86860466003418, "critic_loss": 0.02038094960153103, "reward": 0.07122930139303207, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2387041598558426, 0.1582920104265213, 0.2606561779975891], "policy_updates": 24660, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1713.099805126, "contact_bce": 0.3287138342857361, "contact_force_loss": 0.03346838057041168, "terrain_level_mean": 2.91943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24770, "actor_lr": 6.057967916739137e-06, "archive_windows": 100000, "env_steps": 24770, "total_transitions": 101457920, "num_steps_per_env": 1, "wm_loss": 0.5151229500770569, "actor_loss": -8.840483665466309, "critic_loss": 0.023284167051315308, "reward": 0.07125900685787201, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24295316636562347, 0.1592261642217636, 0.25953367352485657], "policy_updates": 24670, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1716.617742823, "contact_bce": 0.3220294117927551, "contact_force_loss": 0.03272213041782379, "terrain_level_mean": 2.91943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330810546875, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24780, "actor_lr": 6.0421109365693705e-06, "archive_windows": 100000, "env_steps": 24780, "total_transitions": 101498880, "num_steps_per_env": 1, "wm_loss": 0.5137132406234741, "actor_loss": -8.801445007324219, "critic_loss": 0.043349575251340866, "reward": 0.07115717977285385, "falls": 7, "interval_steps": 10, "velocity_mae": [0.247439444065094, 0.15907806158065796, 0.25902047753334045], "policy_updates": 24680, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1720.129563116, "contact_bce": 0.330108106136322, "contact_force_loss": 0.03306761384010315, "terrain_level_mean": 2.920166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24790, "actor_lr": 6.026281216122816e-06, "archive_windows": 100000, "env_steps": 24790, "total_transitions": 101539840, "num_steps_per_env": 1, "wm_loss": 0.5022048950195312, "actor_loss": -8.835472106933594, "critic_loss": 0.024212414398789406, "reward": 0.07142423093318939, "falls": 4, "interval_steps": 10, "velocity_mae": [0.244919091463089, 0.15824013948440552, 0.2560230493545532], "policy_updates": 24690, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1723.6530393720002, "contact_bce": 0.32754677534103394, "contact_force_loss": 0.03351035341620445, "terrain_level_mean": 2.921142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24800, "actor_lr": 6.0104787727587e-06, "archive_windows": 100000, "env_steps": 24800, "total_transitions": 101580800, "num_steps_per_env": 1, "wm_loss": 0.528903603553772, "actor_loss": -8.809379577636719, "critic_loss": 0.021971454843878746, "reward": 0.07139190286397934, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24388104677200317, 0.1575203239917755, 0.25714150071144104], "policy_updates": 24700, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1727.1789528000002, "contact_bce": 0.32080385088920593, "contact_force_loss": 0.033398959785699844, "terrain_level_mean": 2.921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24810, "actor_lr": 5.994703623806339e-06, "archive_windows": 100000, "env_steps": 24810, "total_transitions": 101621760, "num_steps_per_env": 1, "wm_loss": 0.5419193506240845, "actor_loss": -8.863016128540039, "critic_loss": 0.013544929213821888, "reward": 0.07164699584245682, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23880694806575775, 0.15606527030467987, 0.25758832693099976], "policy_updates": 24710, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1730.7174011930001, "contact_bce": 0.3297159969806671, "contact_force_loss": 0.033289384096860886, "terrain_level_mean": 2.924072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.998700737953186, 0.9995356202125549, 2.998764991760254]} {"step": 24820, "actor_lr": 5.978955786565108e-06, "archive_windows": 100000, "env_steps": 24820, "total_transitions": 101662720, "num_steps_per_env": 1, "wm_loss": 0.5834609270095825, "actor_loss": -8.825333595275879, "critic_loss": 0.026649707928299904, "reward": 0.07130447030067444, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23451152443885803, 0.1547081023454666, 0.25561103224754333], "policy_updates": 24720, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1734.2754147320002, "contact_bce": 0.3273654282093048, "contact_force_loss": 0.032808464020490646, "terrain_level_mean": 2.92431640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9983112812042236, 0.9995356202125549, 2.998764991760254]} {"step": 24830, "actor_lr": 5.96323527830446e-06, "archive_windows": 100000, "env_steps": 24830, "total_transitions": 101703680, "num_steps_per_env": 1, "wm_loss": 0.5189809203147888, "actor_loss": -8.868651390075684, "critic_loss": 0.01982898823916912, "reward": 0.07134737819433212, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22995656728744507, 0.15617090463638306, 0.2563215494155884], "policy_updates": 24730, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1737.8162303830002, "contact_bce": 0.32436221837997437, "contact_force_loss": 0.03325076401233673, "terrain_level_mean": 2.924072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9983112812042236, 0.9999411106109619, 2.998764991760254]} {"step": 24840, "actor_lr": 5.9475421162638585e-06, "archive_windows": 100000, "env_steps": 24840, "total_transitions": 101744640, "num_steps_per_env": 1, "wm_loss": 0.48103809356689453, "actor_loss": -8.812110900878906, "critic_loss": 0.028104254975914955, "reward": 0.07120195776224136, "falls": 5, "interval_steps": 10, "velocity_mae": [0.234227254986763, 0.15710660815238953, 0.25543972849845886], "policy_updates": 24740, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1741.357004769, "contact_bce": 0.3231165111064911, "contact_force_loss": 0.03254890441894531, "terrain_level_mean": 2.924072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9983112812042236, 0.9999411106109619, 2.998764991760254]} {"step": 24850, "actor_lr": 5.93187631765276e-06, "archive_windows": 100000, "env_steps": 24850, "total_transitions": 101785600, "num_steps_per_env": 1, "wm_loss": 0.5282009840011597, "actor_loss": -8.833529472351074, "critic_loss": 0.03084086813032627, "reward": 0.07115241140127182, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23518192768096924, 0.15913794934749603, 0.2540692687034607], "policy_updates": 24750, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1744.880838727, "contact_bce": 0.3323284387588501, "contact_force_loss": 0.033703841269016266, "terrain_level_mean": 2.9248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9983112812042236, 0.9999411106109619, 2.998764991760254]} {"step": 24860, "actor_lr": 5.916237899650654e-06, "archive_windows": 100000, "env_steps": 24860, "total_transitions": 101826560, "num_steps_per_env": 1, "wm_loss": 0.4804328382015228, "actor_loss": -8.837223052978516, "critic_loss": 0.02040531486272812, "reward": 0.07140891999006271, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23905961215496063, 0.15706640481948853, 0.25472235679626465], "policy_updates": 24760, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1748.4098357290002, "contact_bce": 0.31952735781669617, "contact_force_loss": 0.031975746154785156, "terrain_level_mean": 2.925537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9983112812042236, 0.9999411106109619, 2.998764991760254]} {"step": 24870, "actor_lr": 5.900626879406973e-06, "archive_windows": 100000, "env_steps": 24870, "total_transitions": 101867520, "num_steps_per_env": 1, "wm_loss": 0.5060331225395203, "actor_loss": -8.817264556884766, "critic_loss": 0.03168484568595886, "reward": 0.07149907201528549, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24022997915744781, 0.1571393460035324, 0.25412872433662415], "policy_updates": 24770, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1751.9657190070002, "contact_bce": 0.32608577609062195, "contact_force_loss": 0.03329794108867645, "terrain_level_mean": 2.92626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9983112812042236, 0.9999411106109619, 2.998764991760254]} {"step": 24880, "actor_lr": 5.885043274041113e-06, "archive_windows": 100000, "env_steps": 24880, "total_transitions": 101908480, "num_steps_per_env": 1, "wm_loss": 0.5403657555580139, "actor_loss": -8.859829902648926, "critic_loss": 0.019126329571008682, "reward": 0.07181642949581146, "falls": 2, "interval_steps": 10, "velocity_mae": [0.237355574965477, 0.1577959805727005, 0.25320306420326233], "policy_updates": 24780, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1755.502952127, "contact_bce": 0.32672038674354553, "contact_force_loss": 0.034246012568473816, "terrain_level_mean": 2.92724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.996675968170166, 0.9999411106109619, 2.998764991760254]} {"step": 24890, "actor_lr": 5.869487100642422e-06, "archive_windows": 100000, "env_steps": 24890, "total_transitions": 101949440, "num_steps_per_env": 1, "wm_loss": 0.5189091563224792, "actor_loss": -8.813959121704102, "critic_loss": 0.019912132993340492, "reward": 0.07164329290390015, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23938055336475372, 0.15850478410720825, 0.2589292824268341], "policy_updates": 24790, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1759.0429271540002, "contact_bce": 0.32741230726242065, "contact_force_loss": 0.0334094874560833, "terrain_level_mean": 2.9296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.996675968170166, 0.9999411106109619, 2.998764991760254]} {"step": 24900, "actor_lr": 5.853958376270138e-06, "archive_windows": 100000, "env_steps": 24900, "total_transitions": 101990400, "num_steps_per_env": 1, "wm_loss": 0.5046716928482056, "actor_loss": -8.821481704711914, "critic_loss": 0.01934942975640297, "reward": 0.07131364941596985, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2398109883069992, 0.16041253507137299, 0.2570880651473999], "policy_updates": 24800, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1762.588582135, "contact_bce": 0.3255978524684906, "contact_force_loss": 0.033197712153196335, "terrain_level_mean": 2.9296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.996675968170166, 0.9999411106109619, 2.998764991760254]} {"step": 24910, "actor_lr": 5.838457117953409e-06, "archive_windows": 100000, "env_steps": 24910, "total_transitions": 102031360, "num_steps_per_env": 1, "wm_loss": 0.5019583702087402, "actor_loss": -8.830936431884766, "critic_loss": 0.02054867148399353, "reward": 0.07096286118030548, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24050933122634888, 0.16070203483104706, 0.256850928068161], "policy_updates": 24810, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1766.1325747800001, "contact_bce": 0.3237033188343048, "contact_force_loss": 0.03263780474662781, "terrain_level_mean": 2.929443359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.996675968170166, 0.9999411106109619, 2.998764991760254]} {"step": 24920, "actor_lr": 5.822983342691277e-06, "archive_windows": 100000, "env_steps": 24920, "total_transitions": 102072320, "num_steps_per_env": 1, "wm_loss": 0.5052955150604248, "actor_loss": -8.853710174560547, "critic_loss": 0.022581899538636208, "reward": 0.07087601721286774, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24407029151916504, 0.16256959736347198, 0.2572142779827118], "policy_updates": 24820, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1769.668642954, "contact_bce": 0.32148605585098267, "contact_force_loss": 0.03203478083014488, "terrain_level_mean": 2.9296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.996675968170166, 0.9999411106109619, 2.9974467754364014]} {"step": 24930, "actor_lr": 5.807537067452627e-06, "archive_windows": 100000, "env_steps": 24930, "total_transitions": 102113280, "num_steps_per_env": 1, "wm_loss": 0.507154107093811, "actor_loss": -8.901122093200684, "critic_loss": 0.016858946532011032, "reward": 0.07073158025741577, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24492740631103516, 0.1624322086572647, 0.25760626792907715], "policy_updates": 24830, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1773.193467029, "contact_bce": 0.3222598135471344, "contact_force_loss": 0.033278293907642365, "terrain_level_mean": 2.93017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.996675968170166, 0.9999411106109619, 2.996702194213867]} {"step": 24940, "actor_lr": 5.792118309176197e-06, "archive_windows": 100000, "env_steps": 24940, "total_transitions": 102154240, "num_steps_per_env": 1, "wm_loss": 0.48520931601524353, "actor_loss": -8.829145431518555, "critic_loss": 0.022506479173898697, "reward": 0.0706711933016777, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24059806764125824, 0.1592114120721817, 0.2566845118999481], "policy_updates": 24840, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1776.7054518470002, "contact_bce": 0.32136106491088867, "contact_force_loss": 0.03217759355902672, "terrain_level_mean": 2.931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 24950, "actor_lr": 5.776727084770542e-06, "archive_windows": 100000, "env_steps": 24950, "total_transitions": 102195200, "num_steps_per_env": 1, "wm_loss": 0.5439537167549133, "actor_loss": -8.8002347946167, "critic_loss": 0.020211657509207726, "reward": 0.07110484689474106, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2391398549079895, 0.1574798971414566, 0.2525898516178131], "policy_updates": 24850, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1780.219672576, "contact_bce": 0.3288969397544861, "contact_force_loss": 0.03341574966907501, "terrain_level_mean": 2.93212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 24960, "actor_lr": 5.76136341111403e-06, "archive_windows": 100000, "env_steps": 24960, "total_transitions": 102236160, "num_steps_per_env": 1, "wm_loss": 0.5035410523414612, "actor_loss": -8.779197692871094, "critic_loss": 0.02221437357366085, "reward": 0.07097920030355453, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23956061899662018, 0.15661774575710297, 0.25690633058547974], "policy_updates": 24860, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1783.7455889960002, "contact_bce": 0.3216123878955841, "contact_force_loss": 0.03292402625083923, "terrain_level_mean": 2.932861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 24970, "actor_lr": 5.746027305054804e-06, "archive_windows": 100000, "env_steps": 24970, "total_transitions": 102277120, "num_steps_per_env": 1, "wm_loss": 0.505017101764679, "actor_loss": -8.855875015258789, "critic_loss": 0.030388353392481804, "reward": 0.07118536531925201, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2421731799840927, 0.15781354904174805, 0.2571460008621216], "policy_updates": 24870, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1787.282715554, "contact_bce": 0.323673278093338, "contact_force_loss": 0.0327436737716198, "terrain_level_mean": 2.932373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 24980, "actor_lr": 5.730718783410799e-06, "archive_windows": 100000, "env_steps": 24980, "total_transitions": 102318080, "num_steps_per_env": 1, "wm_loss": 0.4972822368144989, "actor_loss": -8.890228271484375, "critic_loss": 0.01889422908425331, "reward": 0.07165675610303879, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23887743055820465, 0.1567479521036148, 0.25098440051078796], "policy_updates": 24880, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1790.817085477, "contact_bce": 0.32939064502716064, "contact_force_loss": 0.033051736652851105, "terrain_level_mean": 2.93115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 24990, "actor_lr": 5.715437862969678e-06, "archive_windows": 100000, "env_steps": 24990, "total_transitions": 102359040, "num_steps_per_env": 1, "wm_loss": 0.5108438730239868, "actor_loss": -8.837417602539062, "critic_loss": 0.017428884282708168, "reward": 0.07129218429327011, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2427062839269638, 0.15633179247379303, 0.25580498576164246], "policy_updates": 24890, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1794.34811381, "contact_bce": 0.3215406835079193, "contact_force_loss": 0.03228149935603142, "terrain_level_mean": 2.931884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25000, "actor_lr": 5.700184560488849e-06, "archive_windows": 100000, "env_steps": 25000, "total_transitions": 102400000, "num_steps_per_env": 1, "wm_loss": 0.5189836621284485, "actor_loss": -8.874580383300781, "critic_loss": 0.02173410728573799, "reward": 0.07130976766347885, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2403688281774521, 0.15542404353618622, 0.25650766491889954], "policy_updates": 24900, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1797.870672041, "contact_bce": 0.3281390368938446, "contact_force_loss": 0.03415937349200249, "terrain_level_mean": 2.931884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25010, "actor_lr": 5.68495889269542e-06, "archive_windows": 100000, "env_steps": 25010, "total_transitions": 102440960, "num_steps_per_env": 1, "wm_loss": 0.503380537033081, "actor_loss": -8.872199058532715, "critic_loss": 0.0206789318472147, "reward": 0.07168402522802353, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23699620366096497, 0.15349729359149933, 0.2561289966106415], "policy_updates": 24910, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1801.4203097040001, "contact_bce": 0.32541096210479736, "contact_force_loss": 0.03227512538433075, "terrain_level_mean": 2.931396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25020, "actor_lr": 5.66976087628621e-06, "archive_windows": 100000, "env_steps": 25020, "total_transitions": 102481920, "num_steps_per_env": 1, "wm_loss": 0.5493696331977844, "actor_loss": -8.8247709274292, "critic_loss": 0.03053952194750309, "reward": 0.07181569188833237, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23623879253864288, 0.15416386723518372, 0.2572643756866455], "policy_updates": 24920, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1805.2217747440002, "contact_bce": 0.32768452167510986, "contact_force_loss": 0.03359431400895119, "terrain_level_mean": 2.931884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25030, "actor_lr": 5.654590527927696e-06, "archive_windows": 100000, "env_steps": 25030, "total_transitions": 102522880, "num_steps_per_env": 1, "wm_loss": 0.4810539782047272, "actor_loss": -8.787882804870605, "critic_loss": 0.022603776305913925, "reward": 0.07138268649578094, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23647350072860718, 0.15754924714565277, 0.2602027654647827], "policy_updates": 24930, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1808.748859445, "contact_bce": 0.3248097002506256, "contact_force_loss": 0.03221716359257698, "terrain_level_mean": 2.934814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25040, "actor_lr": 5.6394478642560425e-06, "archive_windows": 100000, "env_steps": 25040, "total_transitions": 102563840, "num_steps_per_env": 1, "wm_loss": 0.4993913769721985, "actor_loss": -8.836551666259766, "critic_loss": 0.021062089130282402, "reward": 0.07097908109426498, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24009864032268524, 0.157956063747406, 0.2556055188179016], "policy_updates": 24940, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1812.3016963050002, "contact_bce": 0.3277745544910431, "contact_force_loss": 0.033922988921403885, "terrain_level_mean": 2.935791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25050, "actor_lr": 5.624332901877023e-06, "archive_windows": 100000, "env_steps": 25050, "total_transitions": 102604800, "num_steps_per_env": 1, "wm_loss": 0.5061512589454651, "actor_loss": -8.841544151306152, "critic_loss": 0.01878461055457592, "reward": 0.07067795842885971, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23844076693058014, 0.15652647614479065, 0.2550787925720215], "policy_updates": 24950, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1815.833430929, "contact_bce": 0.3248172402381897, "contact_force_loss": 0.03292191028594971, "terrain_level_mean": 2.936279296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25060, "actor_lr": 5.609245657366056e-06, "archive_windows": 100000, "env_steps": 25060, "total_transitions": 102645760, "num_steps_per_env": 1, "wm_loss": 0.48912763595581055, "actor_loss": -8.818243980407715, "critic_loss": 0.022886229678988457, "reward": 0.07084996998310089, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2379053384065628, 0.15858767926692963, 0.2509331703186035], "policy_updates": 24960, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1819.360581568, "contact_bce": 0.32408416271209717, "contact_force_loss": 0.03276816010475159, "terrain_level_mean": 2.937744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25070, "actor_lr": 5.594186147268151e-06, "archive_windows": 100000, "env_steps": 25070, "total_transitions": 102686720, "num_steps_per_env": 1, "wm_loss": 0.5335992574691772, "actor_loss": -8.812692642211914, "critic_loss": 0.028521478176116943, "reward": 0.07111087441444397, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23619984090328217, 0.15430143475532532, 0.25472503900527954], "policy_updates": 24970, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1822.900573133, "contact_bce": 0.3331812024116516, "contact_force_loss": 0.03398502990603447, "terrain_level_mean": 2.9384765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25080, "actor_lr": 5.579154388097905e-06, "archive_windows": 100000, "env_steps": 25080, "total_transitions": 102727680, "num_steps_per_env": 1, "wm_loss": 0.47507739067077637, "actor_loss": -8.836355209350586, "critic_loss": 0.019398117437958717, "reward": 0.07128798216581345, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24125416576862335, 0.1529066264629364, 0.25416678190231323], "policy_updates": 24980, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1826.4201675220002, "contact_bce": 0.33029502630233765, "contact_force_loss": 0.03273063153028488, "terrain_level_mean": 2.9384765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25090, "actor_lr": 5.564150396339482e-06, "archive_windows": 100000, "env_steps": 25090, "total_transitions": 102768640, "num_steps_per_env": 1, "wm_loss": 0.513171374797821, "actor_loss": -8.808062553405762, "critic_loss": 0.02564854919910431, "reward": 0.07116921991109848, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23972444236278534, 0.1582174450159073, 0.2559390664100647], "policy_updates": 24990, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1829.9444836100001, "contact_bce": 0.3164352476596832, "contact_force_loss": 0.03206627070903778, "terrain_level_mean": 2.93896484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25100, "actor_lr": 5.549174188446609e-06, "archive_windows": 100000, "env_steps": 25100, "total_transitions": 102809600, "num_steps_per_env": 1, "wm_loss": 0.5116386413574219, "actor_loss": -8.803394317626953, "critic_loss": 0.02624690905213356, "reward": 0.07180522382259369, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23635780811309814, 0.15817038714885712, 0.2550905644893646], "policy_updates": 25000, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1833.5063819690001, "contact_bce": 0.3239304721355438, "contact_force_loss": 0.03321292623877525, "terrain_level_mean": 2.938720703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25110, "actor_lr": 5.5342257808425354e-06, "archive_windows": 100000, "env_steps": 25110, "total_transitions": 102850560, "num_steps_per_env": 1, "wm_loss": 0.5078505873680115, "actor_loss": -8.85897159576416, "critic_loss": 0.029118318110704422, "reward": 0.07117265462875366, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2353402078151703, 0.15706296265125275, 0.2584085166454315], "policy_updates": 25010, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1837.182406154, "contact_bce": 0.3235670030117035, "contact_force_loss": 0.033300839364528656, "terrain_level_mean": 2.93896484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25120, "actor_lr": 5.519305189920006e-06, "archive_windows": 100000, "env_steps": 25120, "total_transitions": 102891520, "num_steps_per_env": 1, "wm_loss": 0.4776945412158966, "actor_loss": -8.847463607788086, "critic_loss": 0.02062958851456642, "reward": 0.07148905098438263, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23284074664115906, 0.15657635033130646, 0.24891896545886993], "policy_updates": 25020, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1840.9441674000002, "contact_bce": 0.3202146887779236, "contact_force_loss": 0.03271155431866646, "terrain_level_mean": 2.938720703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25130, "actor_lr": 5.504412432041293e-06, "archive_windows": 100000, "env_steps": 25130, "total_transitions": 102932480, "num_steps_per_env": 1, "wm_loss": 0.5427083969116211, "actor_loss": -8.852903366088867, "critic_loss": 0.016552062705159187, "reward": 0.07123038917779922, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2343398779630661, 0.15828245878219604, 0.25148946046829224], "policy_updates": 25030, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1844.530048955, "contact_bce": 0.33381354808807373, "contact_force_loss": 0.03479119762778282, "terrain_level_mean": 2.939208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25140, "actor_lr": 5.489547523538127e-06, "archive_windows": 100000, "env_steps": 25140, "total_transitions": 102973440, "num_steps_per_env": 1, "wm_loss": 0.4943225383758545, "actor_loss": -8.883556365966797, "critic_loss": 0.0203752052038908, "reward": 0.07106736302375793, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23722244799137115, 0.15732477605342865, 0.2555559277534485], "policy_updates": 25040, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1848.1030668820001, "contact_bce": 0.31972745060920715, "contact_force_loss": 0.03184489160776138, "terrain_level_mean": 2.939208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.996702194213867]} {"step": 25150, "actor_lr": 5.474710480711695e-06, "archive_windows": 100000, "env_steps": 25150, "total_transitions": 103014400, "num_steps_per_env": 1, "wm_loss": 0.4663640856742859, "actor_loss": -8.800071716308594, "critic_loss": 0.022984081879258156, "reward": 0.07103192061185837, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24162544310092926, 0.15746428072452545, 0.2547040283679962], "policy_updates": 25050, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1851.7831593650003, "contact_bce": 0.3229702413082123, "contact_force_loss": 0.03180650249123573, "terrain_level_mean": 2.93994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.993746519088745]} {"step": 25160, "actor_lr": 5.459901319832656e-06, "archive_windows": 100000, "env_steps": 25160, "total_transitions": 103055360, "num_steps_per_env": 1, "wm_loss": 0.5206838250160217, "actor_loss": -8.832388877868652, "critic_loss": 0.031255092471838, "reward": 0.07059206068515778, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24266788363456726, 0.15826058387756348, 0.25580936670303345], "policy_updates": 25060, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1855.564079489, "contact_bce": 0.3266001343727112, "contact_force_loss": 0.032993435859680176, "terrain_level_mean": 2.939697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9981200695037842, 0.9999411106109619, 2.993746519088745]} {"step": 25170, "actor_lr": 5.445120057141052e-06, "archive_windows": 100000, "env_steps": 25170, "total_transitions": 103096320, "num_steps_per_env": 1, "wm_loss": 0.5171447396278381, "actor_loss": -8.807292938232422, "critic_loss": 0.031008470803499222, "reward": 0.07060493528842926, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2431381493806839, 0.1543709933757782, 0.2532177269458771], "policy_updates": 25070, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1859.4289715210002, "contact_bce": 0.32853764295578003, "contact_force_loss": 0.03269370645284653, "terrain_level_mean": 2.939697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9981200695037842, 0.9976611733436584, 2.993746519088745]} {"step": 25180, "actor_lr": 5.430366708846344e-06, "archive_windows": 100000, "env_steps": 25180, "total_transitions": 103137280, "num_steps_per_env": 1, "wm_loss": 0.508337140083313, "actor_loss": -8.828628540039062, "critic_loss": 0.02572636678814888, "reward": 0.0706745907664299, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23491744697093964, 0.15427549183368683, 0.25159141421318054], "policy_updates": 25080, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1863.32643074, "contact_bce": 0.3289709687232971, "contact_force_loss": 0.03358932584524155, "terrain_level_mean": 2.939697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9981200695037842, 0.9976611733436584, 2.993746519088745]} {"step": 25190, "actor_lr": 5.415641291127404e-06, "archive_windows": 100000, "env_steps": 25190, "total_transitions": 103178240, "num_steps_per_env": 1, "wm_loss": 0.5016298294067383, "actor_loss": -8.864965438842773, "critic_loss": 0.01903066597878933, "reward": 0.07091064751148224, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2340175211429596, 0.1537611037492752, 0.2512142062187195], "policy_updates": 25090, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1867.655488119, "contact_bce": 0.32662054896354675, "contact_force_loss": 0.033220432698726654, "terrain_level_mean": 2.940185546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9981200695037842, 0.9976611733436584, 2.993746519088745]} {"step": 25200, "actor_lr": 5.4009438201324535e-06, "archive_windows": 100000, "env_steps": 25200, "total_transitions": 103219200, "num_steps_per_env": 1, "wm_loss": 0.5175430774688721, "actor_loss": -8.764066696166992, "critic_loss": 0.022899188101291656, "reward": 0.0709875151515007, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23663870990276337, 0.15217621624469757, 0.2500290870666504], "policy_updates": 25100, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1872.283113124, "contact_bce": 0.32364317774772644, "contact_force_loss": 0.03251294791698456, "terrain_level_mean": 2.941162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9981200695037842, 0.9976611733436584, 2.998828887939453]} {"step": 25210, "actor_lr": 5.38627431197907e-06, "archive_windows": 100000, "env_steps": 25210, "total_transitions": 103260160, "num_steps_per_env": 1, "wm_loss": 0.5142787098884583, "actor_loss": -8.822050094604492, "critic_loss": 0.022750576958060265, "reward": 0.0711207166314125, "falls": 0, "interval_steps": 10, "velocity_mae": [0.23185305297374725, 0.15286752581596375, 0.2486041933298111], "policy_updates": 25110, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1876.713009093, "contact_bce": 0.32325586676597595, "contact_force_loss": 0.03256238251924515, "terrain_level_mean": 2.94189453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9981200695037842, 0.998375415802002, 2.998828887939453]} {"step": 25220, "actor_lr": 5.371632782754166e-06, "archive_windows": 100000, "env_steps": 25220, "total_transitions": 103301120, "num_steps_per_env": 1, "wm_loss": 0.4884011149406433, "actor_loss": -8.831892013549805, "critic_loss": 0.027967536821961403, "reward": 0.07084554433822632, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23261326551437378, 0.1520116925239563, 0.2533944547176361], "policy_updates": 25120, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1881.170360189, "contact_bce": 0.32458895444869995, "contact_force_loss": 0.03279200568795204, "terrain_level_mean": 2.94140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9981200695037842, 0.998375415802002, 2.998828887939453]} {"step": 25230, "actor_lr": 5.357019248513974e-06, "archive_windows": 100000, "env_steps": 25230, "total_transitions": 103342080, "num_steps_per_env": 1, "wm_loss": 0.4831427335739136, "actor_loss": -8.855804443359375, "critic_loss": 0.020090186968445778, "reward": 0.07103775441646576, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23724792897701263, 0.1502198725938797, 0.25211507081985474], "policy_updates": 25130, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1885.7949047850002, "contact_bce": 0.3263570964336395, "contact_force_loss": 0.0329412966966629, "terrain_level_mean": 2.942138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9981200695037842, 0.998375415802002, 2.998828887939453]} {"step": 25240, "actor_lr": 5.342433725284023e-06, "archive_windows": 100000, "env_steps": 25240, "total_transitions": 103383040, "num_steps_per_env": 1, "wm_loss": 0.5091134905815125, "actor_loss": -8.836479187011719, "critic_loss": 0.020116016268730164, "reward": 0.07114946097135544, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24050015211105347, 0.15316461026668549, 0.25481265783309937], "policy_updates": 25140, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1890.445363587, "contact_bce": 0.32642340660095215, "contact_force_loss": 0.03335382416844368, "terrain_level_mean": 2.9423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9981200695037842, 0.998375415802002, 2.998828887939453]} {"step": 25250, "actor_lr": 5.327876229059135e-06, "archive_windows": 100000, "env_steps": 25250, "total_transitions": 103424000, "num_steps_per_env": 1, "wm_loss": 0.5121370553970337, "actor_loss": -8.847729682922363, "critic_loss": 0.026810526847839355, "reward": 0.07129229605197906, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2364598661661148, 0.15500396490097046, 0.2565222978591919], "policy_updates": 25150, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1895.0067232290003, "contact_bce": 0.3209631145000458, "contact_force_loss": 0.03284522891044617, "terrain_level_mean": 2.9462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9981200695037842, 0.9988226890563965, 2.998828887939453]} {"step": 25260, "actor_lr": 5.313346775803386e-06, "archive_windows": 100000, "env_steps": 25260, "total_transitions": 103464960, "num_steps_per_env": 1, "wm_loss": 0.4735718071460724, "actor_loss": -8.850948333740234, "critic_loss": 0.027234939858317375, "reward": 0.0703895315527916, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2554018795490265, 0.1518644541501999, 0.2662566900253296], "policy_updates": 25160, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1899.6082369690002, "contact_bce": 0.3278559148311615, "contact_force_loss": 0.03294071555137634, "terrain_level_mean": 2.947021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9971402883529663, 0.9988226890563965, 2.998828887939453]} {"step": 25270, "actor_lr": 5.298845381450104e-06, "archive_windows": 100000, "env_steps": 25270, "total_transitions": 103505920, "num_steps_per_env": 1, "wm_loss": 0.4997001886367798, "actor_loss": -8.836727142333984, "critic_loss": 0.024721277877688408, "reward": 0.07205083221197128, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2315659075975418, 0.15398159623146057, 0.2535938024520874], "policy_updates": 25170, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1904.1647201670003, "contact_bce": 0.32608938217163086, "contact_force_loss": 0.033452074974775314, "terrain_level_mean": 2.947509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9971402883529663, 0.9988226890563965, 2.998828887939453]} {"step": 25280, "actor_lr": 5.284372061901845e-06, "archive_windows": 100000, "env_steps": 25280, "total_transitions": 103546880, "num_steps_per_env": 1, "wm_loss": 0.499981164932251, "actor_loss": -8.888799667358398, "critic_loss": 0.016138792037963867, "reward": 0.07209204882383347, "falls": 2, "interval_steps": 10, "velocity_mae": [0.22455184161663055, 0.15445123612880707, 0.2507045567035675], "policy_updates": 25180, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1908.6835803889999, "contact_bce": 0.33066248893737793, "contact_force_loss": 0.033369503915309906, "terrain_level_mean": 2.94873046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9971402883529663, 0.9988226890563965, 2.998828887939453]} {"step": 25290, "actor_lr": 5.2699268330303775e-06, "archive_windows": 100000, "env_steps": 25290, "total_transitions": 103587840, "num_steps_per_env": 1, "wm_loss": 0.524705171585083, "actor_loss": -8.872190475463867, "critic_loss": 0.021387986838817596, "reward": 0.07195126265287399, "falls": 3, "interval_steps": 10, "velocity_mae": [0.22189293801784515, 0.15164154767990112, 0.251198947429657], "policy_updates": 25190, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1913.254898223, "contact_bce": 0.32271984219551086, "contact_force_loss": 0.03362429514527321, "terrain_level_mean": 2.949462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9971402883529663, 0.9988226890563965, 2.998828887939453]} {"step": 25300, "actor_lr": 5.255509710676662e-06, "archive_windows": 100000, "env_steps": 25300, "total_transitions": 103628800, "num_steps_per_env": 1, "wm_loss": 0.4838615953922272, "actor_loss": -8.876140594482422, "critic_loss": 0.025833893567323685, "reward": 0.071603924036026, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22535884380340576, 0.15393464267253876, 0.25132015347480774], "policy_updates": 25200, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1917.7278497480002, "contact_bce": 0.3232298791408539, "contact_force_loss": 0.03278050199151039, "terrain_level_mean": 2.948974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9971402883529663, 0.9988226890563965, 2.998828887939453]} {"step": 25310, "actor_lr": 5.241120710650849e-06, "archive_windows": 100000, "env_steps": 25310, "total_transitions": 103669760, "num_steps_per_env": 1, "wm_loss": 0.4820598363876343, "actor_loss": -8.804675102233887, "critic_loss": 0.025241976603865623, "reward": 0.0719667300581932, "falls": 5, "interval_steps": 10, "velocity_mae": [0.22695553302764893, 0.15058502554893494, 0.25239109992980957], "policy_updates": 25210, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1922.3297135349999, "contact_bce": 0.31827113032341003, "contact_force_loss": 0.031971994787454605, "terrain_level_mean": 2.94921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9971402883529663, 0.9988226890563965, 2.998828887939453]} {"step": 25320, "actor_lr": 5.22675984873224e-06, "archive_windows": 100000, "env_steps": 25320, "total_transitions": 103710720, "num_steps_per_env": 1, "wm_loss": 0.5013497471809387, "actor_loss": -8.80560302734375, "critic_loss": 0.02531256712973118, "reward": 0.07207176089286804, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22784967720508575, 0.1508280634880066, 0.2499556541442871], "policy_updates": 25220, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1926.7861186590003, "contact_bce": 0.32405897974967957, "contact_force_loss": 0.03312120586633682, "terrain_level_mean": 2.949462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9997882843017578, 0.9988226890563965, 2.998828887939453]} {"step": 25330, "actor_lr": 5.212427140669281e-06, "archive_windows": 100000, "env_steps": 25330, "total_transitions": 103751680, "num_steps_per_env": 1, "wm_loss": 0.5174452662467957, "actor_loss": -8.900699615478516, "critic_loss": 0.01928308978676796, "reward": 0.07204455137252808, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2286466509103775, 0.15136094391345978, 0.25166428089141846], "policy_updates": 25230, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1931.3412891980001, "contact_bce": 0.32101452350616455, "contact_force_loss": 0.03311816230416298, "terrain_level_mean": 2.950439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9997882843017578, 0.9993655681610107, 2.998828887939453]} {"step": 25340, "actor_lr": 5.1981226021795395e-06, "archive_windows": 100000, "env_steps": 25340, "total_transitions": 103792640, "num_steps_per_env": 1, "wm_loss": 0.5230940580368042, "actor_loss": -8.85045051574707, "critic_loss": 0.021871240809559822, "reward": 0.07210629433393478, "falls": 1, "interval_steps": 10, "velocity_mae": [0.22804269194602966, 0.15236209332942963, 0.25104567408561707], "policy_updates": 25240, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1935.96384219, "contact_bce": 0.32046541571617126, "contact_force_loss": 0.033133428543806076, "terrain_level_mean": 2.951416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9997882843017578, 0.9993655681610107, 2.998828887939453]} {"step": 25350, "actor_lr": 5.183846248949697e-06, "archive_windows": 100000, "env_steps": 25350, "total_transitions": 103833600, "num_steps_per_env": 1, "wm_loss": 0.5196426510810852, "actor_loss": -8.843815803527832, "critic_loss": 0.017616121098399162, "reward": 0.07198456674814224, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23012951016426086, 0.153219535946846, 0.25335603952407837], "policy_updates": 25250, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1940.629586435, "contact_bce": 0.3293962776660919, "contact_force_loss": 0.03323459252715111, "terrain_level_mean": 2.951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9997882843017578, 0.9993655681610107, 2.998828887939453]} {"step": 25360, "actor_lr": 5.169598096635523e-06, "archive_windows": 100000, "env_steps": 25360, "total_transitions": 103874560, "num_steps_per_env": 1, "wm_loss": 0.4971032738685608, "actor_loss": -8.882438659667969, "critic_loss": 0.017514830455183983, "reward": 0.0717308297753334, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23287872970104218, 0.15244776010513306, 0.2529754042625427], "policy_updates": 25260, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1945.2857017270003, "contact_bce": 0.3253896236419678, "contact_force_loss": 0.032894983887672424, "terrain_level_mean": 2.95166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.998828887939453]} {"step": 25370, "actor_lr": 5.1553781608618715e-06, "archive_windows": 100000, "env_steps": 25370, "total_transitions": 103915520, "num_steps_per_env": 1, "wm_loss": 0.5227289795875549, "actor_loss": -8.847631454467773, "critic_loss": 0.033741217106580734, "reward": 0.07137644290924072, "falls": 10, "interval_steps": 10, "velocity_mae": [0.23479942977428436, 0.1535254269838333, 0.25667425990104675], "policy_updates": 25270, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1949.7834386210002, "contact_bce": 0.3309168815612793, "contact_force_loss": 0.03361637890338898, "terrain_level_mean": 2.949951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.998828887939453]} {"step": 25380, "actor_lr": 5.141186457222648e-06, "archive_windows": 100000, "env_steps": 25380, "total_transitions": 103956480, "num_steps_per_env": 1, "wm_loss": 0.5018571019172668, "actor_loss": -8.841552734375, "critic_loss": 0.02474060282111168, "reward": 0.07118070125579834, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23659563064575195, 0.155151829123497, 0.2535024881362915], "policy_updates": 25280, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1954.3014805359999, "contact_bce": 0.3224673271179199, "contact_force_loss": 0.03297492861747742, "terrain_level_mean": 2.951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.998828887939453]} {"step": 25390, "actor_lr": 5.1270230012807754e-06, "archive_windows": 100000, "env_steps": 25390, "total_transitions": 103997440, "num_steps_per_env": 1, "wm_loss": 0.5283723473548889, "actor_loss": -8.826347351074219, "critic_loss": 0.02682412974536419, "reward": 0.0716366097331047, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23727497458457947, 0.1562044620513916, 0.25242385268211365], "policy_updates": 25290, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1958.833479285, "contact_bce": 0.3239796459674835, "contact_force_loss": 0.03305085375905037, "terrain_level_mean": 2.95068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.995011329650879]} {"step": 25400, "actor_lr": 5.112887808568236e-06, "archive_windows": 100000, "env_steps": 25400, "total_transitions": 104038400, "num_steps_per_env": 1, "wm_loss": 0.4731796085834503, "actor_loss": -8.864816665649414, "critic_loss": 0.025299355387687683, "reward": 0.07178988307714462, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23480412364006042, 0.1537914276123047, 0.25036442279815674], "policy_updates": 25300, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1963.344224465, "contact_bce": 0.3213180601596832, "contact_force_loss": 0.03247141093015671, "terrain_level_mean": 2.9501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.995011329650879]} {"step": 25410, "actor_lr": 5.098780894586001e-06, "archive_windows": 100000, "env_steps": 25410, "total_transitions": 104079360, "num_steps_per_env": 1, "wm_loss": 0.5199354887008667, "actor_loss": -8.837462425231934, "critic_loss": 0.023904532194137573, "reward": 0.07198473066091537, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23758690059185028, 0.15252803266048431, 0.25172707438468933], "policy_updates": 25310, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1967.8127255140002, "contact_bce": 0.3246147334575653, "contact_force_loss": 0.03256308659911156, "terrain_level_mean": 2.949462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.995011329650879]} {"step": 25420, "actor_lr": 5.084702274804023e-06, "archive_windows": 100000, "env_steps": 25420, "total_transitions": 104120320, "num_steps_per_env": 1, "wm_loss": 0.5374071002006531, "actor_loss": -8.828533172607422, "critic_loss": 0.024523675441741943, "reward": 0.07177571207284927, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2371673583984375, 0.1532096415758133, 0.25452539324760437], "policy_updates": 25320, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1972.452015061, "contact_bce": 0.3205747902393341, "contact_force_loss": 0.033245231956243515, "terrain_level_mean": 2.949462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.995011329650879]} {"step": 25430, "actor_lr": 5.070651964661255e-06, "archive_windows": 100000, "env_steps": 25430, "total_transitions": 104161280, "num_steps_per_env": 1, "wm_loss": 0.526364803314209, "actor_loss": -8.828275680541992, "critic_loss": 0.01861734874546528, "reward": 0.07144372165203094, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23348799347877502, 0.1524171084165573, 0.25486433506011963], "policy_updates": 25330, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1977.174496994, "contact_bce": 0.32171985507011414, "contact_force_loss": 0.03258684650063515, "terrain_level_mean": 2.9501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.995011329650879]} {"step": 25440, "actor_lr": 5.05662997956556e-06, "archive_windows": 100000, "env_steps": 25440, "total_transitions": 104202240, "num_steps_per_env": 1, "wm_loss": 0.5088343024253845, "actor_loss": -8.804729461669922, "critic_loss": 0.02530876360833645, "reward": 0.07101275771856308, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2406666874885559, 0.15293623507022858, 0.25442934036254883], "policy_updates": 25340, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1981.9311365030003, "contact_bce": 0.3268670439720154, "contact_force_loss": 0.03263989835977554, "terrain_level_mean": 2.951416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9997882843017578, 0.9999018907546997, 2.995011329650879]} {"step": 25450, "actor_lr": 5.04263633489377e-06, "archive_windows": 100000, "env_steps": 25450, "total_transitions": 104243200, "num_steps_per_env": 1, "wm_loss": 0.54990553855896, "actor_loss": -8.854333877563477, "critic_loss": 0.02090117149055004, "reward": 0.071071557700634, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24121153354644775, 0.1523532271385193, 0.25716862082481384], "policy_updates": 25350, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1986.5477679240003, "contact_bce": 0.3318943381309509, "contact_force_loss": 0.03482253849506378, "terrain_level_mean": 2.951416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9997882843017578, 0.9993655681610107, 2.995011329650879]} {"step": 25460, "actor_lr": 5.028671045991643e-06, "archive_windows": 100000, "env_steps": 25460, "total_transitions": 104284160, "num_steps_per_env": 1, "wm_loss": 0.5245112180709839, "actor_loss": -8.791498184204102, "critic_loss": 0.02224135957658291, "reward": 0.07090652734041214, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24029935896396637, 0.1525406390428543, 0.25532248616218567], "policy_updates": 25360, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1991.0191795230003, "contact_bce": 0.32855871319770813, "contact_force_loss": 0.0332113578915596, "terrain_level_mean": 2.951904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9997882843017578, 0.9993655681610107, 2.995011329650879]} {"step": 25470, "actor_lr": 5.014734128173825e-06, "archive_windows": 100000, "env_steps": 25470, "total_transitions": 104325120, "num_steps_per_env": 1, "wm_loss": 0.4821266531944275, "actor_loss": -8.822229385375977, "critic_loss": 0.02463151514530182, "reward": 0.07118751853704453, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2422264665365219, 0.15155713260173798, 0.2509729266166687], "policy_updates": 25370, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 1995.544996731, "contact_bce": 0.3260972201824188, "contact_force_loss": 0.0326334573328495, "terrain_level_mean": 2.95361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9997882843017578, 0.9993655681610107, 2.995011329650879]} {"step": 25480, "actor_lr": 5.000825596723851e-06, "archive_windows": 100000, "env_steps": 25480, "total_transitions": 104366080, "num_steps_per_env": 1, "wm_loss": 0.49349868297576904, "actor_loss": -8.80276107788086, "critic_loss": 0.033632367849349976, "reward": 0.07088370621204376, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2427579164505005, 0.155563086271286, 0.2559053301811218], "policy_updates": 25380, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 2000.145485983, "contact_bce": 0.326753705739975, "contact_force_loss": 0.03268568962812424, "terrain_level_mean": 2.953857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9997882843017578, 0.9993655681610107, 2.995011329650879]} {"step": 25490, "actor_lr": 4.986945466894139e-06, "archive_windows": 100000, "env_steps": 25490, "total_transitions": 104407040, "num_steps_per_env": 1, "wm_loss": 0.5001416802406311, "actor_loss": -8.8471097946167, "critic_loss": 0.02064412273466587, "reward": 0.07080214470624924, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23973004519939423, 0.15766476094722748, 0.2544483244419098], "policy_updates": 25390, "skipped_updates": 0, "invalid_env_resets": 11, "elapsed_s": 2004.7308783120002, "contact_bce": 0.32340845465660095, "contact_force_loss": 0.03230731934309006, "terrain_level_mean": 2.9541015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9997882843017578, 0.9988226890563965, 2.995011329650879]} RECOVERY reset 1 invalid environments; first IDs=[2101] {"step": 25500, "actor_lr": 4.9730937539059445e-06, "archive_windows": 100000, "env_steps": 25500, "total_transitions": 104448000, "num_steps_per_env": 1, "wm_loss": 0.5144144892692566, "actor_loss": -8.849284172058105, "critic_loss": 0.023040657863020897, "reward": 0.07034670561552048, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24283470213413239, 0.15604373812675476, 0.2524269223213196], "policy_updates": 25400, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2009.2636029670002, "contact_bce": 0.3228154182434082, "contact_force_loss": 0.03246843442320824, "terrain_level_mean": 2.954345703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9997882843017578, 0.9992313981056213, 2.995011329650879]} {"step": 25510, "actor_lr": 4.959270472949376e-06, "archive_windows": 100000, "env_steps": 25510, "total_transitions": 104488960, "num_steps_per_env": 1, "wm_loss": 0.4741591811180115, "actor_loss": -8.823966979980469, "critic_loss": 0.02878892421722412, "reward": 0.07141095399856567, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24510717391967773, 0.15185074508190155, 0.24919460713863373], "policy_updates": 25410, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2013.8265228760001, "contact_bce": 0.32491016387939453, "contact_force_loss": 0.0317663736641407, "terrain_level_mean": 2.95458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9997882843017578, 0.9992313981056213, 2.995011329650879]} {"step": 25520, "actor_lr": 4.945475639183344e-06, "archive_windows": 100000, "env_steps": 25520, "total_transitions": 104529920, "num_steps_per_env": 1, "wm_loss": 0.5069881081581116, "actor_loss": -8.870476722717285, "critic_loss": 0.021652616560459137, "reward": 0.07130429148674011, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2479436844587326, 0.15134626626968384, 0.24976889789104462], "policy_updates": 25420, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2018.6815633219999, "contact_bce": 0.3273646831512451, "contact_force_loss": 0.03265997767448425, "terrain_level_mean": 2.955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.9997882843017578, 0.9992313981056213, 2.995011329650879]} {"step": 25530, "actor_lr": 4.9317092677355935e-06, "archive_windows": 100000, "env_steps": 25530, "total_transitions": 104570880, "num_steps_per_env": 1, "wm_loss": 0.5356382131576538, "actor_loss": -8.844242095947266, "critic_loss": 0.02560807205736637, "reward": 0.07126516848802567, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24431723356246948, 0.15137341618537903, 0.24976599216461182], "policy_updates": 25430, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2023.2178763750003, "contact_bce": 0.32622864842414856, "contact_force_loss": 0.03321755677461624, "terrain_level_mean": 2.95458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9964479207992554, 0.9992313981056213, 2.995011329650879]} {"step": 25540, "actor_lr": 4.917971373702626e-06, "archive_windows": 100000, "env_steps": 25540, "total_transitions": 104611840, "num_steps_per_env": 1, "wm_loss": 0.5065544843673706, "actor_loss": -8.809743881225586, "critic_loss": 0.02224818244576454, "reward": 0.07108552008867264, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24070657789707184, 0.1516198068857193, 0.2531256079673767], "policy_updates": 25440, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2027.774614974, "contact_bce": 0.32764798402786255, "contact_force_loss": 0.03284785524010658, "terrain_level_mean": 2.955322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9964479207992554, 0.9992313981056213, 2.9993104934692383]} {"step": 25550, "actor_lr": 4.904261972149735e-06, "archive_windows": 100000, "env_steps": 25550, "total_transitions": 104652800, "num_steps_per_env": 1, "wm_loss": 0.500845193862915, "actor_loss": -8.825297355651855, "critic_loss": 0.02090074121952057, "reward": 0.0707588940858841, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24016183614730835, 0.15215343236923218, 0.2569044828414917], "policy_updates": 25450, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2032.3035319780001, "contact_bce": 0.3196055293083191, "contact_force_loss": 0.03237839788198471, "terrain_level_mean": 2.955322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9964479207992554, 0.9992313981056213, 2.9993104934692383]} {"step": 25560, "actor_lr": 4.890581078110951e-06, "archive_windows": 100000, "env_steps": 25560, "total_transitions": 104693760, "num_steps_per_env": 1, "wm_loss": 0.4922541081905365, "actor_loss": -8.797577857971191, "critic_loss": 0.02320202998816967, "reward": 0.0706012174487114, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24430035054683685, 0.1532234102487564, 0.25677257776260376], "policy_updates": 25460, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2036.8094636780002, "contact_bce": 0.32198506593704224, "contact_force_loss": 0.03277963399887085, "terrain_level_mean": 2.955810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9975266456604004, 0.9992313981056213, 2.9993104934692383]} {"step": 25570, "actor_lr": 4.8769287065890585e-06, "archive_windows": 100000, "env_steps": 25570, "total_transitions": 104734720, "num_steps_per_env": 1, "wm_loss": 0.4734314978122711, "actor_loss": -8.814125061035156, "critic_loss": 0.01829005591571331, "reward": 0.07040181010961533, "falls": 13, "interval_steps": 10, "velocity_mae": [0.24319057166576385, 0.1541730910539627, 0.2548869550228119], "policy_updates": 25470, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2041.2949518280002, "contact_bce": 0.3244922161102295, "contact_force_loss": 0.032191988080739975, "terrain_level_mean": 2.952880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9975266456604004, 0.9992313981056213, 2.9993104934692383]} {"step": 25580, "actor_lr": 4.8633048725555464e-06, "archive_windows": 100000, "env_steps": 25580, "total_transitions": 104775680, "num_steps_per_env": 1, "wm_loss": 0.487680047750473, "actor_loss": -8.829964637756348, "critic_loss": 0.020062990486621857, "reward": 0.07053341716527939, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2412572056055069, 0.15434351563453674, 0.2565607726573944], "policy_updates": 25480, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2045.772040834, "contact_bce": 0.3239777088165283, "contact_force_loss": 0.03294182941317558, "terrain_level_mean": 2.954345703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9975266456604004, 0.9992313981056213, 2.9993104934692383]} {"step": 25590, "actor_lr": 4.849709590950635e-06, "archive_windows": 100000, "env_steps": 25590, "total_transitions": 104816640, "num_steps_per_env": 1, "wm_loss": 0.4806182384490967, "actor_loss": -8.848499298095703, "critic_loss": 0.025419021025300026, "reward": 0.07071738690137863, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23838262259960175, 0.153873473405838, 0.25683218240737915], "policy_updates": 25490, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2050.252965923, "contact_bce": 0.3288488984107971, "contact_force_loss": 0.03292582929134369, "terrain_level_mean": 2.95458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9975266456604004, 0.9992313981056213, 2.9993104934692383]} {"step": 25600, "actor_lr": 4.836142876683217e-06, "archive_windows": 100000, "env_steps": 25600, "total_transitions": 104857600, "num_steps_per_env": 1, "wm_loss": 0.46902769804000854, "actor_loss": -8.878030776977539, "critic_loss": 0.0220470167696476, "reward": 0.07070758193731308, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23881025612354279, 0.1551237255334854, 0.2537168860435486], "policy_updates": 25500, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2054.719232969, "contact_bce": 0.32533109188079834, "contact_force_loss": 0.03308291360735893, "terrain_level_mean": 2.955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9975266456604004, 0.9992313981056213, 2.9993104934692383]} {"step": 25610, "actor_lr": 4.822604744630834e-06, "archive_windows": 100000, "env_steps": 25610, "total_transitions": 104898560, "num_steps_per_env": 1, "wm_loss": 0.5084546208381653, "actor_loss": -8.803510665893555, "critic_loss": 0.02544783428311348, "reward": 0.07063847780227661, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24045465886592865, 0.15057551860809326, 0.25342726707458496], "policy_updates": 25510, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2059.135492729, "contact_bce": 0.3283011317253113, "contact_force_loss": 0.03352043032646179, "terrain_level_mean": 2.955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9975266456604004, 0.9992313981056213, 2.9993104934692383]} {"step": 25620, "actor_lr": 4.8090952096397345e-06, "archive_windows": 100000, "env_steps": 25620, "total_transitions": 104939520, "num_steps_per_env": 1, "wm_loss": 0.5088146328926086, "actor_loss": -8.835243225097656, "critic_loss": 0.027157438918948174, "reward": 0.07084397971630096, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2388296127319336, 0.1511368602514267, 0.25517538189888], "policy_updates": 25520, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2063.589393275, "contact_bce": 0.3268147110939026, "contact_force_loss": 0.03258206695318222, "terrain_level_mean": 2.955322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.998627781867981, 0.9988020658493042, 2.9993104934692383]} {"step": 25630, "actor_lr": 4.795614286524769e-06, "archive_windows": 100000, "env_steps": 25630, "total_transitions": 104980480, "num_steps_per_env": 1, "wm_loss": 0.4855283498764038, "actor_loss": -8.84897232055664, "critic_loss": 0.035554852336645126, "reward": 0.0714060589671135, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2390119880437851, 0.15262244641780853, 0.2518780827522278], "policy_updates": 25530, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2068.0546749160003, "contact_bce": 0.3289863169193268, "contact_force_loss": 0.032841283828020096, "terrain_level_mean": 2.955322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.998627781867981, 0.9991803169250488, 2.9993104934692383]} {"step": 25640, "actor_lr": 4.782161990069416e-06, "archive_windows": 100000, "env_steps": 25640, "total_transitions": 105021440, "num_steps_per_env": 1, "wm_loss": 0.5021610260009766, "actor_loss": -8.80286979675293, "critic_loss": 0.02891453541815281, "reward": 0.07115713506937027, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23737111687660217, 0.15362447500228882, 0.2547926902770996], "policy_updates": 25540, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2072.513712809, "contact_bce": 0.32509833574295044, "contact_force_loss": 0.03270729258656502, "terrain_level_mean": 2.955322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.998627781867981, 0.9991803169250488, 2.9993104934692383]} {"step": 25650, "actor_lr": 4.768738335025792e-06, "archive_windows": 100000, "env_steps": 25650, "total_transitions": 105062400, "num_steps_per_env": 1, "wm_loss": 0.5115162134170532, "actor_loss": -8.845362663269043, "critic_loss": 0.02823919616639614, "reward": 0.07093875855207443, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23778408765792847, 0.15312935411930084, 0.2502354383468628], "policy_updates": 25550, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2076.980652857, "contact_bce": 0.32451164722442627, "contact_force_loss": 0.03225352615118027, "terrain_level_mean": 2.95556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9993104934692383]} {"step": 25660, "actor_lr": 4.755343336114555e-06, "archive_windows": 100000, "env_steps": 25660, "total_transitions": 105103360, "num_steps_per_env": 1, "wm_loss": 0.48739248514175415, "actor_loss": -8.87527084350586, "critic_loss": 0.01497924979776144, "reward": 0.07049613445997238, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2426997572183609, 0.15243740379810333, 0.25464025139808655], "policy_updates": 25560, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2081.424006741, "contact_bce": 0.3291260302066803, "contact_force_loss": 0.032872676849365234, "terrain_level_mean": 2.955810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9993104934692383]} {"step": 25670, "actor_lr": 4.741977008024967e-06, "archive_windows": 100000, "env_steps": 25670, "total_transitions": 105144320, "num_steps_per_env": 1, "wm_loss": 0.5250823497772217, "actor_loss": -8.825927734375, "critic_loss": 0.01789151504635811, "reward": 0.0706324502825737, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24347707629203796, 0.15373298525810242, 0.2561372220516205], "policy_updates": 25570, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2085.909205381, "contact_bce": 0.3215649127960205, "contact_force_loss": 0.033510662615299225, "terrain_level_mean": 2.955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9993104934692383]} {"step": 25680, "actor_lr": 4.7286393654148576e-06, "archive_windows": 100000, "env_steps": 25680, "total_transitions": 105185280, "num_steps_per_env": 1, "wm_loss": 0.4717673361301422, "actor_loss": -8.812885284423828, "critic_loss": 0.019894415512681007, "reward": 0.07127274572849274, "falls": 5, "interval_steps": 10, "velocity_mae": [0.242889404296875, 0.15274015069007874, 0.25490909814834595], "policy_updates": 25580, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2090.352340105, "contact_bce": 0.32303386926651, "contact_force_loss": 0.03272758051753044, "terrain_level_mean": 2.954833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25690, "actor_lr": 4.71533042291058e-06, "archive_windows": 100000, "env_steps": 25690, "total_transitions": 105226240, "num_steps_per_env": 1, "wm_loss": 0.5011568665504456, "actor_loss": -8.883776664733887, "critic_loss": 0.023165995255112648, "reward": 0.07134842872619629, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24105174839496613, 0.15154513716697693, 0.252156138420105], "policy_updates": 25590, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2094.799893711, "contact_bce": 0.3141937255859375, "contact_force_loss": 0.03175337612628937, "terrain_level_mean": 2.95458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25700, "actor_lr": 4.702050195107024e-06, "archive_windows": 100000, "env_steps": 25700, "total_transitions": 105267200, "num_steps_per_env": 1, "wm_loss": 0.48707517981529236, "actor_loss": -8.832141876220703, "critic_loss": 0.019885605201125145, "reward": 0.07124132663011551, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23788213729858398, 0.15249484777450562, 0.24851474165916443], "policy_updates": 25600, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2099.261884854, "contact_bce": 0.32579323649406433, "contact_force_loss": 0.03279105946421623, "terrain_level_mean": 2.95556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25710, "actor_lr": 4.688798696567586e-06, "archive_windows": 100000, "env_steps": 25710, "total_transitions": 105308160, "num_steps_per_env": 1, "wm_loss": 0.48004642128944397, "actor_loss": -8.835304260253906, "critic_loss": 0.027264678850769997, "reward": 0.07111146301031113, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23627083003520966, 0.15233784914016724, 0.2518683671951294], "policy_updates": 25610, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2103.7299805860002, "contact_bce": 0.32645460963249207, "contact_force_loss": 0.03259572014212608, "terrain_level_mean": 2.956787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25720, "actor_lr": 4.67557594182416e-06, "archive_windows": 100000, "env_steps": 25720, "total_transitions": 105349120, "num_steps_per_env": 1, "wm_loss": 0.49371814727783203, "actor_loss": -8.855452537536621, "critic_loss": 0.020494332537055016, "reward": 0.07122660428285599, "falls": 5, "interval_steps": 10, "velocity_mae": [0.234561026096344, 0.15367533266544342, 0.24943190813064575], "policy_updates": 25620, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2108.240044308, "contact_bce": 0.31891652941703796, "contact_force_loss": 0.032731205224990845, "terrain_level_mean": 2.956787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25730, "actor_lr": 4.662381945377109e-06, "archive_windows": 100000, "env_steps": 25730, "total_transitions": 105390080, "num_steps_per_env": 1, "wm_loss": 0.5056506991386414, "actor_loss": -8.847593307495117, "critic_loss": 0.022184476256370544, "reward": 0.07146129012107849, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23675745725631714, 0.15635167062282562, 0.2504374384880066], "policy_updates": 25630, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2112.7497078310003, "contact_bce": 0.3268062472343445, "contact_force_loss": 0.033273909240961075, "terrain_level_mean": 2.95654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25740, "actor_lr": 4.649216721695286e-06, "archive_windows": 100000, "env_steps": 25740, "total_transitions": 105431040, "num_steps_per_env": 1, "wm_loss": 0.4982512295246124, "actor_loss": -8.785989761352539, "critic_loss": 0.02361108735203743, "reward": 0.07132188975811005, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23901976644992828, 0.15570813417434692, 0.25314849615097046], "policy_updates": 25640, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2117.214574994, "contact_bce": 0.32076752185821533, "contact_force_loss": 0.032743558287620544, "terrain_level_mean": 2.95751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25750, "actor_lr": 4.636080285215961e-06, "archive_windows": 100000, "env_steps": 25750, "total_transitions": 105472000, "num_steps_per_env": 1, "wm_loss": 0.5087983012199402, "actor_loss": -8.892705917358398, "critic_loss": 0.020903322845697403, "reward": 0.0713549256324768, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2402545064687729, 0.15520592033863068, 0.2554171085357666], "policy_updates": 25650, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2121.7347027220003, "contact_bce": 0.3285973370075226, "contact_force_loss": 0.033002328127622604, "terrain_level_mean": 2.956298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25760, "actor_lr": 4.622972650344845e-06, "archive_windows": 100000, "env_steps": 25760, "total_transitions": 105512960, "num_steps_per_env": 1, "wm_loss": 0.4753413498401642, "actor_loss": -8.865020751953125, "critic_loss": 0.02904191054403782, "reward": 0.07151943445205688, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23780383169651031, 0.1529300957918167, 0.25197115540504456], "policy_updates": 25660, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2126.225043596, "contact_bce": 0.3233165144920349, "contact_force_loss": 0.03266018256545067, "terrain_level_mean": 2.957275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25770, "actor_lr": 4.6098938314560754e-06, "archive_windows": 100000, "env_steps": 25770, "total_transitions": 105553920, "num_steps_per_env": 1, "wm_loss": 0.5185093283653259, "actor_loss": -8.816295623779297, "critic_loss": 0.024286119267344475, "reward": 0.07180560380220413, "falls": 3, "interval_steps": 10, "velocity_mae": [0.232650026679039, 0.15260446071624756, 0.2525081932544708], "policy_updates": 25670, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2130.731828108, "contact_bce": 0.3289327621459961, "contact_force_loss": 0.03367052227258682, "terrain_level_mean": 2.958984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.998627781867981, 0.9994785189628601, 2.9963884353637695]} {"step": 25780, "actor_lr": 4.596843842892176e-06, "archive_windows": 100000, "env_steps": 25780, "total_transitions": 105594880, "num_steps_per_env": 1, "wm_loss": 0.4941966235637665, "actor_loss": -8.838397979736328, "critic_loss": 0.019486503675580025, "reward": 0.07216781377792358, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23175136744976044, 0.1533757597208023, 0.25083038210868835], "policy_updates": 25680, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2135.242280591, "contact_bce": 0.3232167363166809, "contact_force_loss": 0.03323088586330414, "terrain_level_mean": 2.959228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25790, "actor_lr": 4.583822698964056e-06, "archive_windows": 100000, "env_steps": 25790, "total_transitions": 105635840, "num_steps_per_env": 1, "wm_loss": 0.4751615524291992, "actor_loss": -8.838858604431152, "critic_loss": 0.024646060541272163, "reward": 0.07151152193546295, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23958151042461395, 0.15458323061466217, 0.25227582454681396], "policy_updates": 25690, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2139.744968681, "contact_bce": 0.32380834221839905, "contact_force_loss": 0.03263361379504204, "terrain_level_mean": 2.95947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25800, "actor_lr": 4.570830413951001e-06, "archive_windows": 100000, "env_steps": 25800, "total_transitions": 105676800, "num_steps_per_env": 1, "wm_loss": 0.4811762571334839, "actor_loss": -8.877463340759277, "critic_loss": 0.02156246267259121, "reward": 0.0710410624742508, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2416711002588272, 0.15653905272483826, 0.2540290355682373], "policy_updates": 25700, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2144.2445799760003, "contact_bce": 0.3289138972759247, "contact_force_loss": 0.032829541712999344, "terrain_level_mean": 2.95947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25810, "actor_lr": 4.557867002100646e-06, "archive_windows": 100000, "env_steps": 25810, "total_transitions": 105717760, "num_steps_per_env": 1, "wm_loss": 0.5517610311508179, "actor_loss": -8.81975269317627, "critic_loss": 0.02788998745381832, "reward": 0.07092853635549545, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24521654844284058, 0.15697689354419708, 0.2538532316684723], "policy_updates": 25710, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2148.739383774, "contact_bce": 0.33232325315475464, "contact_force_loss": 0.03456900268793106, "terrain_level_mean": 2.960205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25820, "actor_lr": 4.544932477628956e-06, "archive_windows": 100000, "env_steps": 25820, "total_transitions": 105758720, "num_steps_per_env": 1, "wm_loss": 0.5345534682273865, "actor_loss": -8.84256362915039, "critic_loss": 0.02086920104920864, "reward": 0.07100007683038712, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24078574776649475, 0.15596050024032593, 0.2526470422744751], "policy_updates": 25720, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2153.235531145, "contact_bce": 0.32628434896469116, "contact_force_loss": 0.033027030527591705, "terrain_level_mean": 2.961669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25830, "actor_lr": 4.532026854720228e-06, "archive_windows": 100000, "env_steps": 25830, "total_transitions": 105799680, "num_steps_per_env": 1, "wm_loss": 0.49218976497650146, "actor_loss": -8.79171371459961, "critic_loss": 0.02409902587532997, "reward": 0.07125599682331085, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23963505029678345, 0.1555939018726349, 0.25381773710250854], "policy_updates": 25730, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2157.700130066, "contact_bce": 0.32827067375183105, "contact_force_loss": 0.03295592963695526, "terrain_level_mean": 2.962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3291015625, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25840, "actor_lr": 4.519150147527057e-06, "archive_windows": 100000, "env_steps": 25840, "total_transitions": 105840640, "num_steps_per_env": 1, "wm_loss": 0.5055721402168274, "actor_loss": -8.834773063659668, "critic_loss": 0.017046106979250908, "reward": 0.07097354531288147, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24672652781009674, 0.1580376923084259, 0.25171399116516113], "policy_updates": 25740, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2162.1542891110003, "contact_bce": 0.32307863235473633, "contact_force_loss": 0.032623808830976486, "terrain_level_mean": 2.96337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25850, "actor_lr": 4.5063023701703285e-06, "archive_windows": 100000, "env_steps": 25850, "total_transitions": 105881600, "num_steps_per_env": 1, "wm_loss": 0.5006754994392395, "actor_loss": -8.816689491271973, "critic_loss": 0.022492630407214165, "reward": 0.07109414786100388, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24637073278427124, 0.1572277843952179, 0.2502569258213043], "policy_updates": 25750, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2166.675176956, "contact_bce": 0.32790321111679077, "contact_force_loss": 0.03306195139884949, "terrain_level_mean": 2.963623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9963884353637695]} {"step": 25860, "actor_lr": 4.493483536739213e-06, "archive_windows": 100000, "env_steps": 25860, "total_transitions": 105922560, "num_steps_per_env": 1, "wm_loss": 0.4531055986881256, "actor_loss": -8.90374755859375, "critic_loss": 0.014793932437896729, "reward": 0.07108326256275177, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24565881490707397, 0.15685999393463135, 0.25503653287887573], "policy_updates": 25760, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2171.190070337, "contact_bce": 0.3260064721107483, "contact_force_loss": 0.03198949992656708, "terrain_level_mean": 2.964111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.9976561069488525]} {"step": 25870, "actor_lr": 4.480693661291136e-06, "archive_windows": 100000, "env_steps": 25870, "total_transitions": 105963520, "num_steps_per_env": 1, "wm_loss": 0.5083388686180115, "actor_loss": -8.867284774780273, "critic_loss": 0.017193613573908806, "reward": 0.07098652422428131, "falls": 4, "interval_steps": 10, "velocity_mae": [0.245649054646492, 0.1575586199760437, 0.25871145725250244], "policy_updates": 25770, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2175.639833223, "contact_bce": 0.33223724365234375, "contact_force_loss": 0.033399488776922226, "terrain_level_mean": 2.965087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.9976561069488525]} {"step": 25880, "actor_lr": 4.467932757851746e-06, "archive_windows": 100000, "env_steps": 25880, "total_transitions": 106004480, "num_steps_per_env": 1, "wm_loss": 0.48321959376335144, "actor_loss": -8.830806732177734, "critic_loss": 0.017753921449184418, "reward": 0.07101254910230637, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24716271460056305, 0.15929833054542542, 0.25693923234939575], "policy_updates": 25780, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2180.0781928280003, "contact_bce": 0.32695668935775757, "contact_force_loss": 0.03285479173064232, "terrain_level_mean": 2.967041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.9976561069488525]} {"step": 25890, "actor_lr": 4.4552008404149545e-06, "archive_windows": 100000, "env_steps": 25890, "total_transitions": 106045440, "num_steps_per_env": 1, "wm_loss": 0.4983822703361511, "actor_loss": -8.835978507995605, "critic_loss": 0.026568666100502014, "reward": 0.0711764246225357, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2464074343442917, 0.15901777148246765, 0.2540757954120636], "policy_updates": 25790, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2184.596339801, "contact_bce": 0.3235187232494354, "contact_force_loss": 0.032968614250421524, "terrain_level_mean": 2.968017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.9976561069488525]} {"step": 25900, "actor_lr": 4.442497922942866e-06, "archive_windows": 100000, "env_steps": 25900, "total_transitions": 106086400, "num_steps_per_env": 1, "wm_loss": 0.4864790141582489, "actor_loss": -8.839764595031738, "critic_loss": 0.03152021765708923, "reward": 0.0711311548948288, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2473074048757553, 0.1582118272781372, 0.25440114736557007], "policy_updates": 25800, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2189.100414118, "contact_bce": 0.3257620930671692, "contact_force_loss": 0.033131398260593414, "terrain_level_mean": 2.968017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.9976561069488525]} {"step": 25910, "actor_lr": 4.429824019365782e-06, "archive_windows": 100000, "env_steps": 25910, "total_transitions": 106127360, "num_steps_per_env": 1, "wm_loss": 0.5174004435539246, "actor_loss": -8.791380882263184, "critic_loss": 0.0255707036703825, "reward": 0.07109517604112625, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24728915095329285, 0.1597694456577301, 0.25869473814964294], "policy_updates": 25810, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2193.568317616, "contact_bce": 0.32916682958602905, "contact_force_loss": 0.034055449068546295, "terrain_level_mean": 2.96875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.9976561069488525]} {"step": 25920, "actor_lr": 4.417179143582198e-06, "archive_windows": 100000, "env_steps": 25920, "total_transitions": 106168320, "num_steps_per_env": 1, "wm_loss": 0.4617805778980255, "actor_loss": -8.794851303100586, "critic_loss": 0.01746712438762188, "reward": 0.07096552103757858, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2507638931274414, 0.15878716111183167, 0.2559395432472229], "policy_updates": 25820, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2198.029523789, "contact_bce": 0.32503682374954224, "contact_force_loss": 0.03294382989406586, "terrain_level_mean": 2.968017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.9976561069488525]} {"step": 25930, "actor_lr": 4.404563309458777e-06, "archive_windows": 100000, "env_steps": 25930, "total_transitions": 106209280, "num_steps_per_env": 1, "wm_loss": 0.5008640885353088, "actor_loss": -8.831007957458496, "critic_loss": 0.03100242093205452, "reward": 0.07059982419013977, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25186777114868164, 0.15932610630989075, 0.25557151436805725], "policy_updates": 25830, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2202.5440553020003, "contact_bce": 0.3281562328338623, "contact_force_loss": 0.03362694010138512, "terrain_level_mean": 2.968994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.9976561069488525]} {"step": 25940, "actor_lr": 4.391976530830308e-06, "archive_windows": 100000, "env_steps": 25940, "total_transitions": 106250240, "num_steps_per_env": 1, "wm_loss": 0.5045618414878845, "actor_loss": -8.824817657470703, "critic_loss": 0.022036314010620117, "reward": 0.07100814580917358, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24523037672042847, 0.15679492056369781, 0.25372669100761414], "policy_updates": 25840, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2206.993872258, "contact_bce": 0.3292175531387329, "contact_force_loss": 0.03282441943883896, "terrain_level_mean": 2.96875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.998727798461914]} {"step": 25950, "actor_lr": 4.379418821499752e-06, "archive_windows": 100000, "env_steps": 25950, "total_transitions": 106291200, "num_steps_per_env": 1, "wm_loss": 0.5506442189216614, "actor_loss": -8.81350326538086, "critic_loss": 0.022692115977406502, "reward": 0.07139074802398682, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24400831758975983, 0.15561947226524353, 0.2545713782310486], "policy_updates": 25850, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2211.441765704, "contact_bce": 0.3310004770755768, "contact_force_loss": 0.033826570957899094, "terrain_level_mean": 2.96875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9998782873153687, 0.9994785189628601, 2.998727798461914]} {"step": 25960, "actor_lr": 4.366890195238175e-06, "archive_windows": 100000, "env_steps": 25960, "total_transitions": 106332160, "num_steps_per_env": 1, "wm_loss": 0.4800547957420349, "actor_loss": -8.827244758605957, "critic_loss": 0.021979764103889465, "reward": 0.07180999964475632, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2447214275598526, 0.15454374253749847, 0.257269024848938], "policy_updates": 25860, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2215.882969242, "contact_bce": 0.32436853647232056, "contact_force_loss": 0.032341040670871735, "terrain_level_mean": 2.968505859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9998397827148438, 0.9994785189628601, 2.998727798461914]} {"step": 25970, "actor_lr": 4.354390665784747e-06, "archive_windows": 100000, "env_steps": 25970, "total_transitions": 106373120, "num_steps_per_env": 1, "wm_loss": 0.47870704531669617, "actor_loss": -8.784385681152344, "critic_loss": 0.029802296310663223, "reward": 0.07183248549699783, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24299952387809753, 0.15729032456874847, 0.2534092962741852], "policy_updates": 25870, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2220.357936283, "contact_bce": 0.3261464536190033, "contact_force_loss": 0.032956041395664215, "terrain_level_mean": 2.96826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9990572929382324, 0.9994785189628601, 2.998727798461914]} {"step": 25980, "actor_lr": 4.3419202468467465e-06, "archive_windows": 100000, "env_steps": 25980, "total_transitions": 106414080, "num_steps_per_env": 1, "wm_loss": 0.5200255513191223, "actor_loss": -8.820525169372559, "critic_loss": 0.027738606557250023, "reward": 0.0717131495475769, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23801802098751068, 0.15956248342990875, 0.2536779046058655], "policy_updates": 25880, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2224.813286483, "contact_bce": 0.3265591263771057, "contact_force_loss": 0.03343026340007782, "terrain_level_mean": 2.96826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9990572929382324, 0.9994785189628601, 2.998727798461914]} {"step": 25990, "actor_lr": 4.329478952099505e-06, "archive_windows": 100000, "env_steps": 25990, "total_transitions": 106455040, "num_steps_per_env": 1, "wm_loss": 0.4782654941082001, "actor_loss": -8.803277969360352, "critic_loss": 0.02126162126660347, "reward": 0.07182274013757706, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24058370292186737, 0.1571483165025711, 0.25057122111320496], "policy_updates": 25890, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2229.2642742020003, "contact_bce": 0.3230501711368561, "contact_force_loss": 0.03284769132733345, "terrain_level_mean": 2.968017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9990572929382324, 0.9994785189628601, 2.998727798461914]} {"step": 26000, "actor_lr": 4.317066795186425e-06, "archive_windows": 100000, "env_steps": 26000, "total_transitions": 106496000, "num_steps_per_env": 1, "wm_loss": 0.4697859585285187, "actor_loss": -8.865999221801758, "critic_loss": 0.017831936478614807, "reward": 0.07149744778871536, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24111121892929077, 0.1578986644744873, 0.2525360882282257], "policy_updates": 25900, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2233.728099555, "contact_bce": 0.3249831795692444, "contact_force_loss": 0.032027050852775574, "terrain_level_mean": 2.968505859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.99944269657135, 0.9987807869911194, 2.998727798461914]} {"step": 26010, "actor_lr": 4.3046837897189675e-06, "archive_windows": 100000, "env_steps": 26010, "total_transitions": 106536960, "num_steps_per_env": 1, "wm_loss": 0.49914899468421936, "actor_loss": -8.809642791748047, "critic_loss": 0.019442245364189148, "reward": 0.07142355293035507, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24236156046390533, 0.15583248436450958, 0.24705234169960022], "policy_updates": 25910, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2238.30283552, "contact_bce": 0.3245886564254761, "contact_force_loss": 0.03254801407456398, "terrain_level_mean": 2.968994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.99944269657135, 0.9987807869911194, 2.998727798461914]} {"step": 26020, "actor_lr": 4.292329949276616e-06, "archive_windows": 100000, "env_steps": 26020, "total_transitions": 106577920, "num_steps_per_env": 1, "wm_loss": 0.5230609774589539, "actor_loss": -8.773004531860352, "critic_loss": 0.020462026819586754, "reward": 0.07134277373552322, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23763635754585266, 0.15500570833683014, 0.24767985939979553], "policy_updates": 25920, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2243.152508179, "contact_bce": 0.33030274510383606, "contact_force_loss": 0.0336051844060421, "terrain_level_mean": 2.9697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.99944269657135, 0.9987807869911194, 2.998727798461914]} {"step": 26030, "actor_lr": 4.2800052874068705e-06, "archive_windows": 100000, "env_steps": 26030, "total_transitions": 106618880, "num_steps_per_env": 1, "wm_loss": 0.49901875853538513, "actor_loss": -8.840047836303711, "critic_loss": 0.02693338133394718, "reward": 0.07144349813461304, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23934409022331238, 0.1560620814561844, 0.2533746361732483], "policy_updates": 25930, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2247.631639041, "contact_bce": 0.319070428609848, "contact_force_loss": 0.033396054059267044, "terrain_level_mean": 2.971923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.99944269657135, 0.9987807869911194, 2.998727798461914]} {"step": 26040, "actor_lr": 4.267709817625228e-06, "archive_windows": 100000, "env_steps": 26040, "total_transitions": 106659840, "num_steps_per_env": 1, "wm_loss": 0.46486032009124756, "actor_loss": -8.797486305236816, "critic_loss": 0.02216462604701519, "reward": 0.07104940712451935, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24104338884353638, 0.15584874153137207, 0.25490644574165344], "policy_updates": 25940, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2252.102827992, "contact_bce": 0.3264462351799011, "contact_force_loss": 0.03233472257852554, "terrain_level_mean": 2.971923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.99944269657135, 0.9987807869911194, 2.998727798461914]} {"step": 26050, "actor_lr": 4.255443553415185e-06, "archive_windows": 100000, "env_steps": 26050, "total_transitions": 106700800, "num_steps_per_env": 1, "wm_loss": 0.48268282413482666, "actor_loss": -8.851696014404297, "critic_loss": 0.01846640557050705, "reward": 0.07130562514066696, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23966102302074432, 0.1559167206287384, 0.2499738186597824], "policy_updates": 25950, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2256.5537999440003, "contact_bce": 0.3213807940483093, "contact_force_loss": 0.032459501177072525, "terrain_level_mean": 2.97265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.99944269657135, 0.9987807869911194, 2.998727798461914]} {"step": 26060, "actor_lr": 4.2432065082281955e-06, "archive_windows": 100000, "env_steps": 26060, "total_transitions": 106741760, "num_steps_per_env": 1, "wm_loss": 0.4949854910373688, "actor_loss": -8.802069664001465, "critic_loss": 0.07727395743131638, "reward": 0.07139461487531662, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2370092272758484, 0.1571991890668869, 0.2483949363231659], "policy_updates": 25960, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2260.965282745, "contact_bce": 0.3310883045196533, "contact_force_loss": 0.03354265168309212, "terrain_level_mean": 2.973876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26070, "actor_lr": 4.230998695483692e-06, "archive_windows": 100000, "env_steps": 26070, "total_transitions": 106782720, "num_steps_per_env": 1, "wm_loss": 0.5014116764068604, "actor_loss": -8.860062599182129, "critic_loss": 0.022855093702673912, "reward": 0.07145573943853378, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23525483906269073, 0.15403582155704498, 0.25150102376937866], "policy_updates": 25970, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2265.448320205, "contact_bce": 0.3289990723133087, "contact_force_loss": 0.03328351303935051, "terrain_level_mean": 2.973388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26080, "actor_lr": 4.21882012856903e-06, "archive_windows": 100000, "env_steps": 26080, "total_transitions": 106823680, "num_steps_per_env": 1, "wm_loss": 0.48626798391342163, "actor_loss": -8.753334999084473, "critic_loss": 0.03181035444140434, "reward": 0.07132703810930252, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24087785184383392, 0.15207722783088684, 0.25596487522125244], "policy_updates": 25980, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2269.8823404160003, "contact_bce": 0.32996004819869995, "contact_force_loss": 0.033827148377895355, "terrain_level_mean": 2.97314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26090, "actor_lr": 4.206670820839508e-06, "archive_windows": 100000, "env_steps": 26090, "total_transitions": 106864640, "num_steps_per_env": 1, "wm_loss": 0.5218168497085571, "actor_loss": -8.783439636230469, "critic_loss": 0.03537633270025253, "reward": 0.0709976777434349, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24050173163414001, 0.15705005824565887, 0.2524048984050751], "policy_updates": 25990, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2274.307204127, "contact_bce": 0.32639580965042114, "contact_force_loss": 0.03368910402059555, "terrain_level_mean": 2.973876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26100, "actor_lr": 4.194550785618323e-06, "archive_windows": 100000, "env_steps": 26100, "total_transitions": 106905600, "num_steps_per_env": 1, "wm_loss": 0.5202011466026306, "actor_loss": -8.782949447631836, "critic_loss": 0.03326043859124184, "reward": 0.07073097676038742, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23870588839054108, 0.15867523849010468, 0.2540327310562134], "policy_updates": 26000, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2278.715483758, "contact_bce": 0.32128727436065674, "contact_force_loss": 0.03287162631750107, "terrain_level_mean": 2.9736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26110, "actor_lr": 4.1824600361965875e-06, "archive_windows": 100000, "env_steps": 26110, "total_transitions": 106946560, "num_steps_per_env": 1, "wm_loss": 0.5123980641365051, "actor_loss": -8.827406883239746, "critic_loss": 0.025780463591217995, "reward": 0.07104824483394623, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23636431992053986, 0.1557927131652832, 0.25396832823753357], "policy_updates": 26010, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2283.142085893, "contact_bce": 0.32339566946029663, "contact_force_loss": 0.03310651704668999, "terrain_level_mean": 2.973388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26120, "actor_lr": 4.170398585833281e-06, "archive_windows": 100000, "env_steps": 26120, "total_transitions": 106987520, "num_steps_per_env": 1, "wm_loss": 0.5299981236457825, "actor_loss": -8.816213607788086, "critic_loss": 0.02442716248333454, "reward": 0.07101382315158844, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23604367673397064, 0.1548311412334442, 0.2552490830421448], "policy_updates": 26020, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2287.575872676, "contact_bce": 0.322189599275589, "contact_force_loss": 0.03329833596944809, "terrain_level_mean": 2.97412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26130, "actor_lr": 4.158366447755272e-06, "archive_windows": 100000, "env_steps": 26130, "total_transitions": 107028480, "num_steps_per_env": 1, "wm_loss": 0.48691537976264954, "actor_loss": -8.836128234863281, "critic_loss": 0.027243290096521378, "reward": 0.07095843553543091, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24027247726917267, 0.15625229477882385, 0.25281158089637756], "policy_updates": 26030, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2291.995236153, "contact_bce": 0.3291498124599457, "contact_force_loss": 0.03289069980382919, "terrain_level_mean": 2.974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9991121292114258, 0.9987807869911194, 2.998727798461914]} {"step": 26140, "actor_lr": 4.146363635157275e-06, "archive_windows": 100000, "env_steps": 26140, "total_transitions": 107069440, "num_steps_per_env": 1, "wm_loss": 0.5193657279014587, "actor_loss": -8.81044864654541, "critic_loss": 0.02571347914636135, "reward": 0.07103616744279861, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2393721640110016, 0.15681414306163788, 0.2556588649749756], "policy_updates": 26040, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2296.411314084, "contact_bce": 0.3245513141155243, "contact_force_loss": 0.03318914771080017, "terrain_level_mean": 2.97607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9993772506713867, 0.9987807869911194, 2.998727798461914]} {"step": 26150, "actor_lr": 4.1343901612018394e-06, "archive_windows": 100000, "env_steps": 26150, "total_transitions": 107110400, "num_steps_per_env": 1, "wm_loss": 0.4579634666442871, "actor_loss": -8.822635650634766, "critic_loss": 0.02370193414390087, "reward": 0.07055707275867462, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24090199172496796, 0.15614549815654755, 0.2532549500465393], "policy_updates": 26050, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2300.820519355, "contact_bce": 0.3278839886188507, "contact_force_loss": 0.03262649103999138, "terrain_level_mean": 2.97607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333740234375, "command_abs_max": [1.9993772506713867, 0.9987807869911194, 2.998727798461914]} {"step": 26160, "actor_lr": 4.122446039019352e-06, "archive_windows": 100000, "env_steps": 26160, "total_transitions": 107151360, "num_steps_per_env": 1, "wm_loss": 0.4499039053916931, "actor_loss": -8.802727699279785, "critic_loss": 0.02341439761221409, "reward": 0.07022304087877274, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23871581256389618, 0.15665702521800995, 0.250757098197937], "policy_updates": 26060, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2305.179641569, "contact_bce": 0.3259534239768982, "contact_force_loss": 0.03317742049694061, "terrain_level_mean": 2.975830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26170, "actor_lr": 4.110531281708008e-06, "archive_windows": 100000, "env_steps": 26170, "total_transitions": 107192320, "num_steps_per_env": 1, "wm_loss": 0.4820873737335205, "actor_loss": -8.817621231079102, "critic_loss": 0.019084101542830467, "reward": 0.07033182680606842, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23766770958900452, 0.1571946144104004, 0.25244417786598206], "policy_updates": 26070, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2308.702184051, "contact_bce": 0.33009836077690125, "contact_force_loss": 0.0327838696539402, "terrain_level_mean": 2.976806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26180, "actor_lr": 4.098645902333786e-06, "archive_windows": 100000, "env_steps": 26180, "total_transitions": 107233280, "num_steps_per_env": 1, "wm_loss": 0.47676822543144226, "actor_loss": -8.829418182373047, "critic_loss": 0.0201337318867445, "reward": 0.07039803266525269, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23799985647201538, 0.15798254311084747, 0.253690630197525], "policy_updates": 26080, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2312.242367976, "contact_bce": 0.32182079553604126, "contact_force_loss": 0.032634709030389786, "terrain_level_mean": 2.9775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26190, "actor_lr": 4.086789913930486e-06, "archive_windows": 100000, "env_steps": 26190, "total_transitions": 107274240, "num_steps_per_env": 1, "wm_loss": 0.5368257761001587, "actor_loss": -8.842819213867188, "critic_loss": 0.02011064626276493, "reward": 0.06996767967939377, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24336475133895874, 0.1576443314552307, 0.2548263370990753], "policy_updates": 26090, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2315.789850869, "contact_bce": 0.3334716558456421, "contact_force_loss": 0.03385946899652481, "terrain_level_mean": 2.978759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26200, "actor_lr": 4.074963329499643e-06, "archive_windows": 100000, "env_steps": 26200, "total_transitions": 107315200, "num_steps_per_env": 1, "wm_loss": 0.5132186412811279, "actor_loss": -8.808730125427246, "critic_loss": 0.027791887521743774, "reward": 0.069975845515728, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24366798996925354, 0.15560801327228546, 0.25932028889656067], "policy_updates": 26100, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2319.349489429, "contact_bce": 0.3306528329849243, "contact_force_loss": 0.03316289559006691, "terrain_level_mean": 2.978759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26210, "actor_lr": 4.063166162010543e-06, "archive_windows": 100000, "env_steps": 26210, "total_transitions": 107356160, "num_steps_per_env": 1, "wm_loss": 0.5029887557029724, "actor_loss": -8.810309410095215, "critic_loss": 0.02672482840716839, "reward": 0.07024013251066208, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24498628079891205, 0.15427079796791077, 0.25403285026550293], "policy_updates": 26110, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2323.2960069680003, "contact_bce": 0.3264771103858948, "contact_force_loss": 0.03354349359869957, "terrain_level_mean": 2.97802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26220, "actor_lr": 4.051398424400241e-06, "archive_windows": 100000, "env_steps": 26220, "total_transitions": 107397120, "num_steps_per_env": 1, "wm_loss": 0.4934128224849701, "actor_loss": -8.801624298095703, "critic_loss": 0.04445083066821098, "reward": 0.06993518024682999, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2449643462896347, 0.15767252445220947, 0.25500258803367615], "policy_updates": 26120, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2327.228406223, "contact_bce": 0.3305555582046509, "contact_force_loss": 0.03296087682247162, "terrain_level_mean": 2.979736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26230, "actor_lr": 4.039660129573504e-06, "archive_windows": 100000, "env_steps": 26230, "total_transitions": 107438080, "num_steps_per_env": 1, "wm_loss": 0.4967707395553589, "actor_loss": -8.750066757202148, "critic_loss": 0.02971729077398777, "reward": 0.07024278491735458, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24237443506717682, 0.15619489550590515, 0.2546995282173157], "policy_updates": 26130, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2331.159127794, "contact_bce": 0.3283277451992035, "contact_force_loss": 0.033347662538290024, "terrain_level_mean": 2.97900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.998727798461914]} {"step": 26240, "actor_lr": 4.027951290402802e-06, "archive_windows": 100000, "env_steps": 26240, "total_transitions": 107479040, "num_steps_per_env": 1, "wm_loss": 0.4680916965007782, "actor_loss": -8.817988395690918, "critic_loss": 0.03432435169816017, "reward": 0.07046457380056381, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23991307616233826, 0.15736395120620728, 0.25423192977905273], "policy_updates": 26140, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2335.0856929290003, "contact_bce": 0.3273039758205414, "contact_force_loss": 0.03236593306064606, "terrain_level_mean": 2.97998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26250, "actor_lr": 4.016271919728332e-06, "archive_windows": 100000, "env_steps": 26250, "total_transitions": 107520000, "num_steps_per_env": 1, "wm_loss": 0.464246541261673, "actor_loss": -8.839458465576172, "critic_loss": 0.02173074521124363, "reward": 0.07055660337209702, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24046100676059723, 0.15398482978343964, 0.25586459040641785], "policy_updates": 26150, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2339.078632515, "contact_bce": 0.3227905035018921, "contact_force_loss": 0.032338473945856094, "terrain_level_mean": 2.98095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26260, "actor_lr": 4.004622030357936e-06, "archive_windows": 100000, "env_steps": 26260, "total_transitions": 107560960, "num_steps_per_env": 1, "wm_loss": 0.4613572359085083, "actor_loss": -8.832623481750488, "critic_loss": 0.01902119256556034, "reward": 0.07026152312755585, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2418161779642105, 0.15337836742401123, 0.25552257895469666], "policy_updates": 26160, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2343.726136315, "contact_bce": 0.3257821202278137, "contact_force_loss": 0.03255057707428932, "terrain_level_mean": 2.9814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26270, "actor_lr": 3.99300163506715e-06, "archive_windows": 100000, "env_steps": 26270, "total_transitions": 107601920, "num_steps_per_env": 1, "wm_loss": 0.5078945159912109, "actor_loss": -8.77981185913086, "critic_loss": 0.02951759099960327, "reward": 0.07031374424695969, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24265453219413757, 0.15643052756786346, 0.2583042085170746], "policy_updates": 26170, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2348.447581327, "contact_bce": 0.3266317844390869, "contact_force_loss": 0.03346436470746994, "terrain_level_mean": 2.982177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26280, "actor_lr": 3.9814107465991694e-06, "archive_windows": 100000, "env_steps": 26280, "total_transitions": 107642880, "num_steps_per_env": 1, "wm_loss": 0.5097184181213379, "actor_loss": -8.801679611206055, "critic_loss": 0.022039899602532387, "reward": 0.07029430568218231, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2425258755683899, 0.15732939541339874, 0.26069310307502747], "policy_updates": 26180, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2353.1205411260003, "contact_bce": 0.32215356826782227, "contact_force_loss": 0.03292923793196678, "terrain_level_mean": 2.981201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26290, "actor_lr": 3.969849377664818e-06, "archive_windows": 100000, "env_steps": 26290, "total_transitions": 107683840, "num_steps_per_env": 1, "wm_loss": 0.4817202389240265, "actor_loss": -8.844223022460938, "critic_loss": 0.01595044508576393, "reward": 0.0700594037771225, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24337978661060333, 0.1581549048423767, 0.25626155734062195], "policy_updates": 26190, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2357.532402038, "contact_bce": 0.3259001672267914, "contact_force_loss": 0.03317652642726898, "terrain_level_mean": 2.982177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26300, "actor_lr": 3.958317540942559e-06, "archive_windows": 100000, "env_steps": 26300, "total_transitions": 107724800, "num_steps_per_env": 1, "wm_loss": 0.4909118115901947, "actor_loss": -8.820639610290527, "critic_loss": 0.029813099652528763, "reward": 0.07051552087068558, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24676454067230225, 0.15641756355762482, 0.2516182065010071], "policy_updates": 26200, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2361.943080071, "contact_bce": 0.3232559859752655, "contact_force_loss": 0.03294911980628967, "terrain_level_mean": 2.982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26310, "actor_lr": 3.946815249078467e-06, "archive_windows": 100000, "env_steps": 26310, "total_transitions": 107765760, "num_steps_per_env": 1, "wm_loss": 0.4726558029651642, "actor_loss": -8.819561004638672, "critic_loss": 0.023464439436793327, "reward": 0.07043414562940598, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24766747653484344, 0.15317361056804657, 0.25331005454063416], "policy_updates": 26210, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2366.392685111, "contact_bce": 0.3210517466068268, "contact_force_loss": 0.032381247729063034, "terrain_level_mean": 2.982177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9993772506713867, 0.9994272589683533, 2.9979209899902344]} {"step": 26320, "actor_lr": 3.935342514686209e-06, "archive_windows": 100000, "env_steps": 26320, "total_transitions": 107806720, "num_steps_per_env": 1, "wm_loss": 0.5116316080093384, "actor_loss": -8.850179672241211, "critic_loss": 0.018765410408377647, "reward": 0.07065162807703018, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24315446615219116, 0.15775884687900543, 0.2555636167526245], "policy_updates": 26220, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2370.876502522, "contact_bce": 0.33026689291000366, "contact_force_loss": 0.03396112471818924, "terrain_level_mean": 2.982177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9992586374282837, 0.9994272589683533, 2.9979209899902344]} {"step": 26330, "actor_lr": 3.923899350347043e-06, "archive_windows": 100000, "env_steps": 26330, "total_transitions": 107847680, "num_steps_per_env": 1, "wm_loss": 0.4979179799556732, "actor_loss": -8.858851432800293, "critic_loss": 0.02164909429848194, "reward": 0.07085076719522476, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2441500723361969, 0.15742120146751404, 0.25794199109077454], "policy_updates": 26230, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2375.307050214, "contact_bce": 0.3258512616157532, "contact_force_loss": 0.032343972474336624, "terrain_level_mean": 2.982177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9992586374282837, 0.9994272589683533, 2.9979209899902344]} {"step": 26340, "actor_lr": 3.912485768609811e-06, "archive_windows": 100000, "env_steps": 26340, "total_transitions": 107888640, "num_steps_per_env": 1, "wm_loss": 0.5095734000205994, "actor_loss": -8.737960815429688, "critic_loss": 0.031649988144636154, "reward": 0.07123836129903793, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2435006946325302, 0.15813247859477997, 0.256401926279068], "policy_updates": 26240, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2379.717469261, "contact_bce": 0.328777015209198, "contact_force_loss": 0.034246694296598434, "terrain_level_mean": 2.98193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9992586374282837, 0.9994272589683533, 2.9979209899902344]} {"step": 26350, "actor_lr": 3.901101781990901e-06, "archive_windows": 100000, "env_steps": 26350, "total_transitions": 107929600, "num_steps_per_env": 1, "wm_loss": 0.5006032586097717, "actor_loss": -8.847637176513672, "critic_loss": 0.02039455994963646, "reward": 0.07141657918691635, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24261640012264252, 0.15989060699939728, 0.2572568655014038], "policy_updates": 26250, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2384.2170435040002, "contact_bce": 0.32754752039909363, "contact_force_loss": 0.03388995677232742, "terrain_level_mean": 2.9814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9992586374282837, 0.9994272589683533, 2.9979209899902344]} {"step": 26360, "actor_lr": 3.889747402974247e-06, "archive_windows": 100000, "env_steps": 26360, "total_transitions": 107970560, "num_steps_per_env": 1, "wm_loss": 0.49883580207824707, "actor_loss": -8.81924057006836, "critic_loss": 0.021759048104286194, "reward": 0.07145144790410995, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24267999827861786, 0.1620929092168808, 0.25132906436920166], "policy_updates": 26260, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2388.643531272, "contact_bce": 0.3279593288898468, "contact_force_loss": 0.03469938784837723, "terrain_level_mean": 2.981689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9992586374282837, 0.9994272589683533, 2.9979209899902344]} {"step": 26370, "actor_lr": 3.878422644011321e-06, "archive_windows": 100000, "env_steps": 26370, "total_transitions": 108011520, "num_steps_per_env": 1, "wm_loss": 0.5397169589996338, "actor_loss": -8.77795696258545, "critic_loss": 0.025685254484415054, "reward": 0.07106845080852509, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2403024286031723, 0.16029949486255646, 0.2534889876842499], "policy_updates": 26270, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2393.049766176, "contact_bce": 0.32314828038215637, "contact_force_loss": 0.03307025134563446, "terrain_level_mean": 2.982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9992586374282837, 0.9994272589683533, 2.9979209899902344]} {"step": 26380, "actor_lr": 3.867127517521112e-06, "archive_windows": 100000, "env_steps": 26380, "total_transitions": 108052480, "num_steps_per_env": 1, "wm_loss": 0.5031255483627319, "actor_loss": -8.780384063720703, "critic_loss": 0.03315560147166252, "reward": 0.07061676681041718, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24359245598316193, 0.1601024866104126, 0.2606889009475708], "policy_updates": 26280, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2397.445826059, "contact_bce": 0.3300251364707947, "contact_force_loss": 0.03388278931379318, "terrain_level_mean": 2.983642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9992586374282837, 0.9990448355674744, 2.998950719833374]} {"step": 26390, "actor_lr": 3.855862035890101e-06, "archive_windows": 100000, "env_steps": 26390, "total_transitions": 108093440, "num_steps_per_env": 1, "wm_loss": 0.4833383858203888, "actor_loss": -8.82724380493164, "critic_loss": 0.0175845455378294, "reward": 0.07025349140167236, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2493007928133011, 0.16110852360725403, 0.25749632716178894], "policy_updates": 26290, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2401.850155042, "contact_bce": 0.32576432824134827, "contact_force_loss": 0.03294187784194946, "terrain_level_mean": 2.984130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9996522665023804, 0.9990448355674744, 2.998950719833374]} {"step": 26400, "actor_lr": 3.844626211472281e-06, "archive_windows": 100000, "env_steps": 26400, "total_transitions": 108134400, "num_steps_per_env": 1, "wm_loss": 0.5239855051040649, "actor_loss": -8.843430519104004, "critic_loss": 0.025812452659010887, "reward": 0.07022277265787125, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24637863039970398, 0.16181236505508423, 0.25714853405952454], "policy_updates": 26300, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2406.28441594, "contact_bce": 0.32836225628852844, "contact_force_loss": 0.03331787884235382, "terrain_level_mean": 2.9853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9996522665023804, 0.9990448355674744, 2.998950719833374]} {"step": 26410, "actor_lr": 3.833420056589108e-06, "archive_windows": 100000, "env_steps": 26410, "total_transitions": 108175360, "num_steps_per_env": 1, "wm_loss": 0.5201407670974731, "actor_loss": -8.776267051696777, "critic_loss": 0.018923109397292137, "reward": 0.07033783197402954, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24573521316051483, 0.15958218276500702, 0.2593323588371277], "policy_updates": 26310, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2410.735166103, "contact_bce": 0.325480192899704, "contact_force_loss": 0.033077698200941086, "terrain_level_mean": 2.9853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9996522665023804, 0.9991099834442139, 2.998950719833374]} {"step": 26420, "actor_lr": 3.8222435835295055e-06, "archive_windows": 100000, "env_steps": 26420, "total_transitions": 108216320, "num_steps_per_env": 1, "wm_loss": 0.47993120551109314, "actor_loss": -8.829305648803711, "critic_loss": 0.018396595492959023, "reward": 0.07064183801412582, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24188660085201263, 0.15827183425426483, 0.25474420189857483], "policy_updates": 26320, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2415.122289077, "contact_bce": 0.32558852434158325, "contact_force_loss": 0.033710964024066925, "terrain_level_mean": 2.986083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9996522665023804, 0.9991099834442139, 2.998950719833374]} {"step": 26430, "actor_lr": 3.8110968045498447e-06, "archive_windows": 100000, "env_steps": 26430, "total_transitions": 108257280, "num_steps_per_env": 1, "wm_loss": 0.492450475692749, "actor_loss": -8.820805549621582, "critic_loss": 0.021944722160696983, "reward": 0.07101748138666153, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23952268064022064, 0.15791283547878265, 0.2552444040775299], "policy_updates": 26330, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2419.5375980480003, "contact_bce": 0.3239216208457947, "contact_force_loss": 0.032779742032289505, "terrain_level_mean": 2.98583984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9996522665023804, 0.9991099834442139, 2.998950719833374]} {"step": 26440, "actor_lr": 3.799979731873932e-06, "archive_windows": 100000, "env_steps": 26440, "total_transitions": 108298240, "num_steps_per_env": 1, "wm_loss": 0.49806278944015503, "actor_loss": -8.770633697509766, "critic_loss": 0.03237086161971092, "reward": 0.07098621875047684, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23890990018844604, 0.15745951235294342, 0.2557258903980255], "policy_updates": 26340, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2423.966392076, "contact_bce": 0.32734331488609314, "contact_force_loss": 0.03321453556418419, "terrain_level_mean": 2.98486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9996522665023804, 0.9991099834442139, 2.998950719833374]} {"step": 26450, "actor_lr": 3.7888923776930013e-06, "archive_windows": 100000, "env_steps": 26450, "total_transitions": 108339200, "num_steps_per_env": 1, "wm_loss": 0.4945087730884552, "actor_loss": -8.835086822509766, "critic_loss": 0.018255358561873436, "reward": 0.07146652787923813, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23697429895401, 0.15639466047286987, 0.2518826425075531], "policy_updates": 26350, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2428.397516542, "contact_bce": 0.3275810480117798, "contact_force_loss": 0.03280237317085266, "terrain_level_mean": 2.986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9996522665023804, 0.9991099834442139, 2.998950719833374]} {"step": 26460, "actor_lr": 3.7778347541657035e-06, "archive_windows": 100000, "env_steps": 26460, "total_transitions": 108380160, "num_steps_per_env": 1, "wm_loss": 0.5129393935203552, "actor_loss": -8.801312446594238, "critic_loss": 0.029665449634194374, "reward": 0.07114546746015549, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2358836829662323, 0.15556150674819946, 0.2593814730644226], "policy_updates": 26360, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2432.82798328, "contact_bce": 0.3287145495414734, "contact_force_loss": 0.03345014154911041, "terrain_level_mean": 2.986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26470, "actor_lr": 3.76680687341808e-06, "archive_windows": 100000, "env_steps": 26470, "total_transitions": 108421120, "num_steps_per_env": 1, "wm_loss": 0.47799256443977356, "actor_loss": -8.8126802444458, "critic_loss": 0.02696438506245613, "reward": 0.07130371779203415, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23826788365840912, 0.15458156168460846, 0.2594202160835266], "policy_updates": 26370, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2437.22843442, "contact_bce": 0.3302455246448517, "contact_force_loss": 0.0332186259329319, "terrain_level_mean": 2.986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26480, "actor_lr": 3.755808747543539e-06, "archive_windows": 100000, "env_steps": 26480, "total_transitions": 108462080, "num_steps_per_env": 1, "wm_loss": 0.5163218379020691, "actor_loss": -8.820646286010742, "critic_loss": 0.024810541421175003, "reward": 0.0713099017739296, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2349180430173874, 0.15264183282852173, 0.25413820147514343], "policy_updates": 26380, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2441.666301181, "contact_bce": 0.3184491991996765, "contact_force_loss": 0.03257020190358162, "terrain_level_mean": 2.986572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26490, "actor_lr": 3.7448403886028885e-06, "archive_windows": 100000, "env_steps": 26490, "total_transitions": 108503040, "num_steps_per_env": 1, "wm_loss": 0.5194510817527771, "actor_loss": -8.821573257446289, "critic_loss": 0.023268237709999084, "reward": 0.07120135426521301, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23403547704219818, 0.15447525680065155, 0.2559705078601837], "policy_updates": 26390, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2446.103449972, "contact_bce": 0.32543110847473145, "contact_force_loss": 0.03260083124041557, "terrain_level_mean": 2.986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26500, "actor_lr": 3.733901808624269e-06, "archive_windows": 100000, "env_steps": 26500, "total_transitions": 108544000, "num_steps_per_env": 1, "wm_loss": 0.4772064983844757, "actor_loss": -8.799666404724121, "critic_loss": 0.025708694010972977, "reward": 0.07066036015748978, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23618143796920776, 0.15620754659175873, 0.2590179443359375], "policy_updates": 26400, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2450.496007648, "contact_bce": 0.31726616621017456, "contact_force_loss": 0.03284209966659546, "terrain_level_mean": 2.98681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26510, "actor_lr": 3.722993019603181e-06, "archive_windows": 100000, "env_steps": 26510, "total_transitions": 108584960, "num_steps_per_env": 1, "wm_loss": 0.46485787630081177, "actor_loss": -8.820762634277344, "critic_loss": 0.021068090572953224, "reward": 0.07073569297790527, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2391469031572342, 0.15692225098609924, 0.261270672082901], "policy_updates": 26410, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2454.908350359, "contact_bce": 0.3204960823059082, "contact_force_loss": 0.03239334002137184, "terrain_level_mean": 2.987548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26520, "actor_lr": 3.7121140335024536e-06, "archive_windows": 100000, "env_steps": 26520, "total_transitions": 108625920, "num_steps_per_env": 1, "wm_loss": 0.49803775548934937, "actor_loss": -8.802967071533203, "critic_loss": 0.02905919961631298, "reward": 0.07103171199560165, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24073316156864166, 0.15682083368301392, 0.25811493396759033], "policy_updates": 26420, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2459.5838039200003, "contact_bce": 0.3276905417442322, "contact_force_loss": 0.03276335448026657, "terrain_level_mean": 2.98779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26530, "actor_lr": 3.7012648622522158e-06, "archive_windows": 100000, "env_steps": 26530, "total_transitions": 108666880, "num_steps_per_env": 1, "wm_loss": 0.5218554139137268, "actor_loss": -8.810893058776855, "critic_loss": 0.0269742701202631, "reward": 0.0707651674747467, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24295777082443237, 0.15878096222877502, 0.26089489459991455], "policy_updates": 26430, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2463.918366272, "contact_bce": 0.3262353539466858, "contact_force_loss": 0.03307006135582924, "terrain_level_mean": 2.987548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26540, "actor_lr": 3.690445517749921e-06, "archive_windows": 100000, "env_steps": 26540, "total_transitions": 108707840, "num_steps_per_env": 1, "wm_loss": 0.5241988301277161, "actor_loss": -8.81039810180664, "critic_loss": 0.02339104376733303, "reward": 0.07058456540107727, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2416679859161377, 0.1601938009262085, 0.2538185119628906], "policy_updates": 26440, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2468.298570321, "contact_bce": 0.33288174867630005, "contact_force_loss": 0.033732738345861435, "terrain_level_mean": 2.98681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.998950719833374]} {"step": 26550, "actor_lr": 3.6796560118603067e-06, "archive_windows": 100000, "env_steps": 26550, "total_transitions": 108748800, "num_steps_per_env": 1, "wm_loss": 0.5049412846565247, "actor_loss": -8.829627990722656, "critic_loss": 0.017972225323319435, "reward": 0.06998373568058014, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2394515573978424, 0.16083969175815582, 0.2569764256477356], "policy_updates": 26450, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2472.803389958, "contact_bce": 0.32339537143707275, "contact_force_loss": 0.03252681344747543, "terrain_level_mean": 2.986572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.997661590576172]} {"step": 26560, "actor_lr": 3.6688963564153943e-06, "archive_windows": 100000, "env_steps": 26560, "total_transitions": 108789760, "num_steps_per_env": 1, "wm_loss": 0.49020662903785706, "actor_loss": -8.801389694213867, "critic_loss": 0.027669956907629967, "reward": 0.07081222534179688, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23574578762054443, 0.1593286693096161, 0.25096386671066284], "policy_updates": 26460, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2477.289499984, "contact_bce": 0.32379502058029175, "contact_force_loss": 0.03267008811235428, "terrain_level_mean": 2.985595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.997661590576172]} {"step": 26570, "actor_lr": 3.6581665632144572e-06, "archive_windows": 100000, "env_steps": 26570, "total_transitions": 108830720, "num_steps_per_env": 1, "wm_loss": 0.48310092091560364, "actor_loss": -8.876396179199219, "critic_loss": 0.02087540738284588, "reward": 0.0710098147392273, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23648427426815033, 0.1554136425256729, 0.24909783899784088], "policy_updates": 26470, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2481.787200544, "contact_bce": 0.32259440422058105, "contact_force_loss": 0.03252153471112251, "terrain_level_mean": 2.9853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9998395442962646, 0.9991099834442139, 2.997661590576172]} {"step": 26580, "actor_lr": 3.647466644024035e-06, "archive_windows": 100000, "env_steps": 26580, "total_transitions": 108871680, "num_steps_per_env": 1, "wm_loss": 0.4936074912548065, "actor_loss": -8.820293426513672, "critic_loss": 0.029375648126006126, "reward": 0.0706707015633583, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23896722495555878, 0.15611235797405243, 0.2506008446216583], "policy_updates": 26480, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2486.2753545620003, "contact_bce": 0.3280802369117737, "contact_force_loss": 0.03238571807742119, "terrain_level_mean": 2.985107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9998395442962646, 0.9986047148704529, 2.997661590576172]} {"step": 26590, "actor_lr": 3.6367966105778974e-06, "archive_windows": 100000, "env_steps": 26590, "total_transitions": 108912640, "num_steps_per_env": 1, "wm_loss": 0.5337674021720886, "actor_loss": -8.83456039428711, "critic_loss": 0.017301538959145546, "reward": 0.07142673432826996, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23593688011169434, 0.15758202970027924, 0.25111913681030273], "policy_updates": 26490, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2490.716417364, "contact_bce": 0.3286105990409851, "contact_force_loss": 0.03419873118400574, "terrain_level_mean": 2.984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9998395442962646, 0.9986047148704529, 2.997661590576172]} {"step": 26600, "actor_lr": 3.62615647457704e-06, "archive_windows": 100000, "env_steps": 26600, "total_transitions": 108953600, "num_steps_per_env": 1, "wm_loss": 0.47968748211860657, "actor_loss": -8.80706787109375, "critic_loss": 0.023011431097984314, "reward": 0.07097112387418747, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2375425100326538, 0.15750586986541748, 0.2523617446422577], "policy_updates": 26500, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2495.144488948, "contact_bce": 0.32872888445854187, "contact_force_loss": 0.03224220126867294, "terrain_level_mean": 2.98486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9998395442962646, 0.9986047148704529, 2.997661590576172]} {"step": 26610, "actor_lr": 3.615546247689686e-06, "archive_windows": 100000, "env_steps": 26610, "total_transitions": 108994560, "num_steps_per_env": 1, "wm_loss": 0.502324104309082, "actor_loss": -8.779411315917969, "critic_loss": 0.023828981444239616, "reward": 0.07065572589635849, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2422022968530655, 0.16031110286712646, 0.2561505436897278], "policy_updates": 26510, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2499.637230233, "contact_bce": 0.32840588688850403, "contact_force_loss": 0.033994294703006744, "terrain_level_mean": 2.986572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9998395442962646, 0.9987214207649231, 2.997661590576172]} {"step": 26620, "actor_lr": 3.6049659415512497e-06, "archive_windows": 100000, "env_steps": 26620, "total_transitions": 109035520, "num_steps_per_env": 1, "wm_loss": 0.46667930483818054, "actor_loss": -8.892678260803223, "critic_loss": 0.016736967489123344, "reward": 0.07096429914236069, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23909525573253632, 0.1591283231973648, 0.2557554244995117], "policy_updates": 26520, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2504.122821969, "contact_bce": 0.32144060730934143, "contact_force_loss": 0.032577574253082275, "terrain_level_mean": 2.985595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9990861415863037, 0.9987214207649231, 2.997661590576172]} {"step": 26630, "actor_lr": 3.5944155677643266e-06, "archive_windows": 100000, "env_steps": 26630, "total_transitions": 109076480, "num_steps_per_env": 1, "wm_loss": 0.5157005190849304, "actor_loss": -8.824356079101562, "critic_loss": 0.024497054517269135, "reward": 0.07074461877346039, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23948173224925995, 0.1596091240644455, 0.2579294741153717], "policy_updates": 26530, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2508.597795961, "contact_bce": 0.33152952790260315, "contact_force_loss": 0.03407011181116104, "terrain_level_mean": 2.98681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9990861415863037, 0.9994036555290222, 2.997661590576172]} {"step": 26640, "actor_lr": 3.5838951378986996e-06, "archive_windows": 100000, "env_steps": 26640, "total_transitions": 109117440, "num_steps_per_env": 1, "wm_loss": 0.45041659474372864, "actor_loss": -8.775689125061035, "critic_loss": 0.03194905444979668, "reward": 0.07112100720405579, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2408444881439209, 0.16006219387054443, 0.2549349367618561], "policy_updates": 26540, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2513.066903383, "contact_bce": 0.32129475474357605, "contact_force_loss": 0.032090745866298676, "terrain_level_mean": 2.987548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9990861415863037, 0.9994036555290222, 2.997661590576172]} {"step": 26650, "actor_lr": 3.5734046634913096e-06, "archive_windows": 100000, "env_steps": 26650, "total_transitions": 109158400, "num_steps_per_env": 1, "wm_loss": 0.5078370571136475, "actor_loss": -8.824687004089355, "critic_loss": 0.02269391342997551, "reward": 0.07132021337747574, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23839381337165833, 0.1592244952917099, 0.24838481843471527], "policy_updates": 26550, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2516.701029245, "contact_bce": 0.3235839605331421, "contact_force_loss": 0.03299447149038315, "terrain_level_mean": 2.989013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9988880157470703, 0.9994036555290222, 2.997661590576172]} {"step": 26660, "actor_lr": 3.562944156046243e-06, "archive_windows": 100000, "env_steps": 26660, "total_transitions": 109199360, "num_steps_per_env": 1, "wm_loss": 0.49392154812812805, "actor_loss": -8.845193862915039, "critic_loss": 0.018618248403072357, "reward": 0.0709507018327713, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23712176084518433, 0.1580658257007599, 0.25209417939186096], "policy_updates": 26560, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2520.211532107, "contact_bce": 0.32405197620391846, "contact_force_loss": 0.03253732994198799, "terrain_level_mean": 2.98828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9988880157470703, 0.9994036555290222, 2.997661590576172]} {"step": 26670, "actor_lr": 3.5525136270347392e-06, "archive_windows": 100000, "env_steps": 26670, "total_transitions": 109240320, "num_steps_per_env": 1, "wm_loss": 0.5401386022567749, "actor_loss": -8.826055526733398, "critic_loss": 0.02350842021405697, "reward": 0.07071985304355621, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23927849531173706, 0.1588205248117447, 0.259374737739563], "policy_updates": 26570, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2523.7471115870003, "contact_bce": 0.32429373264312744, "contact_force_loss": 0.032921627163887024, "terrain_level_mean": 2.987548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9988880157470703, 0.9994036555290222, 2.997661590576172]} {"step": 26680, "actor_lr": 3.5421130878951453e-06, "archive_windows": 100000, "env_steps": 26680, "total_transitions": 109281280, "num_steps_per_env": 1, "wm_loss": 0.4818858802318573, "actor_loss": -8.823253631591797, "critic_loss": 0.019180571660399437, "reward": 0.07059723138809204, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23843809962272644, 0.1604326218366623, 0.2564541697502136], "policy_updates": 26580, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2527.27648086, "contact_bce": 0.3246411383152008, "contact_force_loss": 0.03297239542007446, "terrain_level_mean": 2.985595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9982922077178955, 0.9994036555290222, 2.997661590576172]} {"step": 26690, "actor_lr": 3.5317425500329305e-06, "archive_windows": 100000, "env_steps": 26690, "total_transitions": 109322240, "num_steps_per_env": 1, "wm_loss": 0.49847161769866943, "actor_loss": -8.827568054199219, "critic_loss": 0.02575240470468998, "reward": 0.07047441601753235, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24190853536128998, 0.16094793379306793, 0.2555297613143921], "policy_updates": 26590, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2530.793371545, "contact_bce": 0.32413995265960693, "contact_force_loss": 0.0321449376642704, "terrain_level_mean": 2.986083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9982922077178955, 0.9994036555290222, 2.997661590576172]} {"step": 26700, "actor_lr": 3.521402024820659e-06, "archive_windows": 100000, "env_steps": 26700, "total_transitions": 109363200, "num_steps_per_env": 1, "wm_loss": 0.46943750977516174, "actor_loss": -8.83969497680664, "critic_loss": 0.020752040669322014, "reward": 0.07061982899904251, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24404974281787872, 0.15896019339561462, 0.2584274411201477], "policy_updates": 26600, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2534.320439502, "contact_bce": 0.3267994523048401, "contact_force_loss": 0.03215137869119644, "terrain_level_mean": 2.988037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9982922077178955, 0.9994036555290222, 2.997661590576172]} {"step": 26710, "actor_lr": 3.5110915235979837e-06, "archive_windows": 100000, "env_steps": 26710, "total_transitions": 109404160, "num_steps_per_env": 1, "wm_loss": 0.47033926844596863, "actor_loss": -8.840072631835938, "critic_loss": 0.027900446206331253, "reward": 0.07067614048719406, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24102535843849182, 0.15857751667499542, 0.2526211142539978], "policy_updates": 26610, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2538.719743869, "contact_bce": 0.32075461745262146, "contact_force_loss": 0.032307203859090805, "terrain_level_mean": 2.98828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9982922077178955, 0.9994036555290222, 2.997661590576172]} {"step": 26720, "actor_lr": 3.5008110576716296e-06, "archive_windows": 100000, "env_steps": 26720, "total_transitions": 109445120, "num_steps_per_env": 1, "wm_loss": 0.4871978759765625, "actor_loss": -8.792352676391602, "critic_loss": 0.019918203353881836, "reward": 0.07129773497581482, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23623059689998627, 0.1542217880487442, 0.2547561526298523], "policy_updates": 26620, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2543.7117307040003, "contact_bce": 0.32680392265319824, "contact_force_loss": 0.03250538930296898, "terrain_level_mean": 2.989013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9982922077178955, 0.9994036555290222, 2.997661590576172]} {"step": 26730, "actor_lr": 3.4905606383153993e-06, "archive_windows": 100000, "env_steps": 26730, "total_transitions": 109486080, "num_steps_per_env": 1, "wm_loss": 0.45737600326538086, "actor_loss": -8.826045989990234, "critic_loss": 0.027493927627801895, "reward": 0.07162740081548691, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23755544424057007, 0.1526794284582138, 0.25020653009414673], "policy_updates": 26630, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2548.74969907, "contact_bce": 0.31957510113716125, "contact_force_loss": 0.03184080496430397, "terrain_level_mean": 2.989990234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9982922077178955, 0.9994036555290222, 2.997661590576172]} {"step": 26740, "actor_lr": 3.480340276770132e-06, "archive_windows": 100000, "env_steps": 26740, "total_transitions": 109527040, "num_steps_per_env": 1, "wm_loss": 0.47964516282081604, "actor_loss": -8.772285461425781, "critic_loss": 0.0352853499352932, "reward": 0.07121748477220535, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24093203246593475, 0.15313425660133362, 0.24843592941761017], "policy_updates": 26640, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2553.740865493, "contact_bce": 0.3244923949241638, "contact_force_loss": 0.03289003297686577, "terrain_level_mean": 2.99169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.997661590576172]} {"step": 26750, "actor_lr": 3.4701499842436965e-06, "archive_windows": 100000, "env_steps": 26750, "total_transitions": 109568000, "num_steps_per_env": 1, "wm_loss": 0.49843138456344604, "actor_loss": -8.819842338562012, "critic_loss": 0.024941330775618553, "reward": 0.07112595438957214, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24181130528450012, 0.15509027242660522, 0.2521466016769409], "policy_updates": 26650, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2559.083181495, "contact_bce": 0.3238958418369293, "contact_force_loss": 0.03302890062332153, "terrain_level_mean": 2.9912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26760, "actor_lr": 3.459989771911007e-06, "archive_windows": 100000, "env_steps": 26760, "total_transitions": 109608960, "num_steps_per_env": 1, "wm_loss": 0.5202163457870483, "actor_loss": -8.809730529785156, "critic_loss": 0.018227338790893555, "reward": 0.07110622525215149, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24586743116378784, 0.1552496701478958, 0.2544839084148407], "policy_updates": 26660, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2564.2373263540003, "contact_bce": 0.3274586498737335, "contact_force_loss": 0.033304642885923386, "terrain_level_mean": 2.9912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26770, "actor_lr": 3.4498596509139817e-06, "archive_windows": 100000, "env_steps": 26770, "total_transitions": 109649920, "num_steps_per_env": 1, "wm_loss": 0.4911918342113495, "actor_loss": -8.808774948120117, "critic_loss": 0.021063806489109993, "reward": 0.07114889472723007, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24346870183944702, 0.15702365338802338, 0.25420084595680237], "policy_updates": 26670, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2569.52495702, "contact_bce": 0.32656359672546387, "contact_force_loss": 0.0329512357711792, "terrain_level_mean": 2.9921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26780, "actor_lr": 3.4397596323615397e-06, "archive_windows": 100000, "env_steps": 26780, "total_transitions": 109690880, "num_steps_per_env": 1, "wm_loss": 0.49581268429756165, "actor_loss": -8.82796859741211, "critic_loss": 0.020270971581339836, "reward": 0.07088270038366318, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24189414083957672, 0.15764707326889038, 0.2530464231967926], "policy_updates": 26680, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2574.7192822740003, "contact_bce": 0.32569921016693115, "contact_force_loss": 0.03300898149609566, "terrain_level_mean": 2.994384765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26790, "actor_lr": 3.4296897273295874e-06, "archive_windows": 100000, "env_steps": 26790, "total_transitions": 109731840, "num_steps_per_env": 1, "wm_loss": 0.5054228901863098, "actor_loss": -8.752376556396484, "critic_loss": 0.032139696180820465, "reward": 0.0709797590970993, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24131540954113007, 0.15942789614200592, 0.2513456642627716], "policy_updates": 26690, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2579.9012342720002, "contact_bce": 0.32688653469085693, "contact_force_loss": 0.032969411462545395, "terrain_level_mean": 2.994873046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26800, "actor_lr": 3.4196499468610094e-06, "archive_windows": 100000, "env_steps": 26800, "total_transitions": 109772800, "num_steps_per_env": 1, "wm_loss": 0.5047953724861145, "actor_loss": -8.780630111694336, "critic_loss": 0.024354247376322746, "reward": 0.070764921605587, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2454037219285965, 0.16085396707057953, 0.25541621446609497], "policy_updates": 26700, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2585.137908572, "contact_bce": 0.33049511909484863, "contact_force_loss": 0.03345600143074989, "terrain_level_mean": 2.994384765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26810, "actor_lr": 3.4096403019656615e-06, "archive_windows": 100000, "env_steps": 26810, "total_transitions": 109813760, "num_steps_per_env": 1, "wm_loss": 0.5047183036804199, "actor_loss": -8.788403511047363, "critic_loss": 0.03744327649474144, "reward": 0.07069467008113861, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24441657960414886, 0.1573360711336136, 0.2546772062778473], "policy_updates": 26710, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2590.2295432230003, "contact_bce": 0.3244127333164215, "contact_force_loss": 0.033266447484493256, "terrain_level_mean": 2.995361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26820, "actor_lr": 3.39966080362034e-06, "archive_windows": 100000, "env_steps": 26820, "total_transitions": 109854720, "num_steps_per_env": 1, "wm_loss": 0.5135854482650757, "actor_loss": -8.833426475524902, "critic_loss": 0.029124140739440918, "reward": 0.07068216055631638, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24284644424915314, 0.15694956481456757, 0.2590249478816986], "policy_updates": 26720, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2595.353535028, "contact_bce": 0.3266736567020416, "contact_force_loss": 0.03355535492300987, "terrain_level_mean": 2.99560546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26830, "actor_lr": 3.3897114627687927e-06, "archive_windows": 100000, "env_steps": 26830, "total_transitions": 109895680, "num_steps_per_env": 1, "wm_loss": 0.4822674095630646, "actor_loss": -8.819785118103027, "critic_loss": 0.026799043640494347, "reward": 0.07073687762022018, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2421261966228485, 0.15632259845733643, 0.2545238435268402], "policy_updates": 26730, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2600.4573676180003, "contact_bce": 0.32458630204200745, "contact_force_loss": 0.032683879137039185, "terrain_level_mean": 2.99658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26840, "actor_lr": 3.379792290321693e-06, "archive_windows": 100000, "env_steps": 26840, "total_transitions": 109936640, "num_steps_per_env": 1, "wm_loss": 0.49629122018814087, "actor_loss": -8.807119369506836, "critic_loss": 0.02081095613539219, "reward": 0.07027461379766464, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24070484936237335, 0.1550525277853012, 0.2556018531322479], "policy_updates": 26740, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2605.6547375600003, "contact_bce": 0.3225323259830475, "contact_force_loss": 0.032535407692193985, "terrain_level_mean": 2.998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26850, "actor_lr": 3.3699032971566267e-06, "archive_windows": 100000, "env_steps": 26850, "total_transitions": 109977600, "num_steps_per_env": 1, "wm_loss": 0.46191802620887756, "actor_loss": -8.824009895324707, "critic_loss": 0.021409770473837852, "reward": 0.07050400972366333, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2392207682132721, 0.1564507633447647, 0.25125330686569214], "policy_updates": 26750, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2610.705005351, "contact_bce": 0.32413801550865173, "contact_force_loss": 0.03214976564049721, "terrain_level_mean": 3.0, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26860, "actor_lr": 3.360044494118091e-06, "archive_windows": 100000, "env_steps": 26860, "total_transitions": 110018560, "num_steps_per_env": 1, "wm_loss": 0.46676763892173767, "actor_loss": -8.826147079467773, "critic_loss": 0.02877032570540905, "reward": 0.07096096128225327, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2379666119813919, 0.15614333748817444, 0.25107520818710327], "policy_updates": 26760, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2615.77014219, "contact_bce": 0.33238691091537476, "contact_force_loss": 0.033184297382831573, "terrain_level_mean": 2.9990234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9982922077178955, 0.9997391104698181, 2.9981696605682373]} {"step": 26870, "actor_lr": 3.3502158920174673e-06, "archive_windows": 100000, "env_steps": 26870, "total_transitions": 110059520, "num_steps_per_env": 1, "wm_loss": 0.49928081035614014, "actor_loss": -8.856802940368652, "critic_loss": 0.015413925051689148, "reward": 0.07083972543478012, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2431900054216385, 0.1573406308889389, 0.2541719377040863], "policy_updates": 26770, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2620.899372255, "contact_bce": 0.32082420587539673, "contact_force_loss": 0.033050376921892166, "terrain_level_mean": 3.00048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9971357583999634, 0.9997391104698181, 2.9981696605682373]} {"step": 26880, "actor_lr": 3.3404175016330217e-06, "archive_windows": 100000, "env_steps": 26880, "total_transitions": 110100480, "num_steps_per_env": 1, "wm_loss": 0.482492059469223, "actor_loss": -8.830339431762695, "critic_loss": 0.02366563491523266, "reward": 0.070714071393013, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24452689290046692, 0.15966591238975525, 0.25337308645248413], "policy_updates": 26780, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2625.959575053, "contact_bce": 0.3229326605796814, "contact_force_loss": 0.033126480877399445, "terrain_level_mean": 3.001220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9971357583999634, 0.9997391104698181, 2.9981696605682373]} {"step": 26890, "actor_lr": 3.3306493337098967e-06, "archive_windows": 100000, "env_steps": 26890, "total_transitions": 110141440, "num_steps_per_env": 1, "wm_loss": 0.5026693940162659, "actor_loss": -8.805082321166992, "critic_loss": 0.031879693269729614, "reward": 0.07059647887945175, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24129174649715424, 0.15971560776233673, 0.2569703459739685], "policy_updates": 26790, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2631.130123636, "contact_bce": 0.32309308648109436, "contact_force_loss": 0.03371188044548035, "terrain_level_mean": 3.001708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9971357583999634, 0.9997391104698181, 2.9981696605682373]} {"step": 26900, "actor_lr": 3.3209113989600825e-06, "archive_windows": 100000, "env_steps": 26900, "total_transitions": 110182400, "num_steps_per_env": 1, "wm_loss": 0.5173914432525635, "actor_loss": -8.774007797241211, "critic_loss": 0.026677513495087624, "reward": 0.07085628807544708, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24031852185726166, 0.1596202403306961, 0.2562497854232788], "policy_updates": 26800, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2636.34403641, "contact_bce": 0.3344709575176239, "contact_force_loss": 0.032975900918245316, "terrain_level_mean": 3.001220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9971357583999634, 0.9986047148704529, 2.9981696605682373]} {"step": 26910, "actor_lr": 3.311203708062423e-06, "archive_windows": 100000, "env_steps": 26910, "total_transitions": 110223360, "num_steps_per_env": 1, "wm_loss": 0.46702420711517334, "actor_loss": -8.759648323059082, "critic_loss": 0.02814733050763607, "reward": 0.07117749750614166, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24240122735500336, 0.1590094417333603, 0.2520356774330139], "policy_updates": 26810, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2641.5738295690003, "contact_bce": 0.3210027813911438, "contact_force_loss": 0.031978316605091095, "terrain_level_mean": 3.00146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9971357583999634, 0.9986047148704529, 2.9981696605682373]} {"step": 26920, "actor_lr": 3.301526271662585e-06, "archive_windows": 100000, "env_steps": 26920, "total_transitions": 110264320, "num_steps_per_env": 1, "wm_loss": 0.48893046379089355, "actor_loss": -8.807551383972168, "critic_loss": 0.026026440784335136, "reward": 0.0710517168045044, "falls": 5, "interval_steps": 10, "velocity_mae": [0.243533194065094, 0.15719477832317352, 0.25174185633659363], "policy_updates": 26820, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2646.671264097, "contact_bce": 0.32634177803993225, "contact_force_loss": 0.03382919728755951, "terrain_level_mean": 3.001220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9971357583999634, 0.9992921948432922, 2.9981696605682373]} {"step": 26930, "actor_lr": 3.2918791003730682e-06, "archive_windows": 100000, "env_steps": 26930, "total_transitions": 110305280, "num_steps_per_env": 1, "wm_loss": 0.4856283962726593, "actor_loss": -8.826520919799805, "critic_loss": 0.0263428445905447, "reward": 0.07118991017341614, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24073584377765656, 0.15763285756111145, 0.25300395488739014], "policy_updates": 26830, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2651.79033537, "contact_bce": 0.32437652349472046, "contact_force_loss": 0.03277193754911423, "terrain_level_mean": 3.001708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9971357583999634, 0.9992921948432922, 2.9981696605682373]} {"step": 26940, "actor_lr": 3.282262204773174e-06, "archive_windows": 100000, "env_steps": 26940, "total_transitions": 110346240, "num_steps_per_env": 1, "wm_loss": 0.47828659415245056, "actor_loss": -8.785232543945312, "critic_loss": 0.023800447583198547, "reward": 0.07102879136800766, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24294856190681458, 0.15667690336704254, 0.24905739724636078], "policy_updates": 26840, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2656.89050172, "contact_bce": 0.33113983273506165, "contact_force_loss": 0.03320752829313278, "terrain_level_mean": 3.001708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9971357583999634, 0.9992921948432922, 2.9981696605682373]} {"step": 26950, "actor_lr": 3.272675595409013e-06, "archive_windows": 100000, "env_steps": 26950, "total_transitions": 110387200, "num_steps_per_env": 1, "wm_loss": 0.5062744617462158, "actor_loss": -8.75819206237793, "critic_loss": 0.029255105182528496, "reward": 0.07086896151304245, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2449580729007721, 0.158781036734581, 0.25130829215049744], "policy_updates": 26850, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2661.990747242, "contact_bce": 0.3229748606681824, "contact_force_loss": 0.03288359194993973, "terrain_level_mean": 3.002685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.9981696605682373]} {"step": 26960, "actor_lr": 3.2631192827934823e-06, "archive_windows": 100000, "env_steps": 26960, "total_transitions": 110428160, "num_steps_per_env": 1, "wm_loss": 0.5001584887504578, "actor_loss": -8.821727752685547, "critic_loss": 0.0218766238540411, "reward": 0.07087957859039307, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24121077358722687, 0.15752901136875153, 0.25155875086784363], "policy_updates": 26860, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2667.1096170650003, "contact_bce": 0.32088562846183777, "contact_force_loss": 0.03264506906270981, "terrain_level_mean": 3.00390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.9981696605682373]} {"step": 26970, "actor_lr": 3.2535932774062354e-06, "archive_windows": 100000, "env_steps": 26970, "total_transitions": 110469120, "num_steps_per_env": 1, "wm_loss": 0.48635590076446533, "actor_loss": -8.821330070495605, "critic_loss": 0.020928582176566124, "reward": 0.07118614763021469, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24079523980617523, 0.1567397266626358, 0.24960997700691223], "policy_updates": 26870, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2672.241007322, "contact_bce": 0.3271917700767517, "contact_force_loss": 0.033763520419597626, "terrain_level_mean": 3.004150390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.9981696605682373]} {"step": 26980, "actor_lr": 3.244097589693719e-06, "archive_windows": 100000, "env_steps": 26980, "total_transitions": 110510080, "num_steps_per_env": 1, "wm_loss": 0.4823416769504547, "actor_loss": -8.813390731811523, "critic_loss": 0.03622199967503548, "reward": 0.07088008522987366, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24103312194347382, 0.15796509385108948, 0.2511441707611084], "policy_updates": 26880, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2677.385919067, "contact_bce": 0.3248620927333832, "contact_force_loss": 0.03249597176909447, "terrain_level_mean": 3.005126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.9981696605682373]} {"step": 26990, "actor_lr": 3.234632230069112e-06, "archive_windows": 100000, "env_steps": 26990, "total_transitions": 110551040, "num_steps_per_env": 1, "wm_loss": 0.4746033847332001, "actor_loss": -8.797487258911133, "critic_loss": 0.01866004429757595, "reward": 0.0703815296292305, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24163514375686646, 0.15719355642795563, 0.2511156499385834], "policy_updates": 26890, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2682.501642556, "contact_bce": 0.32395610213279724, "contact_force_loss": 0.03210347518324852, "terrain_level_mean": 3.0048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.9981696605682373]} {"step": 27000, "actor_lr": 3.2251972089123397e-06, "archive_windows": 100000, "env_steps": 27000, "total_transitions": 110592000, "num_steps_per_env": 1, "wm_loss": 0.4692927896976471, "actor_loss": -8.817501068115234, "critic_loss": 0.0254146046936512, "reward": 0.07030834257602692, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24469856917858124, 0.15657682716846466, 0.25001707673072815], "policy_updates": 26900, "skipped_updates": 0, "invalid_env_resets": 12, "elapsed_s": 2687.8514445260003, "contact_bce": 0.322494238615036, "contact_force_loss": 0.031931765377521515, "terrain_level_mean": 3.00537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.9981696605682373]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_027000.mp4 RECOVERY reset 1 invalid environments; first IDs=[2094] {"step": 27010, "actor_lr": 3.215792536570072e-06, "archive_windows": 100000, "env_steps": 27010, "total_transitions": 110632960, "num_steps_per_env": 1, "wm_loss": 0.48255208134651184, "actor_loss": -8.84263801574707, "critic_loss": 0.02237974852323532, "reward": 0.07050123065710068, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25803205370903015, 0.1535499542951584, 0.25566887855529785], "policy_updates": 26910, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2701.039888177, "contact_bce": 0.32055315375328064, "contact_force_loss": 0.03223571553826332, "terrain_level_mean": 3.00732421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.9991605281829834]} {"step": 27020, "actor_lr": 3.2064182233556743e-06, "archive_windows": 100000, "env_steps": 27020, "total_transitions": 110673920, "num_steps_per_env": 1, "wm_loss": 0.5057584643363953, "actor_loss": -8.835041046142578, "critic_loss": 0.01717538945376873, "reward": 0.07145518809556961, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2438257485628128, 0.15334700047969818, 0.25351816415786743], "policy_updates": 26920, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2706.3711782660002, "contact_bce": 0.32173603773117065, "contact_force_loss": 0.03247420862317085, "terrain_level_mean": 3.0087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.999321460723877]} {"step": 27030, "actor_lr": 3.1970742795492283e-06, "archive_windows": 100000, "env_steps": 27030, "total_transitions": 110714880, "num_steps_per_env": 1, "wm_loss": 0.5064798593521118, "actor_loss": -8.846925735473633, "critic_loss": 0.03230943903326988, "reward": 0.07190407812595367, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23603007197380066, 0.15215325355529785, 0.2513081729412079], "policy_updates": 26930, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2711.533270371, "contact_bce": 0.3287675082683563, "contact_force_loss": 0.03339684382081032, "terrain_level_mean": 3.008544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.9989986419677734, 0.9992921948432922, 2.999321460723877]} {"step": 27040, "actor_lr": 3.1877607153975203e-06, "archive_windows": 100000, "env_steps": 27040, "total_transitions": 110755840, "num_steps_per_env": 1, "wm_loss": 0.4613637924194336, "actor_loss": -8.823869705200195, "critic_loss": 0.028098974376916885, "reward": 0.07225854694843292, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2309877872467041, 0.1490103155374527, 0.2479323446750641], "policy_updates": 26940, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2716.761236179, "contact_bce": 0.32277944684028625, "contact_force_loss": 0.03159520402550697, "terrain_level_mean": 3.007568359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27050, "actor_lr": 3.1784775411140164e-06, "archive_windows": 100000, "env_steps": 27050, "total_transitions": 110796800, "num_steps_per_env": 1, "wm_loss": 0.49566134810447693, "actor_loss": -8.789648056030273, "critic_loss": 0.0340469591319561, "reward": 0.07197960466146469, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2360295057296753, 0.14967775344848633, 0.25114840269088745], "policy_updates": 26950, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2721.9114745340003, "contact_bce": 0.3251899778842926, "contact_force_loss": 0.03299325332045555, "terrain_level_mean": 3.008056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27060, "actor_lr": 3.1692247668788517e-06, "archive_windows": 100000, "env_steps": 27060, "total_transitions": 110837760, "num_steps_per_env": 1, "wm_loss": 0.49775704741477966, "actor_loss": -8.840118408203125, "critic_loss": 0.024980194866657257, "reward": 0.07207956165075302, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23469975590705872, 0.15148168802261353, 0.2501450479030609], "policy_updates": 26960, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2727.256420711, "contact_bce": 0.3331392705440521, "contact_force_loss": 0.03320102021098137, "terrain_level_mean": 3.009033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27070, "actor_lr": 3.160002402838828e-06, "archive_windows": 100000, "env_steps": 27070, "total_transitions": 110878720, "num_steps_per_env": 1, "wm_loss": 0.48388171195983887, "actor_loss": -8.8003568649292, "critic_loss": 0.027226800099015236, "reward": 0.07238125056028366, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2303542047739029, 0.15291129052639008, 0.2510391175746918], "policy_updates": 26970, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2732.468077095, "contact_bce": 0.32487210631370544, "contact_force_loss": 0.03311416506767273, "terrain_level_mean": 3.0087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27080, "actor_lr": 3.1508104591074e-06, "archive_windows": 100000, "env_steps": 27080, "total_transitions": 110919680, "num_steps_per_env": 1, "wm_loss": 0.5147637724876404, "actor_loss": -8.811846733093262, "critic_loss": 0.019723592326045036, "reward": 0.07226628065109253, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2324853092432022, 0.1518612951040268, 0.2506536841392517], "policy_updates": 26980, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2737.562079468, "contact_bce": 0.3179514408111572, "contact_force_loss": 0.031889908015728, "terrain_level_mean": 3.009033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27090, "actor_lr": 3.1416489457646566e-06, "archive_windows": 100000, "env_steps": 27090, "total_transitions": 110960640, "num_steps_per_env": 1, "wm_loss": 0.4507005214691162, "actor_loss": -8.79302978515625, "critic_loss": 0.02253269962966442, "reward": 0.07191819697618484, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23492217063903809, 0.15477395057678223, 0.2529999017715454], "policy_updates": 26990, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2742.618371943, "contact_bce": 0.3230297565460205, "contact_force_loss": 0.03186536952853203, "terrain_level_mean": 3.009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27100, "actor_lr": 3.1325178728573266e-06, "archive_windows": 100000, "env_steps": 27100, "total_transitions": 111001600, "num_steps_per_env": 1, "wm_loss": 0.49104827642440796, "actor_loss": -8.794275283813477, "critic_loss": 0.034158799797296524, "reward": 0.07156870514154434, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23580919206142426, 0.15571027994155884, 0.25661584734916687], "policy_updates": 27000, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2748.000687785, "contact_bce": 0.32489457726478577, "contact_force_loss": 0.03281775861978531, "terrain_level_mean": 3.009521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358642578125, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27110, "actor_lr": 3.1234172503987477e-06, "archive_windows": 100000, "env_steps": 27110, "total_transitions": 111042560, "num_steps_per_env": 1, "wm_loss": 0.4794739782810211, "actor_loss": -8.815505981445312, "critic_loss": 0.025590891018509865, "reward": 0.07174120098352432, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23914815485477448, 0.1543322503566742, 0.2550218105316162], "policy_updates": 27010, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2752.985526936, "contact_bce": 0.32452741265296936, "contact_force_loss": 0.032986193895339966, "terrain_level_mean": 3.010986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27120, "actor_lr": 3.114347088368868e-06, "archive_windows": 100000, "env_steps": 27120, "total_transitions": 111083520, "num_steps_per_env": 1, "wm_loss": 0.4969387352466583, "actor_loss": -8.76778793334961, "critic_loss": 0.029289845377206802, "reward": 0.07174628227949142, "falls": 8, "interval_steps": 10, "velocity_mae": [0.242967426776886, 0.1523636430501938, 0.25430595874786377], "policy_updates": 27020, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2757.873279495, "contact_bce": 0.32293644547462463, "contact_force_loss": 0.03331679105758667, "terrain_level_mean": 3.010009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27130, "actor_lr": 3.1053073967142367e-06, "archive_windows": 100000, "env_steps": 27130, "total_transitions": 111124480, "num_steps_per_env": 1, "wm_loss": 0.46274054050445557, "actor_loss": -8.811422348022461, "critic_loss": 0.02579876221716404, "reward": 0.07190166413784027, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24425522983074188, 0.1511593610048294, 0.2548055648803711], "policy_updates": 27030, "skipped_updates": 0, "invalid_env_resets": 13, "elapsed_s": 2762.881815331, "contact_bce": 0.32276347279548645, "contact_force_loss": 0.03239143639802933, "terrain_level_mean": 3.0107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} RECOVERY reset 1 invalid environments; first IDs=[2004] {"step": 27140, "actor_lr": 3.096298185347978e-06, "archive_windows": 100000, "env_steps": 27140, "total_transitions": 111165440, "num_steps_per_env": 1, "wm_loss": 0.5074448585510254, "actor_loss": -8.823790550231934, "critic_loss": 0.020496003329753876, "reward": 0.07192951440811157, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23912285268306732, 0.1491623967885971, 0.2530304789543152], "policy_updates": 27040, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2768.159968835, "contact_bce": 0.3257753551006317, "contact_force_loss": 0.03274375945329666, "terrain_level_mean": 3.010986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27150, "actor_lr": 3.087319464149796e-06, "archive_windows": 100000, "env_steps": 27150, "total_transitions": 111206400, "num_steps_per_env": 1, "wm_loss": 0.46928223967552185, "actor_loss": -8.85059928894043, "critic_loss": 0.0236932635307312, "reward": 0.07182919234037399, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23827287554740906, 0.1522940993309021, 0.25499609112739563], "policy_updates": 27050, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2773.288428572, "contact_bce": 0.3168197274208069, "contact_force_loss": 0.03247727453708649, "terrain_level_mean": 3.011962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27160, "actor_lr": 3.0783712429659637e-06, "archive_windows": 100000, "env_steps": 27160, "total_transitions": 111247360, "num_steps_per_env": 1, "wm_loss": 0.4771498143672943, "actor_loss": -8.773991584777832, "critic_loss": 0.030444830656051636, "reward": 0.0717611089348793, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2391677051782608, 0.1538861244916916, 0.2567940652370453], "policy_updates": 27060, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2778.251420857, "contact_bce": 0.3237670361995697, "contact_force_loss": 0.03213915601372719, "terrain_level_mean": 3.011474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27170, "actor_lr": 3.0694535316093065e-06, "archive_windows": 100000, "env_steps": 27170, "total_transitions": 111288320, "num_steps_per_env": 1, "wm_loss": 0.48210710287094116, "actor_loss": -8.789487838745117, "critic_loss": 0.03209489583969116, "reward": 0.07203127443790436, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2432807832956314, 0.15117627382278442, 0.25341731309890747], "policy_updates": 27070, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2783.149209448, "contact_bce": 0.32468128204345703, "contact_force_loss": 0.032529376447200775, "terrain_level_mean": 3.011474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27180, "actor_lr": 3.0605663398591815e-06, "archive_windows": 100000, "env_steps": 27180, "total_transitions": 111329280, "num_steps_per_env": 1, "wm_loss": 0.47707995772361755, "actor_loss": -8.839110374450684, "critic_loss": 0.02416840009391308, "reward": 0.07152780890464783, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24566851556301117, 0.15230000019073486, 0.2519826292991638], "policy_updates": 27080, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2788.045512058, "contact_bce": 0.32852810621261597, "contact_force_loss": 0.033286839723587036, "terrain_level_mean": 3.010498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27190, "actor_lr": 3.0517096774614854e-06, "archive_windows": 100000, "env_steps": 27190, "total_transitions": 111370240, "num_steps_per_env": 1, "wm_loss": 0.47857362031936646, "actor_loss": -8.818578720092773, "critic_loss": 0.0262938030064106, "reward": 0.07161233574151993, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24700979888439178, 0.1545424610376358, 0.254037469625473], "policy_updates": 27090, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2792.901111276, "contact_bce": 0.3213765025138855, "contact_force_loss": 0.03281909599900246, "terrain_level_mean": 3.009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27200, "actor_lr": 3.0428835541286325e-06, "archive_windows": 100000, "env_steps": 27200, "total_transitions": 111411200, "num_steps_per_env": 1, "wm_loss": 0.5487316250801086, "actor_loss": -8.792377471923828, "critic_loss": 0.023403016850352287, "reward": 0.07157322019338608, "falls": 7, "interval_steps": 10, "velocity_mae": [0.246681347489357, 0.15514932572841644, 0.2563565671443939], "policy_updates": 27100, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2797.733575289, "contact_bce": 0.32262101769447327, "contact_force_loss": 0.032794129103422165, "terrain_level_mean": 3.009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9996534585952759, 0.9992921948432922, 2.999321460723877]} {"step": 27210, "actor_lr": 3.034087979539553e-06, "archive_windows": 100000, "env_steps": 27210, "total_transitions": 111452160, "num_steps_per_env": 1, "wm_loss": 0.4701462984085083, "actor_loss": -8.7984619140625, "critic_loss": 0.029813850298523903, "reward": 0.07186931371688843, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24675105512142181, 0.15463754534721375, 0.2535499930381775], "policy_updates": 27110, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2802.742049683, "contact_bce": 0.32466059923171997, "contact_force_loss": 0.0331331230700016, "terrain_level_mean": 3.009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9996534585952759, 0.9997506141662598, 2.999321460723877]} {"step": 27220, "actor_lr": 3.025322963339675e-06, "archive_windows": 100000, "env_steps": 27220, "total_transitions": 111493120, "num_steps_per_env": 1, "wm_loss": 0.47400763630867004, "actor_loss": -8.823894500732422, "critic_loss": 0.022073108702898026, "reward": 0.07172144949436188, "falls": 2, "interval_steps": 10, "velocity_mae": [0.246349036693573, 0.15657947957515717, 0.25871506333351135], "policy_updates": 27120, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2807.8519630280002, "contact_bce": 0.32509273290634155, "contact_force_loss": 0.0318295955657959, "terrain_level_mean": 3.010986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9996534585952759, 0.9997506141662598, 2.999321460723877]} {"step": 27230, "actor_lr": 3.016588515140911e-06, "archive_windows": 100000, "env_steps": 27230, "total_transitions": 111534080, "num_steps_per_env": 1, "wm_loss": 0.4853525161743164, "actor_loss": -8.822076797485352, "critic_loss": 0.019935719668865204, "reward": 0.07111566513776779, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24904973804950714, 0.1574305295944214, 0.25822797417640686], "policy_updates": 27130, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2812.940229668, "contact_bce": 0.3236698806285858, "contact_force_loss": 0.032313022762537, "terrain_level_mean": 3.0107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.999321460723877]} {"step": 27240, "actor_lr": 3.007884644521647e-06, "archive_windows": 100000, "env_steps": 27240, "total_transitions": 111575040, "num_steps_per_env": 1, "wm_loss": 0.4815405011177063, "actor_loss": -8.780599594116211, "critic_loss": 0.03263942152261734, "reward": 0.07098790258169174, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24746941030025482, 0.15552842617034912, 0.25551849603652954], "policy_updates": 27140, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2817.92109337, "contact_bce": 0.32585498690605164, "contact_force_loss": 0.03281021490693092, "terrain_level_mean": 3.01025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.999321460723877]} {"step": 27250, "actor_lr": 2.9992113610267565e-06, "archive_windows": 100000, "env_steps": 27250, "total_transitions": 111616000, "num_steps_per_env": 1, "wm_loss": 0.5101122856140137, "actor_loss": -8.795236587524414, "critic_loss": 0.02905121259391308, "reward": 0.07126114517450333, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24540485441684723, 0.15519185364246368, 0.25984060764312744], "policy_updates": 27150, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2823.062511743, "contact_bce": 0.3249572515487671, "contact_force_loss": 0.03326166421175003, "terrain_level_mean": 3.011474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.999321460723877]} {"step": 27260, "actor_lr": 2.9905686741675506e-06, "archive_windows": 100000, "env_steps": 27260, "total_transitions": 111656960, "num_steps_per_env": 1, "wm_loss": 0.5046274662017822, "actor_loss": -8.8377685546875, "critic_loss": 0.019821591675281525, "reward": 0.07150080054998398, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24515017867088318, 0.1564916968345642, 0.25829049944877625], "policy_updates": 27160, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2828.297664991, "contact_bce": 0.3274509012699127, "contact_force_loss": 0.03360353782773018, "terrain_level_mean": 3.01220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.999321460723877]} {"step": 27270, "actor_lr": 2.9819565934217936e-06, "archive_windows": 100000, "env_steps": 27270, "total_transitions": 111697920, "num_steps_per_env": 1, "wm_loss": 0.46668770909309387, "actor_loss": -8.809903144836426, "critic_loss": 0.026948267593979836, "reward": 0.07159129530191422, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2427949756383896, 0.15700078010559082, 0.25659850239753723], "policy_updates": 27170, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2833.621744069, "contact_bce": 0.3282276690006256, "contact_force_loss": 0.03274812921881676, "terrain_level_mean": 3.013427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.999321460723877]} {"step": 27280, "actor_lr": 2.9733751282337012e-06, "archive_windows": 100000, "env_steps": 27280, "total_transitions": 111738880, "num_steps_per_env": 1, "wm_loss": 0.4652905762195587, "actor_loss": -8.7869234085083, "critic_loss": 0.02506154216825962, "reward": 0.07154711335897446, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24406930804252625, 0.15647819638252258, 0.25506383180618286], "policy_updates": 27180, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2838.715824576, "contact_bce": 0.3216226100921631, "contact_force_loss": 0.032360780984163284, "terrain_level_mean": 3.014404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.999321460723877]} {"step": 27290, "actor_lr": 2.964824288013887e-06, "archive_windows": 100000, "env_steps": 27290, "total_transitions": 111779840, "num_steps_per_env": 1, "wm_loss": 0.5117917060852051, "actor_loss": -8.7831392288208, "critic_loss": 0.023872673511505127, "reward": 0.07146164029836655, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2476499080657959, 0.1540757417678833, 0.2545414865016937], "policy_updates": 27190, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2843.978263892, "contact_bce": 0.3281109035015106, "contact_force_loss": 0.03361150994896889, "terrain_level_mean": 3.01416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.999321460723877]} {"step": 27300, "actor_lr": 2.9563040821393993e-06, "archive_windows": 100000, "env_steps": 27300, "total_transitions": 111820800, "num_steps_per_env": 1, "wm_loss": 0.50666743516922, "actor_loss": -8.782054901123047, "critic_loss": 0.028575414791703224, "reward": 0.07123210281133652, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24928176403045654, 0.15365082025527954, 0.2555772364139557], "policy_updates": 27200, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2849.07877532, "contact_bce": 0.32671377062797546, "contact_force_loss": 0.0327778086066246, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27310, "actor_lr": 2.9478145199536907e-06, "archive_windows": 100000, "env_steps": 27310, "total_transitions": 111861760, "num_steps_per_env": 1, "wm_loss": 0.4827214777469635, "actor_loss": -8.816093444824219, "critic_loss": 0.024773670360445976, "reward": 0.07136105746030807, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24511249363422394, 0.153073251247406, 0.25078117847442627], "policy_updates": 27210, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2854.113544704, "contact_bce": 0.31498029828071594, "contact_force_loss": 0.032543785870075226, "terrain_level_mean": 3.01220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27320, "actor_lr": 2.9393556107666096e-06, "archive_windows": 100000, "env_steps": 27320, "total_transitions": 111902720, "num_steps_per_env": 1, "wm_loss": 0.48256391286849976, "actor_loss": -8.825511932373047, "critic_loss": 0.021627426147460938, "reward": 0.07146067172288895, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24153149127960205, 0.1543528437614441, 0.2495279610157013], "policy_updates": 27220, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2859.2675224590002, "contact_bce": 0.3254244029521942, "contact_force_loss": 0.03305147960782051, "terrain_level_mean": 3.01220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27330, "actor_lr": 2.930927363854386e-06, "archive_windows": 100000, "env_steps": 27330, "total_transitions": 111943680, "num_steps_per_env": 1, "wm_loss": 0.4833444058895111, "actor_loss": -8.790884017944336, "critic_loss": 0.02585393190383911, "reward": 0.0713064894080162, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23912553489208221, 0.15463270246982574, 0.24785536527633667], "policy_updates": 27230, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2864.535361839, "contact_bce": 0.32279661297798157, "contact_force_loss": 0.03277125954627991, "terrain_level_mean": 3.011474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27340, "actor_lr": 2.9225297884596217e-06, "archive_windows": 100000, "env_steps": 27340, "total_transitions": 111984640, "num_steps_per_env": 1, "wm_loss": 0.47885003685951233, "actor_loss": -8.799734115600586, "critic_loss": 0.024963408708572388, "reward": 0.07168730348348618, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23654812574386597, 0.15258947014808655, 0.24551232159137726], "policy_updates": 27240, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2869.744253616, "contact_bce": 0.3237152695655823, "contact_force_loss": 0.032802678644657135, "terrain_level_mean": 3.011474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27350, "actor_lr": 2.9141628937912914e-06, "archive_windows": 100000, "env_steps": 27350, "total_transitions": 112025600, "num_steps_per_env": 1, "wm_loss": 0.48497653007507324, "actor_loss": -8.872957229614258, "critic_loss": 0.018429791554808617, "reward": 0.0713389664888382, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23699337244033813, 0.15381643176078796, 0.24713630974292755], "policy_updates": 27250, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2874.848844313, "contact_bce": 0.3215491771697998, "contact_force_loss": 0.033437252044677734, "terrain_level_mean": 3.01220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27360, "actor_lr": 2.9058266890247155e-06, "archive_windows": 100000, "env_steps": 27360, "total_transitions": 112066560, "num_steps_per_env": 1, "wm_loss": 0.4634459912776947, "actor_loss": -8.817222595214844, "critic_loss": 0.018416037783026695, "reward": 0.07081800699234009, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24133887887001038, 0.156612828373909, 0.2520369291305542], "policy_updates": 27260, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2880.116580402, "contact_bce": 0.32476159930229187, "contact_force_loss": 0.032551493495702744, "terrain_level_mean": 3.011962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27370, "actor_lr": 2.897521183301573e-06, "archive_windows": 100000, "env_steps": 27370, "total_transitions": 112107520, "num_steps_per_env": 1, "wm_loss": 0.47604072093963623, "actor_loss": -8.861212730407715, "critic_loss": 0.019310614094138145, "reward": 0.07003650069236755, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24306373298168182, 0.1589127480983734, 0.255800724029541], "policy_updates": 27270, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2885.168885738, "contact_bce": 0.3264921307563782, "contact_force_loss": 0.032954685389995575, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9991931915283203]} {"step": 27380, "actor_lr": 2.889246385729867e-06, "archive_windows": 100000, "env_steps": 27380, "total_transitions": 112148480, "num_steps_per_env": 1, "wm_loss": 0.47552967071533203, "actor_loss": -8.848136901855469, "critic_loss": 0.02550589106976986, "reward": 0.07032632827758789, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23898006975650787, 0.15931876003742218, 0.2572314143180847], "policy_updates": 27280, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2890.1643900550002, "contact_bce": 0.323857843875885, "contact_force_loss": 0.03260144963860512, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9996583461761475]} {"step": 27390, "actor_lr": 2.881002305383923e-06, "archive_windows": 100000, "env_steps": 27390, "total_transitions": 112189440, "num_steps_per_env": 1, "wm_loss": 0.5006993412971497, "actor_loss": -8.814764976501465, "critic_loss": 0.01787768304347992, "reward": 0.0707942396402359, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2404579371213913, 0.15807843208312988, 0.25433841347694397], "policy_updates": 27290, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2895.101981567, "contact_bce": 0.3234488070011139, "contact_force_loss": 0.033184412866830826, "terrain_level_mean": 3.01318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9996583461761475]} {"step": 27400, "actor_lr": 2.872788951304392e-06, "archive_windows": 100000, "env_steps": 27400, "total_transitions": 112230400, "num_steps_per_env": 1, "wm_loss": 0.46686846017837524, "actor_loss": -8.796825408935547, "critic_loss": 0.028996629640460014, "reward": 0.07056363672018051, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23785538971424103, 0.16017721593379974, 0.2575492262840271], "policy_updates": 27300, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2900.392786529, "contact_bce": 0.32561856508255005, "contact_force_loss": 0.03197357431054115, "terrain_level_mean": 3.01318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9977357387542725, 0.9997506141662598, 2.9996583461761475]} {"step": 27410, "actor_lr": 2.864606332498218e-06, "archive_windows": 100000, "env_steps": 27410, "total_transitions": 112271360, "num_steps_per_env": 1, "wm_loss": 0.5103060603141785, "actor_loss": -8.8479642868042, "critic_loss": 0.027194593101739883, "reward": 0.07087358087301254, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23755033314228058, 0.1580531895160675, 0.25675544142723083], "policy_updates": 27310, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2906.0556543000002, "contact_bce": 0.3267139792442322, "contact_force_loss": 0.033283933997154236, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27420, "actor_lr": 2.8564544579386446e-06, "archive_windows": 100000, "env_steps": 27420, "total_transitions": 112312320, "num_steps_per_env": 1, "wm_loss": 0.49695494771003723, "actor_loss": -8.837051391601562, "critic_loss": 0.02181125245988369, "reward": 0.07070979475975037, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24324551224708557, 0.16068395972251892, 0.2574305534362793], "policy_updates": 27320, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2911.307036737, "contact_bce": 0.3256084620952606, "contact_force_loss": 0.03252274543046951, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27430, "actor_lr": 2.848333336565212e-06, "archive_windows": 100000, "env_steps": 27430, "total_transitions": 112353280, "num_steps_per_env": 1, "wm_loss": 0.4803265631198883, "actor_loss": -8.796496391296387, "critic_loss": 0.02612427808344364, "reward": 0.07040929794311523, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24748750030994415, 0.16008266806602478, 0.2529560625553131], "policy_updates": 27330, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2916.280877392, "contact_bce": 0.3251855969429016, "contact_force_loss": 0.03285625949501991, "terrain_level_mean": 3.01318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27440, "actor_lr": 2.8402429772837203e-06, "archive_windows": 100000, "env_steps": 27440, "total_transitions": 112394240, "num_steps_per_env": 1, "wm_loss": 0.45068368315696716, "actor_loss": -8.79340648651123, "critic_loss": 0.03693374991416931, "reward": 0.07013344019651413, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24607719480991364, 0.15780049562454224, 0.2542632520198822], "policy_updates": 27340, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2921.393267709, "contact_bce": 0.32479923963546753, "contact_force_loss": 0.03200798109173775, "terrain_level_mean": 3.013427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27450, "actor_lr": 2.8321833889662372e-06, "archive_windows": 100000, "env_steps": 27450, "total_transitions": 112435200, "num_steps_per_env": 1, "wm_loss": 0.5132108330726624, "actor_loss": -8.83371353149414, "critic_loss": 0.018160535022616386, "reward": 0.07063468545675278, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24520719051361084, 0.15622760355472565, 0.2526680827140808], "policy_updates": 27350, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2926.682057563, "contact_bce": 0.3263721466064453, "contact_force_loss": 0.03343353047966957, "terrain_level_mean": 3.013916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27460, "actor_lr": 2.824154580451089e-06, "archive_windows": 100000, "env_steps": 27460, "total_transitions": 112476160, "num_steps_per_env": 1, "wm_loss": 0.5322456955909729, "actor_loss": -8.816750526428223, "critic_loss": 0.028445735573768616, "reward": 0.07066996395587921, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2400617003440857, 0.15718649327754974, 0.25618231296539307], "policy_updates": 27360, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2931.759766001, "contact_bce": 0.3233552873134613, "contact_force_loss": 0.032713960856199265, "terrain_level_mean": 3.013427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27470, "actor_lr": 2.8161565605428573e-06, "archive_windows": 100000, "env_steps": 27470, "total_transitions": 112517120, "num_steps_per_env": 1, "wm_loss": 0.5020679831504822, "actor_loss": -8.863401412963867, "critic_loss": 0.025102263316512108, "reward": 0.07081625610589981, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2366945445537567, 0.15695993602275848, 0.25187328457832336], "policy_updates": 27370, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2937.062905721, "contact_bce": 0.3233594298362732, "contact_force_loss": 0.0328899510204792, "terrain_level_mean": 3.013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27480, "actor_lr": 2.8081893380123376e-06, "archive_windows": 100000, "env_steps": 27480, "total_transitions": 112558080, "num_steps_per_env": 1, "wm_loss": 0.48327386379241943, "actor_loss": -8.786211013793945, "critic_loss": 0.02450810931622982, "reward": 0.07049788534641266, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23577356338500977, 0.15784096717834473, 0.252422034740448], "policy_updates": 27380, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2942.319469271, "contact_bce": 0.32145199179649353, "contact_force_loss": 0.03312485292553902, "terrain_level_mean": 3.013427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9985151290893555, 0.9997506141662598, 2.9996583461761475]} {"step": 27490, "actor_lr": 2.80025292159658e-06, "archive_windows": 100000, "env_steps": 27490, "total_transitions": 112599040, "num_steps_per_env": 1, "wm_loss": 0.4541793763637543, "actor_loss": -8.845962524414062, "critic_loss": 0.028581324964761734, "reward": 0.07057168334722519, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23900051414966583, 0.15690629184246063, 0.25169357657432556], "policy_updates": 27390, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2947.5005051050002, "contact_bce": 0.32511433959007263, "contact_force_loss": 0.03304680436849594, "terrain_level_mean": 3.01318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9996036291122437, 0.9997506141662598, 2.9996583461761475]} {"step": 27500, "actor_lr": 2.7923473199988345e-06, "archive_windows": 100000, "env_steps": 27500, "total_transitions": 112640000, "num_steps_per_env": 1, "wm_loss": 0.5041250586509705, "actor_loss": -8.802648544311523, "critic_loss": 0.026479607447981834, "reward": 0.07101541012525558, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23776033520698547, 0.15554179251194, 0.25019603967666626], "policy_updates": 27400, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2952.5918111260003, "contact_bce": 0.32845067977905273, "contact_force_loss": 0.03448000177741051, "terrain_level_mean": 3.013916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9996036291122437, 0.9997506141662598, 2.9996583461761475]} {"step": 27510, "actor_lr": 2.784472541888552e-06, "archive_windows": 100000, "env_steps": 27510, "total_transitions": 112680960, "num_steps_per_env": 1, "wm_loss": 0.4895569980144501, "actor_loss": -8.766825675964355, "critic_loss": 0.04110894724726677, "reward": 0.07077579200267792, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23954735696315765, 0.1556461602449417, 0.2492198795080185], "policy_updates": 27410, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2957.7050382420002, "contact_bce": 0.3261217176914215, "contact_force_loss": 0.03263681009411812, "terrain_level_mean": 3.0146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9996036291122437, 0.9997506141662598, 2.9996583461761475]} {"step": 27520, "actor_lr": 2.7766285959014073e-06, "archive_windows": 100000, "env_steps": 27520, "total_transitions": 112721920, "num_steps_per_env": 1, "wm_loss": 0.47433602809906006, "actor_loss": -8.852347373962402, "critic_loss": 0.01840631105005741, "reward": 0.07074066251516342, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23909582197666168, 0.15477143228054047, 0.24909880757331848], "policy_updates": 27420, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2962.651540079, "contact_bce": 0.3173719346523285, "contact_force_loss": 0.03223814442753792, "terrain_level_mean": 3.014404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9996036291122437, 0.9997506141662598, 2.9996583461761475]} {"step": 27530, "actor_lr": 2.7688154906392407e-06, "archive_windows": 100000, "env_steps": 27530, "total_transitions": 112762880, "num_steps_per_env": 1, "wm_loss": 0.47689270973205566, "actor_loss": -8.810779571533203, "critic_loss": 0.02910648100078106, "reward": 0.07079542428255081, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23662157356739044, 0.15533097088336945, 0.24992899596691132], "policy_updates": 27430, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2967.705154775, "contact_bce": 0.3213233947753906, "contact_force_loss": 0.03331543132662773, "terrain_level_mean": 3.013427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9996036291122437, 0.9997506141662598, 2.9996583461761475]} {"step": 27540, "actor_lr": 2.76103323467008e-06, "archive_windows": 100000, "env_steps": 27540, "total_transitions": 112803840, "num_steps_per_env": 1, "wm_loss": 0.4791105389595032, "actor_loss": -8.822383880615234, "critic_loss": 0.031656794250011444, "reward": 0.07113009691238403, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2385047823190689, 0.15295089781284332, 0.2495839148759842], "policy_updates": 27440, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2972.751346783, "contact_bce": 0.32112228870391846, "contact_force_loss": 0.032453056424856186, "terrain_level_mean": 3.01318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9996036291122437, 0.9997506141662598, 2.9996583461761475]} {"step": 27550, "actor_lr": 2.7532818365281294e-06, "archive_windows": 100000, "env_steps": 27550, "total_transitions": 112844800, "num_steps_per_env": 1, "wm_loss": 0.489713579416275, "actor_loss": -8.793014526367188, "critic_loss": 0.025299087166786194, "reward": 0.07132904976606369, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23781061172485352, 0.15029719471931458, 0.2517712116241455], "policy_updates": 27450, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2977.814389919, "contact_bce": 0.3185330927371979, "contact_force_loss": 0.03217175602912903, "terrain_level_mean": 3.0146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9996036291122437, 0.9977700710296631, 2.9996583461761475]} {"step": 27560, "actor_lr": 2.7455613047137407e-06, "archive_windows": 100000, "env_steps": 27560, "total_transitions": 112885760, "num_steps_per_env": 1, "wm_loss": 0.46833881735801697, "actor_loss": -8.824552536010742, "critic_loss": 0.026321491226553917, "reward": 0.0712716355919838, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24177956581115723, 0.15045194327831268, 0.2528885304927826], "policy_updates": 27460, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2982.989388254, "contact_bce": 0.3191412389278412, "contact_force_loss": 0.03231407701969147, "terrain_level_mean": 3.01513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9947854280471802, 0.9977700710296631, 2.9996583461761475]} {"step": 27570, "actor_lr": 2.737871647693422e-06, "archive_windows": 100000, "env_steps": 27570, "total_transitions": 112926720, "num_steps_per_env": 1, "wm_loss": 0.4901137053966522, "actor_loss": -8.839445114135742, "critic_loss": 0.02263157069683075, "reward": 0.07096844166517258, "falls": 0, "interval_steps": 10, "velocity_mae": [0.2425706535577774, 0.14938876032829285, 0.24699249863624573], "policy_updates": 27470, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2988.120786264, "contact_bce": 0.3290921747684479, "contact_force_loss": 0.03268001601099968, "terrain_level_mean": 3.01611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9992445707321167, 0.9977700710296631, 2.9996583461761475]} {"step": 27580, "actor_lr": 2.730212873899832e-06, "archive_windows": 100000, "env_steps": 27580, "total_transitions": 112967680, "num_steps_per_env": 1, "wm_loss": 0.4880133271217346, "actor_loss": -8.796417236328125, "critic_loss": 0.035651735961437225, "reward": 0.07049517333507538, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2439616173505783, 0.15015994012355804, 0.25163424015045166], "policy_updates": 27480, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2993.168867141, "contact_bce": 0.3307851254940033, "contact_force_loss": 0.03349238634109497, "terrain_level_mean": 3.01513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9994232654571533, 0.9977700710296631, 2.9996583461761475]} {"step": 27590, "actor_lr": 2.7225849917317516e-06, "archive_windows": 100000, "env_steps": 27590, "total_transitions": 113008640, "num_steps_per_env": 1, "wm_loss": 0.5000618696212769, "actor_loss": -8.829005241394043, "critic_loss": 0.018920989707112312, "reward": 0.07019742578268051, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24513457715511322, 0.1532570719718933, 0.2516317665576935], "policy_updates": 27490, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 2998.189593183, "contact_bce": 0.3270041346549988, "contact_force_loss": 0.03303848206996918, "terrain_level_mean": 3.01416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9994232654571533, 0.9977700710296631, 2.9996583461761475]} {"step": 27600, "actor_lr": 2.7149880095540907e-06, "archive_windows": 100000, "env_steps": 27600, "total_transitions": 113049600, "num_steps_per_env": 1, "wm_loss": 0.489228755235672, "actor_loss": -8.840221405029297, "critic_loss": 0.030123889446258545, "reward": 0.07031195610761642, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24279823899269104, 0.152460977435112, 0.2525175213813782], "policy_updates": 27500, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 3003.199699863, "contact_bce": 0.3217907249927521, "contact_force_loss": 0.03247832506895065, "terrain_level_mean": 3.015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9994232654571533, 0.9987640380859375, 2.9996583461761475]} {"step": 27610, "actor_lr": 2.707421935697868e-06, "archive_windows": 100000, "env_steps": 27610, "total_transitions": 113090560, "num_steps_per_env": 1, "wm_loss": 0.4767519533634186, "actor_loss": -8.802188873291016, "critic_loss": 0.02082071639597416, "reward": 0.07062865793704987, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24010856449604034, 0.15226134657859802, 0.24782218039035797], "policy_updates": 27510, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 3008.190176867, "contact_bce": 0.3212803900241852, "contact_force_loss": 0.03216012939810753, "terrain_level_mean": 3.0146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9994232654571533, 0.9987640380859375, 2.9996583461761475]} {"step": 27620, "actor_lr": 2.6998867784602174e-06, "archive_windows": 100000, "env_steps": 27620, "total_transitions": 113131520, "num_steps_per_env": 1, "wm_loss": 0.4899466335773468, "actor_loss": -8.843517303466797, "critic_loss": 0.02145267091691494, "reward": 0.07077476382255554, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23688164353370667, 0.15190544724464417, 0.24663977324962616], "policy_updates": 27520, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 3013.219311781, "contact_bce": 0.32418057322502136, "contact_force_loss": 0.0336732417345047, "terrain_level_mean": 3.01611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9994232654571533, 0.9987640380859375, 2.9996583461761475]} {"step": 27630, "actor_lr": 2.692382546104353e-06, "archive_windows": 100000, "env_steps": 27630, "total_transitions": 113172480, "num_steps_per_env": 1, "wm_loss": 0.4794073700904846, "actor_loss": -8.838852882385254, "critic_loss": 0.020929697901010513, "reward": 0.07047086954116821, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23873348534107208, 0.1550612598657608, 0.25547704100608826], "policy_updates": 27530, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 3018.0989083100003, "contact_bce": 0.3252063989639282, "contact_force_loss": 0.03285207226872444, "terrain_level_mean": 3.016845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9994232654571533, 0.9987640380859375, 2.995911121368408]} {"step": 27640, "actor_lr": 2.684909246859594e-06, "archive_windows": 100000, "env_steps": 27640, "total_transitions": 113213440, "num_steps_per_env": 1, "wm_loss": 0.47466710209846497, "actor_loss": -8.80124282836914, "critic_loss": 0.026194080710411072, "reward": 0.0703820288181305, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24186038970947266, 0.15704753994941711, 0.25437697768211365], "policy_updates": 27540, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 3022.998587909, "contact_bce": 0.32328295707702637, "contact_force_loss": 0.03290291875600815, "terrain_level_mean": 3.016845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9994232654571533, 0.9994828701019287, 2.995911121368408]} {"step": 27650, "actor_lr": 2.677466888921329e-06, "archive_windows": 100000, "env_steps": 27650, "total_transitions": 113254400, "num_steps_per_env": 1, "wm_loss": 0.4931735098361969, "actor_loss": -8.831003189086914, "critic_loss": 0.026606356725096703, "reward": 0.07041061669588089, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24232915043830872, 0.15737980604171753, 0.2513329088687897], "policy_updates": 27550, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 3027.965309398, "contact_bce": 0.32806524634361267, "contact_force_loss": 0.03342917189002037, "terrain_level_mean": 3.01611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9994232654571533, 0.9994828701019287, 2.995911121368408]} {"step": 27660, "actor_lr": 2.6700554804510124e-06, "archive_windows": 100000, "env_steps": 27660, "total_transitions": 113295360, "num_steps_per_env": 1, "wm_loss": 0.5228396654129028, "actor_loss": -8.75795841217041, "critic_loss": 0.039346423000097275, "reward": 0.07041491568088531, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24232958257198334, 0.15682871639728546, 0.25308239459991455], "policy_updates": 27560, "skipped_updates": 0, "invalid_env_resets": 14, "elapsed_s": 3033.24860862, "contact_bce": 0.3263595700263977, "contact_force_loss": 0.033129893243312836, "terrain_level_mean": 3.016845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9994232654571533, 0.9994828701019287, 2.995911121368408]} RECOVERY reset 1 invalid environments; first IDs=[42] {"step": 27670, "actor_lr": 2.662675029576162e-06, "archive_windows": 100000, "env_steps": 27670, "total_transitions": 113336320, "num_steps_per_env": 1, "wm_loss": 0.5157496333122253, "actor_loss": -8.8443021774292, "critic_loss": 0.02309388853609562, "reward": 0.07041019201278687, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24452954530715942, 0.15669037401676178, 0.2536611557006836], "policy_updates": 27570, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3038.2286692810003, "contact_bce": 0.3240184485912323, "contact_force_loss": 0.0332813560962677, "terrain_level_mean": 3.016357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27680, "actor_lr": 2.6553255443903523e-06, "archive_windows": 100000, "env_steps": 27680, "total_transitions": 113377280, "num_steps_per_env": 1, "wm_loss": 0.48877641558647156, "actor_loss": -8.791230201721191, "critic_loss": 0.027128303423523903, "reward": 0.07044541090726852, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24601778388023376, 0.1580747663974762, 0.25204429030418396], "policy_updates": 27580, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3043.872785288, "contact_bce": 0.32413363456726074, "contact_force_loss": 0.03323720395565033, "terrain_level_mean": 3.01611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27690, "actor_lr": 2.648007032953185e-06, "archive_windows": 100000, "env_steps": 27690, "total_transitions": 113418240, "num_steps_per_env": 1, "wm_loss": 0.47593677043914795, "actor_loss": -8.824777603149414, "critic_loss": 0.021657783538103104, "reward": 0.07076442986726761, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2456924170255661, 0.15605247020721436, 0.25295981764793396], "policy_updates": 27590, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3049.1854173730003, "contact_bce": 0.322021484375, "contact_force_loss": 0.033165644854307175, "terrain_level_mean": 3.016845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27700, "actor_lr": 2.640719503290318e-06, "archive_windows": 100000, "env_steps": 27700, "total_transitions": 113459200, "num_steps_per_env": 1, "wm_loss": 0.48417213559150696, "actor_loss": -8.824305534362793, "critic_loss": 0.023728495463728905, "reward": 0.07047360390424728, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2381274700164795, 0.15638986229896545, 0.25400134921073914], "policy_updates": 27600, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3054.5294119590003, "contact_bce": 0.3285757005214691, "contact_force_loss": 0.03353072330355644, "terrain_level_mean": 3.0166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27710, "actor_lr": 2.633462963393414e-06, "archive_windows": 100000, "env_steps": 27710, "total_transitions": 113500160, "num_steps_per_env": 1, "wm_loss": 0.46792301535606384, "actor_loss": -8.80279541015625, "critic_loss": 0.02251865528523922, "reward": 0.07055456191301346, "falls": 4, "interval_steps": 10, "velocity_mae": [0.236816868185997, 0.15864382684230804, 0.25340887904167175], "policy_updates": 27610, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3059.8990405130003, "contact_bce": 0.32198426127433777, "contact_force_loss": 0.03295289725065231, "terrain_level_mean": 3.01611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27720, "actor_lr": 2.626237421220156e-06, "archive_windows": 100000, "env_steps": 27720, "total_transitions": 113541120, "num_steps_per_env": 1, "wm_loss": 0.453519731760025, "actor_loss": -8.799819946289062, "critic_loss": 0.02791621722280979, "reward": 0.07037501782178879, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24062806367874146, 0.15988382697105408, 0.2544264495372772], "policy_updates": 27620, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3065.2798314, "contact_bce": 0.31964561343193054, "contact_force_loss": 0.031402647495269775, "terrain_level_mean": 3.014892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27730, "actor_lr": 2.6190428846942434e-06, "archive_windows": 100000, "env_steps": 27730, "total_transitions": 113582080, "num_steps_per_env": 1, "wm_loss": 0.48111680150032043, "actor_loss": -8.844549179077148, "critic_loss": 0.031382400542497635, "reward": 0.07037875801324844, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2420308142900467, 0.15878580510616302, 0.2542564570903778], "policy_updates": 27630, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3070.648931772, "contact_bce": 0.32437288761138916, "contact_force_loss": 0.03334517776966095, "terrain_level_mean": 3.015869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27740, "actor_lr": 2.6118793617053658e-06, "archive_windows": 100000, "env_steps": 27740, "total_transitions": 113623040, "num_steps_per_env": 1, "wm_loss": 0.5171418786048889, "actor_loss": -8.849294662475586, "critic_loss": 0.02441016398370266, "reward": 0.07009443640708923, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24241143465042114, 0.1580931395292282, 0.2518697679042816], "policy_updates": 27640, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3076.07096764, "contact_bce": 0.32398730516433716, "contact_force_loss": 0.03248362988233566, "terrain_level_mean": 3.016845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27750, "actor_lr": 2.604746860109199e-06, "archive_windows": 100000, "env_steps": 27750, "total_transitions": 113664000, "num_steps_per_env": 1, "wm_loss": 0.4747997522354126, "actor_loss": -8.774295806884766, "critic_loss": 0.022459719330072403, "reward": 0.06980624049901962, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24496661126613617, 0.15861603617668152, 0.25577905774116516], "policy_updates": 27650, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3081.443066753, "contact_bce": 0.3215763568878174, "contact_force_loss": 0.032414354383945465, "terrain_level_mean": 3.01611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.995911121368408]} {"step": 27760, "actor_lr": 2.5976453877274127e-06, "archive_windows": 100000, "env_steps": 27760, "total_transitions": 113704960, "num_steps_per_env": 1, "wm_loss": 0.480903685092926, "actor_loss": -8.8306884765625, "critic_loss": 0.02414877526462078, "reward": 0.06960927695035934, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24707631766796112, 0.1616041511297226, 0.2627502977848053], "policy_updates": 27660, "skipped_updates": 0, "invalid_env_resets": 15, "elapsed_s": 3086.887433018, "contact_bce": 0.3243114948272705, "contact_force_loss": 0.032330647110939026, "terrain_level_mean": 3.016357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.9909565448760986]} RECOVERY reset 1 invalid environments; first IDs=[1491] {"step": 27770, "actor_lr": 2.5905749523476427e-06, "archive_windows": 100000, "env_steps": 27770, "total_transitions": 113745920, "num_steps_per_env": 1, "wm_loss": 0.48922860622406006, "actor_loss": -8.817543983459473, "critic_loss": 0.020457929000258446, "reward": 0.06964591145515442, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24622000753879547, 0.16280335187911987, 0.25793027877807617], "policy_updates": 27670, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3092.356557388, "contact_bce": 0.3201519548892975, "contact_force_loss": 0.03253617137670517, "terrain_level_mean": 3.015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.9909565448760986]} {"step": 27780, "actor_lr": 2.5835355617234767e-06, "archive_windows": 100000, "env_steps": 27780, "total_transitions": 113786880, "num_steps_per_env": 1, "wm_loss": 0.47493240237236023, "actor_loss": -8.82095718383789, "critic_loss": 0.02802724950015545, "reward": 0.06957157701253891, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24407793581485748, 0.16267918050289154, 0.2528587877750397], "policy_updates": 27680, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3097.806144655, "contact_bce": 0.32305288314819336, "contact_force_loss": 0.0322127565741539, "terrain_level_mean": 3.013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.9909565448760986]} {"step": 27790, "actor_lr": 2.5765272235744827e-06, "archive_windows": 100000, "env_steps": 27790, "total_transitions": 113827840, "num_steps_per_env": 1, "wm_loss": 0.5169685482978821, "actor_loss": -8.813920021057129, "critic_loss": 0.03352845460176468, "reward": 0.06992712616920471, "falls": 1, "interval_steps": 10, "velocity_mae": [0.243172287940979, 0.1620790660381317, 0.2580367624759674], "policy_updates": 27690, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3103.243847435, "contact_bce": 0.3249306380748749, "contact_force_loss": 0.03261584788560867, "terrain_level_mean": 3.015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.9909565448760986]} {"step": 27800, "actor_lr": 2.569549945586157e-06, "archive_windows": 100000, "env_steps": 27800, "total_transitions": 113868800, "num_steps_per_env": 1, "wm_loss": 0.48461657762527466, "actor_loss": -8.773330688476562, "critic_loss": 0.028265148401260376, "reward": 0.06983387470245361, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24452152848243713, 0.16025586426258087, 0.25944629311561584], "policy_updates": 27700, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3108.6562380190003, "contact_bce": 0.3221836984157562, "contact_force_loss": 0.03301963582634926, "terrain_level_mean": 3.0146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.999712586402893, 0.9994828701019287, 2.9909565448760986]} {"step": 27810, "actor_lr": 2.562603735409938e-06, "archive_windows": 100000, "env_steps": 27810, "total_transitions": 113909760, "num_steps_per_env": 1, "wm_loss": 0.49977976083755493, "actor_loss": -8.758431434631348, "critic_loss": 0.028195196762681007, "reward": 0.06978815048933029, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2454601526260376, 0.1574646532535553, 0.259145587682724], "policy_updates": 27710, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3114.07534239, "contact_bce": 0.3230414390563965, "contact_force_loss": 0.03287256136536598, "terrain_level_mean": 3.013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.999712586402893, 0.9995782375335693, 2.9909565448760986]} {"step": 27820, "actor_lr": 2.555688600663204e-06, "archive_windows": 100000, "env_steps": 27820, "total_transitions": 113950720, "num_steps_per_env": 1, "wm_loss": 0.47190526127815247, "actor_loss": -8.7598876953125, "critic_loss": 0.03131881356239319, "reward": 0.06967635452747345, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24410885572433472, 0.16051921248435974, 0.25785699486732483], "policy_updates": 27720, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3119.5005722660003, "contact_bce": 0.32635292410850525, "contact_force_loss": 0.032731011509895325, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.999712586402893, 0.9995782375335693, 2.9909565448760986]} {"step": 27830, "actor_lr": 2.548804548929247e-06, "archive_windows": 100000, "env_steps": 27830, "total_transitions": 113991680, "num_steps_per_env": 1, "wm_loss": 0.478880375623703, "actor_loss": -8.862052917480469, "critic_loss": 0.016574304550886154, "reward": 0.07048817723989487, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2424917221069336, 0.16156989336013794, 0.25946617126464844], "policy_updates": 27730, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3124.79138015, "contact_bce": 0.3156701624393463, "contact_force_loss": 0.032491929829120636, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.999712586402893, 0.9995782375335693, 2.9909565448760986]} {"step": 27840, "actor_lr": 2.5419515877572676e-06, "archive_windows": 100000, "env_steps": 27840, "total_transitions": 114032640, "num_steps_per_env": 1, "wm_loss": 0.5027676820755005, "actor_loss": -8.74786376953125, "critic_loss": 0.030983610078692436, "reward": 0.0704827830195427, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2436050921678543, 0.16054345667362213, 0.25346964597702026], "policy_updates": 27740, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3129.9882546050003, "contact_bce": 0.3248829245567322, "contact_force_loss": 0.03300722688436508, "terrain_level_mean": 3.01171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.999712586402893, 0.9995782375335693, 2.9923155307769775]} {"step": 27850, "actor_lr": 2.5351297246623822e-06, "archive_windows": 100000, "env_steps": 27850, "total_transitions": 114073600, "num_steps_per_env": 1, "wm_loss": 0.5150923728942871, "actor_loss": -8.804798126220703, "critic_loss": 0.02661694400012493, "reward": 0.07060756534337997, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2441054880619049, 0.15950822830200195, 0.254268079996109], "policy_updates": 27750, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3135.138277513, "contact_bce": 0.3194733262062073, "contact_force_loss": 0.03308994695544243, "terrain_level_mean": 3.01318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.999712586402893, 0.9987542629241943, 2.9923155307769775]} {"step": 27860, "actor_lr": 2.528338967125597e-06, "archive_windows": 100000, "env_steps": 27860, "total_transitions": 114114560, "num_steps_per_env": 1, "wm_loss": 0.49920856952667236, "actor_loss": -8.836084365844727, "critic_loss": 0.020985489711165428, "reward": 0.07006172090768814, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24205555021762848, 0.15901966392993927, 0.2597446143627167], "policy_updates": 27760, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3140.273325645, "contact_bce": 0.3251408636569977, "contact_force_loss": 0.03304075449705124, "terrain_level_mean": 3.013916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.999712586402893, 0.9987542629241943, 2.9923155307769775]} {"step": 27870, "actor_lr": 2.521579322593811e-06, "archive_windows": 100000, "env_steps": 27870, "total_transitions": 114155520, "num_steps_per_env": 1, "wm_loss": 0.49877119064331055, "actor_loss": -8.759340286254883, "critic_loss": 0.030335431918501854, "reward": 0.06979992240667343, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23955124616622925, 0.15976212918758392, 0.26210683584213257], "policy_updates": 27770, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3145.563685304, "contact_bce": 0.32771968841552734, "contact_force_loss": 0.03264271840453148, "terrain_level_mean": 3.014892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9992445707321167, 0.9987591505050659, 2.9923155307769775]} {"step": 27880, "actor_lr": 2.5148507984798127e-06, "archive_windows": 100000, "env_steps": 27880, "total_transitions": 114196480, "num_steps_per_env": 1, "wm_loss": 0.4659150242805481, "actor_loss": -8.821067810058594, "critic_loss": 0.02599239908158779, "reward": 0.07002424448728561, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23906059563159943, 0.15985697507858276, 0.2552078068256378], "policy_updates": 27780, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3150.811684977, "contact_bce": 0.31931743025779724, "contact_force_loss": 0.03217364475131035, "terrain_level_mean": 3.014892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9975076913833618, 0.9987591505050659, 2.9923155307769775]} {"step": 27890, "actor_lr": 2.508153402162243e-06, "archive_windows": 100000, "env_steps": 27890, "total_transitions": 114237440, "num_steps_per_env": 1, "wm_loss": 0.519899845123291, "actor_loss": -8.73956298828125, "critic_loss": 0.03796818107366562, "reward": 0.07047098129987717, "falls": 10, "interval_steps": 10, "velocity_mae": [0.23760737478733063, 0.16056787967681885, 0.2497841715812683], "policy_updates": 27790, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3156.351395443, "contact_bce": 0.3224983811378479, "contact_force_loss": 0.03270948305726051, "terrain_level_mean": 3.013916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9975076913833618, 0.9987591505050659, 2.9923155307769775]} {"step": 27900, "actor_lr": 2.501487140985617e-06, "archive_windows": 100000, "env_steps": 27900, "total_transitions": 114278400, "num_steps_per_env": 1, "wm_loss": 0.4501984715461731, "actor_loss": -8.797565460205078, "critic_loss": 0.027970580384135246, "reward": 0.0709058865904808, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2383933812379837, 0.15791460871696472, 0.2506427764892578], "policy_updates": 27800, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3161.5923463500003, "contact_bce": 0.3168398141860962, "contact_force_loss": 0.031289514154195786, "terrain_level_mean": 3.013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9975076913833618, 0.9987591505050659, 2.9923155307769775]} {"step": 27910, "actor_lr": 2.4948520222603126e-06, "archive_windows": 100000, "env_steps": 27910, "total_transitions": 114319360, "num_steps_per_env": 1, "wm_loss": 0.45983707904815674, "actor_loss": -8.75273609161377, "critic_loss": 0.03993075713515282, "reward": 0.07095132768154144, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23981063067913055, 0.15716512501239777, 0.2567327618598938], "policy_updates": 27810, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3166.823316408, "contact_bce": 0.3219877779483795, "contact_force_loss": 0.03199833258986473, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9975076913833618, 0.9987591505050659, 2.9923155307769775]} {"step": 27920, "actor_lr": 2.488248053262552e-06, "archive_windows": 100000, "env_steps": 27920, "total_transitions": 114360320, "num_steps_per_env": 1, "wm_loss": 0.4659472107887268, "actor_loss": -8.863668441772461, "critic_loss": 0.021928414702415466, "reward": 0.07095164060592651, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2367493212223053, 0.15765908360481262, 0.25612977147102356], "policy_updates": 27820, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3172.1083328560003, "contact_bce": 0.3169569671154022, "contact_force_loss": 0.03257356956601143, "terrain_level_mean": 3.013427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9975076913833618, 0.999248743057251, 2.9923155307769775]} {"step": 27930, "actor_lr": 2.481675241234395e-06, "archive_windows": 100000, "env_steps": 27930, "total_transitions": 114401280, "num_steps_per_env": 1, "wm_loss": 0.4958841800689697, "actor_loss": -8.774428367614746, "critic_loss": 0.020719945430755615, "reward": 0.07082506269216537, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2384733259677887, 0.15703962743282318, 0.256678968667984], "policy_updates": 27830, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3177.412657385, "contact_bce": 0.3251167833805084, "contact_force_loss": 0.03291293606162071, "terrain_level_mean": 3.012451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9975076913833618, 0.999248743057251, 2.9923155307769775]} {"step": 27940, "actor_lr": 2.475133593383732e-06, "archive_windows": 100000, "env_steps": 27940, "total_transitions": 114442240, "num_steps_per_env": 1, "wm_loss": 0.4864446818828583, "actor_loss": -8.781527519226074, "critic_loss": 0.0302025955170393, "reward": 0.0710027813911438, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23862293362617493, 0.15703189373016357, 0.25548356771469116], "policy_updates": 27840, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3182.6515381120003, "contact_bce": 0.3251480460166931, "contact_force_loss": 0.032404545694589615, "terrain_level_mean": 3.011474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9975076913833618, 0.999248743057251, 2.9923155307769775]} {"step": 27950, "actor_lr": 2.468623116884288e-06, "archive_windows": 100000, "env_steps": 27950, "total_transitions": 114483200, "num_steps_per_env": 1, "wm_loss": 0.4996630549430847, "actor_loss": -8.790828704833984, "critic_loss": 0.029810382053256035, "reward": 0.0705704391002655, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2377990037202835, 0.15945039689540863, 0.25774243474006653], "policy_updates": 27850, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3187.846295246, "contact_bce": 0.32412824034690857, "contact_force_loss": 0.03354274109005928, "terrain_level_mean": 3.01171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9975076913833618, 0.999248743057251, 2.9923155307769775]} {"step": 27960, "actor_lr": 2.462143818875597e-06, "archive_windows": 100000, "env_steps": 27960, "total_transitions": 114524160, "num_steps_per_env": 1, "wm_loss": 0.4709661304950714, "actor_loss": -8.83390998840332, "critic_loss": 0.01994556002318859, "reward": 0.07105021923780441, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23547779023647308, 0.1566360741853714, 0.25832265615463257], "policy_updates": 27860, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3192.844233869, "contact_bce": 0.31777262687683105, "contact_force_loss": 0.032045889645814896, "terrain_level_mean": 3.010498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9975076913833618, 0.999248743057251, 2.9923155307769775]} {"step": 27970, "actor_lr": 2.455695706463e-06, "archive_windows": 100000, "env_steps": 27970, "total_transitions": 114565120, "num_steps_per_env": 1, "wm_loss": 0.5041635632514954, "actor_loss": -8.770121574401855, "critic_loss": 0.036442872136831284, "reward": 0.07123800367116928, "falls": 11, "interval_steps": 10, "velocity_mae": [0.23607099056243896, 0.15531279146671295, 0.2535112202167511], "policy_updates": 27870, "skipped_updates": 0, "invalid_env_resets": 16, "elapsed_s": 3197.748163752, "contact_bce": 0.32752764225006104, "contact_force_loss": 0.033128634095191956, "terrain_level_mean": 3.00927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9975076913833618, 0.999248743057251, 2.9959959983825684]} RECOVERY reset 1 invalid environments; first IDs=[1814] {"step": 27980, "actor_lr": 2.449278786717651e-06, "archive_windows": 100000, "env_steps": 27980, "total_transitions": 114606080, "num_steps_per_env": 1, "wm_loss": 0.48222896456718445, "actor_loss": -8.81580924987793, "critic_loss": 0.02874683402478695, "reward": 0.07095278054475784, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23790089786052704, 0.15664345026016235, 0.25021156668663025], "policy_updates": 27880, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3202.709615063, "contact_bce": 0.3240891695022583, "contact_force_loss": 0.0329488068819046, "terrain_level_mean": 3.009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9975076913833618, 0.999248743057251, 2.9959959983825684]} {"step": 27990, "actor_lr": 2.4428930666764795e-06, "archive_windows": 100000, "env_steps": 27990, "total_transitions": 114647040, "num_steps_per_env": 1, "wm_loss": 0.4933800995349884, "actor_loss": -8.803130149841309, "critic_loss": 0.021101731806993484, "reward": 0.0705636739730835, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24161143600940704, 0.1583549976348877, 0.2545129358768463], "policy_updates": 27890, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3207.638659185, "contact_bce": 0.3243834376335144, "contact_force_loss": 0.03257191926240921, "terrain_level_mean": 3.01123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9950884580612183, 0.999350905418396, 2.9959959983825684]} {"step": 28000, "actor_lr": 2.4365385533422177e-06, "archive_windows": 100000, "env_steps": 28000, "total_transitions": 114688000, "num_steps_per_env": 1, "wm_loss": 0.5209147334098816, "actor_loss": -8.72885799407959, "critic_loss": 0.0357205830514431, "reward": 0.07092224806547165, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23781687021255493, 0.15479347109794617, 0.2603897750377655], "policy_updates": 27900, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3212.553404715, "contact_bce": 0.320502907037735, "contact_force_loss": 0.03275022655725479, "terrain_level_mean": 3.01123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9950884580612183, 0.999350905418396, 2.9959959983825684]} {"step": 28010, "actor_lr": 2.430215253683369e-06, "archive_windows": 100000, "env_steps": 28010, "total_transitions": 114728960, "num_steps_per_env": 1, "wm_loss": 0.4871176779270172, "actor_loss": -8.788592338562012, "critic_loss": 0.03000849485397339, "reward": 0.07087793946266174, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23980340361595154, 0.15446433424949646, 0.25869399309158325], "policy_updates": 27910, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3217.572416037, "contact_bce": 0.3266744911670685, "contact_force_loss": 0.0335250087082386, "terrain_level_mean": 3.012939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9972870349884033, 0.999350905418396, 2.9959959983825684]} {"step": 28020, "actor_lr": 2.4239231746341988e-06, "archive_windows": 100000, "env_steps": 28020, "total_transitions": 114769920, "num_steps_per_env": 1, "wm_loss": 0.4906176030635834, "actor_loss": -8.835350036621094, "critic_loss": 0.026108724996447563, "reward": 0.07077911496162415, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24401016533374786, 0.1561158448457718, 0.25576502084732056], "policy_updates": 27920, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3222.7918749230003, "contact_bce": 0.32034003734588623, "contact_force_loss": 0.03272697702050209, "terrain_level_mean": 3.013916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9972870349884033, 0.999350905418396, 2.9959959983825684]} {"step": 28030, "actor_lr": 2.417662323094748e-06, "archive_windows": 100000, "env_steps": 28030, "total_transitions": 114810880, "num_steps_per_env": 1, "wm_loss": 0.4979037940502167, "actor_loss": -8.815811157226562, "critic_loss": 0.02752479910850525, "reward": 0.07116624712944031, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2382185459136963, 0.1565842181444168, 0.25314074754714966], "policy_updates": 27930, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3228.06759724, "contact_bce": 0.31183934211730957, "contact_force_loss": 0.03196309134364128, "terrain_level_mean": 3.01513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9972870349884033, 0.999350905418396, 2.9962100982666016]} {"step": 28040, "actor_lr": 2.4114327059308103e-06, "archive_windows": 100000, "env_steps": 28040, "total_transitions": 114851840, "num_steps_per_env": 1, "wm_loss": 0.5167734622955322, "actor_loss": -8.854761123657227, "critic_loss": 0.018973583355545998, "reward": 0.07107823342084885, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2347767949104309, 0.15817345678806305, 0.25870442390441895], "policy_updates": 27940, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3233.294524236, "contact_bce": 0.32599058747291565, "contact_force_loss": 0.03294718265533447, "terrain_level_mean": 3.014892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9972870349884033, 0.999350905418396, 2.9962100982666016]} {"step": 28050, "actor_lr": 2.4052343299739267e-06, "archive_windows": 100000, "env_steps": 28050, "total_transitions": 114892800, "num_steps_per_env": 1, "wm_loss": 0.46702975034713745, "actor_loss": -8.812395095825195, "critic_loss": 0.030763406306505203, "reward": 0.07088794559240341, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23557104170322418, 0.1568806916475296, 0.26315200328826904], "policy_updates": 27950, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3238.412957636, "contact_bce": 0.32105588912963867, "contact_force_loss": 0.03209485113620758, "terrain_level_mean": 3.014892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28060, "actor_lr": 2.399067202021367e-06, "archive_windows": 100000, "env_steps": 28060, "total_transitions": 114933760, "num_steps_per_env": 1, "wm_loss": 0.4886600375175476, "actor_loss": -8.778146743774414, "critic_loss": 0.03521095961332321, "reward": 0.07106571644544601, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23837704956531525, 0.15580227971076965, 0.25597083568573], "policy_updates": 27960, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3243.4376122470003, "contact_bce": 0.3202514052391052, "contact_force_loss": 0.03152716904878616, "terrain_level_mean": 3.01513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28070, "actor_lr": 2.3929313288361525e-06, "archive_windows": 100000, "env_steps": 28070, "total_transitions": 114974720, "num_steps_per_env": 1, "wm_loss": 0.47325581312179565, "actor_loss": -8.82170581817627, "critic_loss": 0.02161175012588501, "reward": 0.07060803472995758, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24359183013439178, 0.15983502566814423, 0.254474937915802], "policy_updates": 27970, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3248.589196725, "contact_bce": 0.3280569911003113, "contact_force_loss": 0.03324944153428078, "terrain_level_mean": 3.016357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28080, "actor_lr": 2.386826717147012e-06, "archive_windows": 100000, "env_steps": 28080, "total_transitions": 115015680, "num_steps_per_env": 1, "wm_loss": 0.5252775549888611, "actor_loss": -8.850666046142578, "critic_loss": 0.0224785003811121, "reward": 0.07035421580076218, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24099376797676086, 0.1594512164592743, 0.2553888261318207], "policy_updates": 27980, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3253.5796465430003, "contact_bce": 0.3254995048046112, "contact_force_loss": 0.033489592373371124, "terrain_level_mean": 3.015869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28090, "actor_lr": 2.3807533736484066e-06, "archive_windows": 100000, "env_steps": 28090, "total_transitions": 115056640, "num_steps_per_env": 1, "wm_loss": 0.4851210117340088, "actor_loss": -8.811175346374512, "critic_loss": 0.023710867390036583, "reward": 0.07099615037441254, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24059560894966125, 0.15683849155902863, 0.2538381814956665], "policy_updates": 27990, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3258.679679449, "contact_bce": 0.3189949095249176, "contact_force_loss": 0.032446153461933136, "terrain_level_mean": 3.01611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28100, "actor_lr": 2.374711305000506e-06, "archive_windows": 100000, "env_steps": 28100, "total_transitions": 115097600, "num_steps_per_env": 1, "wm_loss": 0.5154479742050171, "actor_loss": -8.810554504394531, "critic_loss": 0.023988837376236916, "reward": 0.07143832743167877, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23871353268623352, 0.15677820146083832, 0.2561396658420563], "policy_updates": 28000, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3263.748640541, "contact_bce": 0.32194140553474426, "contact_force_loss": 0.03291871026158333, "terrain_level_mean": 3.01708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28110, "actor_lr": 2.368700517829169e-06, "archive_windows": 100000, "env_steps": 28110, "total_transitions": 115138560, "num_steps_per_env": 1, "wm_loss": 0.49089476466178894, "actor_loss": -8.819038391113281, "critic_loss": 0.030773192644119263, "reward": 0.07120077311992645, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23591293394565582, 0.1561858355998993, 0.2571529150009155], "policy_updates": 28010, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3268.880043738, "contact_bce": 0.31876084208488464, "contact_force_loss": 0.03263723477721214, "terrain_level_mean": 3.01708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28120, "actor_lr": 2.362721018725967e-06, "archive_windows": 100000, "env_steps": 28120, "total_transitions": 115179520, "num_steps_per_env": 1, "wm_loss": 0.4995124936103821, "actor_loss": -8.7362060546875, "critic_loss": 0.026448339223861694, "reward": 0.07091766595840454, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2403457909822464, 0.1564016491174698, 0.2582188844680786], "policy_updates": 28020, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3274.017700843, "contact_bce": 0.32505908608436584, "contact_force_loss": 0.03293535113334656, "terrain_level_mean": 3.017333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28130, "actor_lr": 2.356772814248151e-06, "archive_windows": 100000, "env_steps": 28130, "total_transitions": 115220480, "num_steps_per_env": 1, "wm_loss": 0.49432313442230225, "actor_loss": -8.828100204467773, "critic_loss": 0.025348573923110962, "reward": 0.07104881852865219, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23823054134845734, 0.1562996208667755, 0.25815731287002563], "policy_updates": 28030, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3279.099752433, "contact_bce": 0.32506972551345825, "contact_force_loss": 0.03324436768889427, "terrain_level_mean": 3.017822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28140, "actor_lr": 2.3508559109186616e-06, "archive_windows": 100000, "env_steps": 28140, "total_transitions": 115261440, "num_steps_per_env": 1, "wm_loss": 0.4955727159976959, "actor_loss": -8.815977096557617, "critic_loss": 0.025498438626527786, "reward": 0.07085002213716507, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23881998658180237, 0.1569187045097351, 0.2539415955543518], "policy_updates": 28040, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3284.189901432, "contact_bce": 0.3191131353378296, "contact_force_loss": 0.03219253197312355, "terrain_level_mean": 3.017333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28150, "actor_lr": 2.3449703152261057e-06, "archive_windows": 100000, "env_steps": 28150, "total_transitions": 115302400, "num_steps_per_env": 1, "wm_loss": 0.502855658531189, "actor_loss": -8.773834228515625, "critic_loss": 0.028232812881469727, "reward": 0.07091794162988663, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23821939527988434, 0.15838496387004852, 0.2514207363128662], "policy_updates": 28050, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3289.290150035, "contact_bce": 0.32243138551712036, "contact_force_loss": 0.03261896222829819, "terrain_level_mean": 3.017333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28160, "actor_lr": 2.339116033624757e-06, "archive_windows": 100000, "env_steps": 28160, "total_transitions": 115343360, "num_steps_per_env": 1, "wm_loss": 0.4745660424232483, "actor_loss": -8.762845993041992, "critic_loss": 0.02832132577896118, "reward": 0.07074252516031265, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23851783573627472, 0.1571025252342224, 0.25506171584129333], "policy_updates": 28060, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3294.293494042, "contact_bce": 0.31946468353271484, "contact_force_loss": 0.03171062842011452, "terrain_level_mean": 3.017333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28170, "actor_lr": 2.3332930725345604e-06, "archive_windows": 100000, "env_steps": 28170, "total_transitions": 115384320, "num_steps_per_env": 1, "wm_loss": 0.5068886876106262, "actor_loss": -8.806411743164062, "critic_loss": 0.025648105889558792, "reward": 0.07081534713506699, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23796355724334717, 0.15606102347373962, 0.25405794382095337], "policy_updates": 28070, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3299.278766376, "contact_bce": 0.319429486989975, "contact_force_loss": 0.032593823969364166, "terrain_level_mean": 3.016845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28180, "actor_lr": 2.3275014383410973e-06, "archive_windows": 100000, "env_steps": 28180, "total_transitions": 115425280, "num_steps_per_env": 1, "wm_loss": 0.4900650382041931, "actor_loss": -8.852483749389648, "critic_loss": 0.02287396602332592, "reward": 0.07059731334447861, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23988403379917145, 0.154819056391716, 0.2543206512928009], "policy_updates": 28080, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3304.2397517980003, "contact_bce": 0.32143446803092957, "contact_force_loss": 0.032532259821891785, "terrain_level_mean": 3.0166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9972870349884033, 0.9994014501571655, 2.9962100982666016]} {"step": 28190, "actor_lr": 2.321741137395613e-06, "archive_windows": 100000, "env_steps": 28190, "total_transitions": 115466240, "num_steps_per_env": 1, "wm_loss": 0.5451202988624573, "actor_loss": -8.75682258605957, "critic_loss": 0.02706441842019558, "reward": 0.07135050743818283, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2387036234140396, 0.1552215963602066, 0.25609534978866577], "policy_updates": 28090, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3309.231365264, "contact_bce": 0.318637877702713, "contact_force_loss": 0.03282247111201286, "terrain_level_mean": 3.016845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9992460012435913, 0.9994014501571655, 2.9962100982666016]} {"step": 28200, "actor_lr": 2.316012176014982e-06, "archive_windows": 100000, "env_steps": 28200, "total_transitions": 115507200, "num_steps_per_env": 1, "wm_loss": 0.4524204432964325, "actor_loss": -8.799970626831055, "critic_loss": 0.03263361379504204, "reward": 0.07138247787952423, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23895740509033203, 0.15480826795101166, 0.25375881791114807], "policy_updates": 28100, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3314.208422915, "contact_bce": 0.3211962878704071, "contact_force_loss": 0.03178626671433449, "terrain_level_mean": 3.017822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9992460012435913, 0.9994014501571655, 2.992077350616455]} {"step": 28210, "actor_lr": 2.310314560481711e-06, "archive_windows": 100000, "env_steps": 28210, "total_transitions": 115548160, "num_steps_per_env": 1, "wm_loss": 0.45834195613861084, "actor_loss": -8.795626640319824, "critic_loss": 0.026939107105135918, "reward": 0.07102611660957336, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24019977450370789, 0.1540822684764862, 0.2554738223552704], "policy_updates": 28110, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3319.188596986, "contact_bce": 0.32074084877967834, "contact_force_loss": 0.03196854889392853, "terrain_level_mean": 3.018310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9972870349884033, 0.999248743057251, 2.992077350616455]} {"step": 28220, "actor_lr": 2.3046482970439365e-06, "archive_windows": 100000, "env_steps": 28220, "total_transitions": 115589120, "num_steps_per_env": 1, "wm_loss": 0.4688990116119385, "actor_loss": -8.808574676513672, "critic_loss": 0.02426503412425518, "reward": 0.07122620195150375, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2404765784740448, 0.1537659764289856, 0.25078296661376953], "policy_updates": 28120, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3324.17802543, "contact_bce": 0.32207348942756653, "contact_force_loss": 0.032817114144563675, "terrain_level_mean": 3.019287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9966328144073486, 0.999248743057251, 2.992077350616455]} {"step": 28230, "actor_lr": 2.2990133919154075e-06, "archive_windows": 100000, "env_steps": 28230, "total_transitions": 115630080, "num_steps_per_env": 1, "wm_loss": 0.4713665246963501, "actor_loss": -8.79323959350586, "critic_loss": 0.023944610729813576, "reward": 0.07117670029401779, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2386820763349533, 0.15274278819561005, 0.2538107633590698], "policy_updates": 28130, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3329.169737393, "contact_bce": 0.318200945854187, "contact_force_loss": 0.03215404972434044, "terrain_level_mean": 3.01904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9966328144073486, 0.999248743057251, 2.992077350616455]} {"step": 28240, "actor_lr": 2.293409851275489e-06, "archive_windows": 100000, "env_steps": 28240, "total_transitions": 115671040, "num_steps_per_env": 1, "wm_loss": 0.5229553580284119, "actor_loss": -8.829177856445312, "critic_loss": 0.02778264880180359, "reward": 0.07139796763658524, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23896494507789612, 0.15414559841156006, 0.2524876594543457], "policy_updates": 28140, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3334.478136753, "contact_bce": 0.32232534885406494, "contact_force_loss": 0.03281451389193535, "terrain_level_mean": 3.019775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9966328144073486, 0.999248743057251, 2.994749069213867]} {"step": 28250, "actor_lr": 2.2878376812691538e-06, "archive_windows": 100000, "env_steps": 28250, "total_transitions": 115712000, "num_steps_per_env": 1, "wm_loss": 0.48780784010887146, "actor_loss": -8.816102027893066, "critic_loss": 0.030805563554167747, "reward": 0.07113634794950485, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23931746184825897, 0.15689872205257416, 0.2550906538963318], "policy_updates": 28150, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3339.530440589, "contact_bce": 0.3219490647315979, "contact_force_loss": 0.03201252594590187, "terrain_level_mean": 3.0205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28260, "actor_lr": 2.2822968880069655e-06, "archive_windows": 100000, "env_steps": 28260, "total_transitions": 115752960, "num_steps_per_env": 1, "wm_loss": 0.4679654836654663, "actor_loss": -8.788553237915039, "critic_loss": 0.02739514224231243, "reward": 0.07077547907829285, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24108798801898956, 0.15827085077762604, 0.25772371888160706], "policy_updates": 28160, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3344.9086285460003, "contact_bce": 0.3226664066314697, "contact_force_loss": 0.03283483907580376, "terrain_level_mean": 3.021728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28270, "actor_lr": 2.2767874775650884e-06, "archive_windows": 100000, "env_steps": 28270, "total_transitions": 115793920, "num_steps_per_env": 1, "wm_loss": 0.4866371750831604, "actor_loss": -8.830236434936523, "critic_loss": 0.02932032011449337, "reward": 0.07087945938110352, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24346713721752167, 0.15774810314178467, 0.2548280954360962], "policy_updates": 28170, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3350.2106046050003, "contact_bce": 0.3225841522216797, "contact_force_loss": 0.032930489629507065, "terrain_level_mean": 3.021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28280, "actor_lr": 2.2713094559852614e-06, "archive_windows": 100000, "env_steps": 28280, "total_transitions": 115834880, "num_steps_per_env": 1, "wm_loss": 0.4722115695476532, "actor_loss": -8.80616283416748, "critic_loss": 0.02694091573357582, "reward": 0.0707954615354538, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2453356385231018, 0.15833882987499237, 0.2583511769771576], "policy_updates": 28180, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3355.311167572, "contact_bce": 0.3115127384662628, "contact_force_loss": 0.03152075037360191, "terrain_level_mean": 3.022216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28290, "actor_lr": 2.2658628292748104e-06, "archive_windows": 100000, "env_steps": 28290, "total_transitions": 115875840, "num_steps_per_env": 1, "wm_loss": 0.4791693687438965, "actor_loss": -8.81627082824707, "critic_loss": 0.02468809112906456, "reward": 0.07139580696821213, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24393676221370697, 0.15736624598503113, 0.2580590844154358], "policy_updates": 28190, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3360.3044568180003, "contact_bce": 0.3239486813545227, "contact_force_loss": 0.03306299075484276, "terrain_level_mean": 3.02294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28300, "actor_lr": 2.2604476034066253e-06, "archive_windows": 100000, "env_steps": 28300, "total_transitions": 115916800, "num_steps_per_env": 1, "wm_loss": 0.49683913588523865, "actor_loss": -8.75991153717041, "critic_loss": 0.021486878395080566, "reward": 0.07128103822469711, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24593481421470642, 0.15724460780620575, 0.25386011600494385], "policy_updates": 28200, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3365.2331004800003, "contact_bce": 0.3239419162273407, "contact_force_loss": 0.0321599543094635, "terrain_level_mean": 3.023193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28310, "actor_lr": 2.2550637843191672e-06, "archive_windows": 100000, "env_steps": 28310, "total_transitions": 115957760, "num_steps_per_env": 1, "wm_loss": 0.523430347442627, "actor_loss": -8.799454689025879, "critic_loss": 0.030080368742346764, "reward": 0.07113981246948242, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2437300831079483, 0.15536406636238098, 0.25401344895362854], "policy_updates": 28210, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3370.149364257, "contact_bce": 0.3279290497303009, "contact_force_loss": 0.033936891704797745, "terrain_level_mean": 3.023193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28320, "actor_lr": 2.24971137791646e-06, "archive_windows": 100000, "env_steps": 28320, "total_transitions": 115998720, "num_steps_per_env": 1, "wm_loss": 0.4836142957210541, "actor_loss": -8.769869804382324, "critic_loss": 0.03078489564359188, "reward": 0.07077223807573318, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24199824035167694, 0.15685030817985535, 0.2547014355659485], "policy_updates": 28220, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3375.05939984, "contact_bce": 0.3200806677341461, "contact_force_loss": 0.03277109935879707, "terrain_level_mean": 3.02392578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9971249103546143, 0.9985260963439941, 2.994749069213867]} {"step": 28330, "actor_lr": 2.2443903900680592e-06, "archive_windows": 100000, "env_steps": 28330, "total_transitions": 116039680, "num_steps_per_env": 1, "wm_loss": 0.5002703666687012, "actor_loss": -8.81903076171875, "critic_loss": 0.017158135771751404, "reward": 0.07070013880729675, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2454681396484375, 0.15722009539604187, 0.2588759660720825], "policy_updates": 28230, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3380.039792716, "contact_bce": 0.31800761818885803, "contact_force_loss": 0.03252938762307167, "terrain_level_mean": 3.025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9971249103546143, 0.9987645745277405, 2.9998741149902344]} {"step": 28340, "actor_lr": 2.2391008266090964e-06, "archive_windows": 100000, "env_steps": 28340, "total_transitions": 116080640, "num_steps_per_env": 1, "wm_loss": 0.47640618681907654, "actor_loss": -8.846414566040039, "critic_loss": 0.022671079263091087, "reward": 0.07049708813428879, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24702394008636475, 0.15690255165100098, 0.2594294250011444], "policy_updates": 28240, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3385.190947292, "contact_bce": 0.3246704936027527, "contact_force_loss": 0.03335278481245041, "terrain_level_mean": 3.024169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9971249103546143, 0.9987645745277405, 2.9998741149902344]} {"step": 28350, "actor_lr": 2.2338426933402157e-06, "archive_windows": 100000, "env_steps": 28350, "total_transitions": 116121600, "num_steps_per_env": 1, "wm_loss": 0.49400585889816284, "actor_loss": -8.839876174926758, "critic_loss": 0.017120879143476486, "reward": 0.07061981409788132, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24497148394584656, 0.15574465692043304, 0.2588379681110382], "policy_updates": 28250, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3390.502866352, "contact_bce": 0.32234206795692444, "contact_force_loss": 0.03216658905148506, "terrain_level_mean": 3.024169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9971249103546143, 0.9987645745277405, 2.9998741149902344]} {"step": 28360, "actor_lr": 2.2286159960276066e-06, "archive_windows": 100000, "env_steps": 28360, "total_transitions": 116162560, "num_steps_per_env": 1, "wm_loss": 0.46946343779563904, "actor_loss": -8.797443389892578, "critic_loss": 0.0261862613260746, "reward": 0.07095631211996078, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24178683757781982, 0.15450477600097656, 0.25448694825172424], "policy_updates": 28260, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3395.67933115, "contact_bce": 0.3161872923374176, "contact_force_loss": 0.031726837158203125, "terrain_level_mean": 3.026123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9971249103546143, 0.9987645745277405, 2.9998741149902344]} {"step": 28370, "actor_lr": 2.223420740402993e-06, "archive_windows": 100000, "env_steps": 28370, "total_transitions": 116203520, "num_steps_per_env": 1, "wm_loss": 0.49641579389572144, "actor_loss": -8.878847122192383, "critic_loss": 0.020343560725450516, "reward": 0.07106534391641617, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2456555962562561, 0.15459859371185303, 0.25848057866096497], "policy_updates": 28270, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3400.996790747, "contact_bce": 0.31774649024009705, "contact_force_loss": 0.032275840640068054, "terrain_level_mean": 3.02783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9971249103546143, 0.9987645745277405, 2.9998741149902344]} {"step": 28380, "actor_lr": 2.218256932163596e-06, "archive_windows": 100000, "env_steps": 28380, "total_transitions": 116244480, "num_steps_per_env": 1, "wm_loss": 0.4622518718242645, "actor_loss": -8.829625129699707, "critic_loss": 0.027880752459168434, "reward": 0.07100727409124374, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24436666071414948, 0.15458272397518158, 0.2567242980003357], "policy_updates": 28280, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3405.979532575, "contact_bce": 0.32343873381614685, "contact_force_loss": 0.03272023797035217, "terrain_level_mean": 3.028564453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9971249103546143, 0.9987645745277405, 2.9998741149902344]} {"step": 28390, "actor_lr": 2.2131245769721696e-06, "archive_windows": 100000, "env_steps": 28390, "total_transitions": 116285440, "num_steps_per_env": 1, "wm_loss": 0.49532419443130493, "actor_loss": -8.773530960083008, "critic_loss": 0.023335667327046394, "reward": 0.07104750722646713, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24319903552532196, 0.1523800790309906, 0.25270625948905945], "policy_updates": 28290, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3410.969530449, "contact_bce": 0.3296631872653961, "contact_force_loss": 0.0331239327788353, "terrain_level_mean": 3.028564453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9971249103546143, 0.9987645745277405, 2.9998741149902344]} {"step": 28400, "actor_lr": 2.208023680456976e-06, "archive_windows": 100000, "env_steps": 28400, "total_transitions": 116326400, "num_steps_per_env": 1, "wm_loss": 0.49161961674690247, "actor_loss": -8.829143524169922, "critic_loss": 0.021976707503199577, "reward": 0.07118747383356094, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24607475101947784, 0.1511252075433731, 0.2526797354221344], "policy_updates": 28300, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3414.665571267, "contact_bce": 0.3223494291305542, "contact_force_loss": 0.032008569687604904, "terrain_level_mean": 3.030029296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9971249103546143, 0.9996217489242554, 2.9998741149902344]} {"step": 28410, "actor_lr": 2.2029542482117667e-06, "archive_windows": 100000, "env_steps": 28410, "total_transitions": 116367360, "num_steps_per_env": 1, "wm_loss": 0.47283464670181274, "actor_loss": -8.796697616577148, "critic_loss": 0.026209330186247826, "reward": 0.07118843495845795, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24982021749019623, 0.15318608283996582, 0.2515961229801178], "policy_updates": 28310, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3418.2005267100003, "contact_bce": 0.31750351190567017, "contact_force_loss": 0.03194395452737808, "terrain_level_mean": 3.02978515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9971249103546143, 0.9996217489242554, 2.9998741149902344]} {"step": 28420, "actor_lr": 2.197916285795798e-06, "archive_windows": 100000, "env_steps": 28420, "total_transitions": 116408320, "num_steps_per_env": 1, "wm_loss": 0.5130221843719482, "actor_loss": -8.803942680358887, "critic_loss": 0.022648056969046593, "reward": 0.07094813883304596, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2487110197544098, 0.15352043509483337, 0.2563540041446686], "policy_updates": 28320, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3421.725109609, "contact_bce": 0.32872822880744934, "contact_force_loss": 0.03307386115193367, "terrain_level_mean": 3.029052734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33154296875, "command_abs_max": [1.9971249103546143, 0.9996217489242554, 2.9998741149902344]} {"step": 28430, "actor_lr": 2.1929097987338147e-06, "archive_windows": 100000, "env_steps": 28430, "total_transitions": 116449280, "num_steps_per_env": 1, "wm_loss": 0.50887531042099, "actor_loss": -8.820894241333008, "critic_loss": 0.01736336760222912, "reward": 0.07059719413518906, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2538040578365326, 0.15550896525382996, 0.25723516941070557], "policy_updates": 28330, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3425.241466737, "contact_bce": 0.31917521357536316, "contact_force_loss": 0.033494655042886734, "terrain_level_mean": 3.02880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9971249103546143, 0.9996217489242554, 2.9998741149902344]} {"step": 28440, "actor_lr": 2.1879347925160424e-06, "archive_windows": 100000, "env_steps": 28440, "total_transitions": 116490240, "num_steps_per_env": 1, "wm_loss": 0.48597434163093567, "actor_loss": -8.800853729248047, "critic_loss": 0.0211386289447546, "reward": 0.07061715424060822, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2487206906080246, 0.15885300934314728, 0.25736406445503235], "policy_updates": 28340, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3428.78009337, "contact_bce": 0.3174077570438385, "contact_force_loss": 0.0325782410800457, "terrain_level_mean": 3.02783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.999657154083252, 0.9996217489242554, 2.9998741149902344]} {"step": 28450, "actor_lr": 2.1829912725981855e-06, "archive_windows": 100000, "env_steps": 28450, "total_transitions": 116531200, "num_steps_per_env": 1, "wm_loss": 0.5029659867286682, "actor_loss": -8.822332382202148, "critic_loss": 0.03086400032043457, "reward": 0.07076866179704666, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24651895463466644, 0.1590501070022583, 0.25877097249031067], "policy_updates": 28350, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3432.318774703, "contact_bce": 0.32707101106643677, "contact_force_loss": 0.0332099124789238, "terrain_level_mean": 3.027587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.999657154083252, 0.9996217489242554, 2.9998741149902344]} {"step": 28460, "actor_lr": 2.1780792444014174e-06, "archive_windows": 100000, "env_steps": 28460, "total_transitions": 116572160, "num_steps_per_env": 1, "wm_loss": 0.4824463725090027, "actor_loss": -8.77364730834961, "critic_loss": 0.021706916391849518, "reward": 0.07137008756399155, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2439834177494049, 0.15607723593711853, 0.25791817903518677], "policy_updates": 28360, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3435.865959906, "contact_bce": 0.3246239423751831, "contact_force_loss": 0.032663360238075256, "terrain_level_mean": 3.02734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28470, "actor_lr": 2.1731987133123837e-06, "archive_windows": 100000, "env_steps": 28470, "total_transitions": 116613120, "num_steps_per_env": 1, "wm_loss": 0.48080140352249146, "actor_loss": -8.788711547851562, "critic_loss": 0.029936838895082474, "reward": 0.07123295217752457, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24448522925376892, 0.15745887160301208, 0.2600516676902771], "policy_updates": 28370, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3439.4853212850003, "contact_bce": 0.32072287797927856, "contact_force_loss": 0.03230975568294525, "terrain_level_mean": 3.02734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28480, "actor_lr": 2.168349684683184e-06, "archive_windows": 100000, "env_steps": 28480, "total_transitions": 116654080, "num_steps_per_env": 1, "wm_loss": 0.48470979928970337, "actor_loss": -8.811957359313965, "critic_loss": 0.01918214000761509, "reward": 0.07112494111061096, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24556799232959747, 0.15962070226669312, 0.25681012868881226], "policy_updates": 28380, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3443.478522029, "contact_bce": 0.32471856474876404, "contact_force_loss": 0.03271113708615303, "terrain_level_mean": 3.026611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28490, "actor_lr": 2.163532163831373e-06, "archive_windows": 100000, "env_steps": 28490, "total_transitions": 116695040, "num_steps_per_env": 1, "wm_loss": 0.49757084250450134, "actor_loss": -8.799060821533203, "critic_loss": 0.03570709377527237, "reward": 0.07109670341014862, "falls": 3, "interval_steps": 10, "velocity_mae": [0.244729146361351, 0.16064688563346863, 0.2554040849208832], "policy_updates": 28390, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3447.251865734, "contact_bce": 0.32212990522384644, "contact_force_loss": 0.03238220140337944, "terrain_level_mean": 3.026611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28500, "actor_lr": 2.1587461560399494e-06, "archive_windows": 100000, "env_steps": 28500, "total_transitions": 116736000, "num_steps_per_env": 1, "wm_loss": 0.4953024387359619, "actor_loss": -8.801651000976562, "critic_loss": 0.024437591433525085, "reward": 0.07104536145925522, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2434823215007782, 0.15811458230018616, 0.2558479309082031], "policy_updates": 28400, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3451.7529418060003, "contact_bce": 0.32308322191238403, "contact_force_loss": 0.03271309658885002, "terrain_level_mean": 3.026123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28510, "actor_lr": 2.153991666557361e-06, "archive_windows": 100000, "env_steps": 28510, "total_transitions": 116776960, "num_steps_per_env": 1, "wm_loss": 0.5156441330909729, "actor_loss": -8.842033386230469, "critic_loss": 0.02549312822520733, "reward": 0.07082062214612961, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24780799448490143, 0.15567319095134735, 0.25637173652648926], "policy_updates": 28410, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3456.298960778, "contact_bce": 0.3232312500476837, "contact_force_loss": 0.033173322677612305, "terrain_level_mean": 3.025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28520, "actor_lr": 2.149268700597485e-06, "archive_windows": 100000, "env_steps": 28520, "total_transitions": 116817920, "num_steps_per_env": 1, "wm_loss": 0.48065099120140076, "actor_loss": -8.762621879577637, "critic_loss": 0.03598963841795921, "reward": 0.07067614048719406, "falls": 0, "interval_steps": 10, "velocity_mae": [0.25107789039611816, 0.15803980827331543, 0.2600000500679016], "policy_updates": 28420, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3460.748620281, "contact_bce": 0.3260459303855896, "contact_force_loss": 0.03364844620227814, "terrain_level_mean": 3.027099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28530, "actor_lr": 2.144577263339638e-06, "archive_windows": 100000, "env_steps": 28530, "total_transitions": 116858880, "num_steps_per_env": 1, "wm_loss": 0.49937304854393005, "actor_loss": -8.787443161010742, "critic_loss": 0.02664939872920513, "reward": 0.07046503573656082, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2514135539531708, 0.16001462936401367, 0.26475998759269714], "policy_updates": 28430, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3465.199904213, "contact_bce": 0.3239631950855255, "contact_force_loss": 0.031912662088871, "terrain_level_mean": 3.02880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28540, "actor_lr": 2.1399173599285556e-06, "archive_windows": 100000, "env_steps": 28540, "total_transitions": 116899840, "num_steps_per_env": 1, "wm_loss": 0.4979371428489685, "actor_loss": -8.786633491516113, "critic_loss": 0.024638153612613678, "reward": 0.07113028317689896, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24768072366714478, 0.15902946889400482, 0.2611173093318939], "policy_updates": 28440, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3469.6519602060002, "contact_bce": 0.3216973543167114, "contact_force_loss": 0.032864220440387726, "terrain_level_mean": 3.028076171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28550, "actor_lr": 2.1352889954743877e-06, "archive_windows": 100000, "env_steps": 28550, "total_transitions": 116940800, "num_steps_per_env": 1, "wm_loss": 0.47430458664894104, "actor_loss": -8.784736633300781, "critic_loss": 0.02799142710864544, "reward": 0.07102887332439423, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24835564196109772, 0.1582961529493332, 0.25886693596839905], "policy_updates": 28450, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3474.109236285, "contact_bce": 0.3231688141822815, "contact_force_loss": 0.03243057057261467, "terrain_level_mean": 3.028564453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28560, "actor_lr": 2.130692175052708e-06, "archive_windows": 100000, "env_steps": 28560, "total_transitions": 116981760, "num_steps_per_env": 1, "wm_loss": 0.48650410771369934, "actor_loss": -8.789249420166016, "critic_loss": 0.028616011142730713, "reward": 0.07075279951095581, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2424725592136383, 0.16004525125026703, 0.2599527835845947], "policy_updates": 28460, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3477.706763683, "contact_bce": 0.3251924514770508, "contact_force_loss": 0.032585665583610535, "terrain_level_mean": 3.028076171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.999657154083252, 0.9990744590759277, 2.9998741149902344]} {"step": 28570, "actor_lr": 2.126126903704488e-06, "archive_windows": 100000, "env_steps": 28570, "total_transitions": 117022720, "num_steps_per_env": 1, "wm_loss": 0.4788837134838104, "actor_loss": -8.760271072387695, "critic_loss": 0.033891160041093826, "reward": 0.07067429274320602, "falls": 11, "interval_steps": 10, "velocity_mae": [0.24659545719623566, 0.16105087101459503, 0.2616051435470581], "policy_updates": 28470, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3482.012443564, "contact_bce": 0.32000496983528137, "contact_force_loss": 0.03253915160894394, "terrain_level_mean": 3.02685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.999657154083252, 0.9995602965354919, 2.9998741149902344]} {"step": 28580, "actor_lr": 2.121593186436118e-06, "archive_windows": 100000, "env_steps": 28580, "total_transitions": 117063680, "num_steps_per_env": 1, "wm_loss": 0.47059565782546997, "actor_loss": -8.829700469970703, "critic_loss": 0.020295022055506706, "reward": 0.07112625241279602, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2443326860666275, 0.158611461520195, 0.25748056173324585], "policy_updates": 28480, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3486.341290953, "contact_bce": 0.32352927327156067, "contact_force_loss": 0.032554712146520615, "terrain_level_mean": 3.02734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.999657154083252, 0.9995602965354919, 2.9998741149902344]} {"step": 28590, "actor_lr": 2.1170910282193685e-06, "archive_windows": 100000, "env_steps": 28590, "total_transitions": 117104640, "num_steps_per_env": 1, "wm_loss": 0.480964720249176, "actor_loss": -8.838512420654297, "critic_loss": 0.02254590392112732, "reward": 0.07136961072683334, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23945635557174683, 0.15976448357105255, 0.255779892206192], "policy_updates": 28490, "skipped_updates": 0, "invalid_env_resets": 17, "elapsed_s": 3490.667872109, "contact_bce": 0.32243624329566956, "contact_force_loss": 0.03278606757521629, "terrain_level_mean": 3.027587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9997096061706543, 0.9995602965354919, 2.9998741149902344]} RECOVERY reset 1 invalid environments; first IDs=[1686] {"step": 28600, "actor_lr": 2.112620433991406e-06, "archive_windows": 100000, "env_steps": 28600, "total_transitions": 117145600, "num_steps_per_env": 1, "wm_loss": 0.4875935912132263, "actor_loss": -8.838001251220703, "critic_loss": 0.02671380154788494, "reward": 0.07112476974725723, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23811286687850952, 0.1584678441286087, 0.2536943256855011], "policy_updates": 28500, "skipped_updates": 0, "invalid_env_resets": 18, "elapsed_s": 3495.022293724, "contact_bce": 0.32473140954971313, "contact_force_loss": 0.0329347625374794, "terrain_level_mean": 3.02783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9997096061706543, 0.9995602965354919, 2.9998741149902344]} {"step": 28610, "actor_lr": 2.108181408654788e-06, "archive_windows": 100000, "env_steps": 28610, "total_transitions": 117186560, "num_steps_per_env": 1, "wm_loss": 0.47915118932724, "actor_loss": -8.810406684875488, "critic_loss": 0.03262921795248985, "reward": 0.07088100910186768, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24112769961357117, 0.15849162638187408, 0.2541031539440155], "policy_updates": 28510, "skipped_updates": 0, "invalid_env_resets": 18, "elapsed_s": 3499.6428838310003, "contact_bce": 0.31724783778190613, "contact_force_loss": 0.03146994113922119, "terrain_level_mean": 3.0283203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9997096061706543, 0.9995602965354919, 2.9998741149902344]} {"step": 28620, "actor_lr": 2.10377395707745e-06, "archive_windows": 100000, "env_steps": 28620, "total_transitions": 117227520, "num_steps_per_env": 1, "wm_loss": 0.5307586193084717, "actor_loss": -8.748039245605469, "critic_loss": 0.030980372801423073, "reward": 0.07138251513242722, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23894093930721283, 0.15334990620613098, 0.25313660502433777], "policy_updates": 28520, "skipped_updates": 0, "invalid_env_resets": 18, "elapsed_s": 3503.957493238, "contact_bce": 0.3229908049106598, "contact_force_loss": 0.03385600075125694, "terrain_level_mean": 3.028564453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9997096061706543, 0.9995602965354919, 2.9998741149902344]} RECOVERY reset 1 invalid environments; first IDs=[849] {"step": 28630, "actor_lr": 2.099398084092698e-06, "archive_windows": 100000, "env_steps": 28630, "total_transitions": 117268480, "num_steps_per_env": 1, "wm_loss": 0.49366962909698486, "actor_loss": -8.777517318725586, "critic_loss": 0.03352835401892662, "reward": 0.07124075293540955, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23803843557834625, 0.15358678996562958, 0.25389039516448975], "policy_updates": 28530, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3508.290777224, "contact_bce": 0.3278399109840393, "contact_force_loss": 0.03313097357749939, "terrain_level_mean": 3.029296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9998137950897217, 0.9995602965354919, 2.9998741149902344]} {"step": 28640, "actor_lr": 2.095053794499225e-06, "archive_windows": 100000, "env_steps": 28640, "total_transitions": 117309440, "num_steps_per_env": 1, "wm_loss": 0.49802255630493164, "actor_loss": -8.83846664428711, "critic_loss": 0.02229980006814003, "reward": 0.07171892374753952, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23513206839561462, 0.15397080779075623, 0.2527386546134949], "policy_updates": 28540, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3512.607061671, "contact_bce": 0.3277623951435089, "contact_force_loss": 0.03293923661112785, "terrain_level_mean": 3.02978515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28650, "actor_lr": 2.090741093061068e-06, "archive_windows": 100000, "env_steps": 28650, "total_transitions": 117350400, "num_steps_per_env": 1, "wm_loss": 0.538938581943512, "actor_loss": -8.794544219970703, "critic_loss": 0.02793465368449688, "reward": 0.07100214809179306, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23765337467193604, 0.15563134849071503, 0.2547019422054291], "policy_updates": 28550, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3516.924679918, "contact_bce": 0.32718393206596375, "contact_force_loss": 0.033469308167696, "terrain_level_mean": 3.030029296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28660, "actor_lr": 2.0864599845076306e-06, "archive_windows": 100000, "env_steps": 28660, "total_transitions": 117391360, "num_steps_per_env": 1, "wm_loss": 0.476945161819458, "actor_loss": -8.847712516784668, "critic_loss": 0.030055522918701172, "reward": 0.07091008871793747, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23615257441997528, 0.15850411355495453, 0.25535833835601807], "policy_updates": 28560, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3521.247422145, "contact_bce": 0.3219175636768341, "contact_force_loss": 0.032873209565877914, "terrain_level_mean": 3.02978515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28670, "actor_lr": 2.082210473533684e-06, "archive_windows": 100000, "env_steps": 28670, "total_transitions": 117432320, "num_steps_per_env": 1, "wm_loss": 0.5125290751457214, "actor_loss": -8.787137985229492, "critic_loss": 0.0338401198387146, "reward": 0.07113101333379745, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23981359601020813, 0.15809644758701324, 0.25403982400894165], "policy_updates": 28570, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3525.604005311, "contact_bce": 0.31966447830200195, "contact_force_loss": 0.032267600297927856, "terrain_level_mean": 3.02978515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28680, "actor_lr": 2.0779925647993293e-06, "archive_windows": 100000, "env_steps": 28680, "total_transitions": 117473280, "num_steps_per_env": 1, "wm_loss": 0.5105820894241333, "actor_loss": -8.746282577514648, "critic_loss": 0.03293834254145622, "reward": 0.07103012502193451, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2419227659702301, 0.15475843846797943, 0.25874772667884827], "policy_updates": 28580, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3529.900414865, "contact_bce": 0.32671478390693665, "contact_force_loss": 0.0333554781973362, "terrain_level_mean": 3.031494140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28690, "actor_lr": 2.0738062629300197e-06, "archive_windows": 100000, "env_steps": 28690, "total_transitions": 117514240, "num_steps_per_env": 1, "wm_loss": 0.49977201223373413, "actor_loss": -8.866371154785156, "critic_loss": 0.020674889907240868, "reward": 0.07090529054403305, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24365448951721191, 0.15480825304985046, 0.2596642076969147], "policy_updates": 28590, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3534.251592572, "contact_bce": 0.3204306662082672, "contact_force_loss": 0.03279849514365196, "terrain_level_mean": 3.0302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28700, "actor_lr": 2.069651572516556e-06, "archive_windows": 100000, "env_steps": 28700, "total_transitions": 117555200, "num_steps_per_env": 1, "wm_loss": 0.5298228859901428, "actor_loss": -8.802488327026367, "critic_loss": 0.031629402190446854, "reward": 0.07109487801790237, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24732597172260284, 0.15772834420204163, 0.26164504885673523], "policy_updates": 28600, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3538.53160806, "contact_bce": 0.33173668384552, "contact_force_loss": 0.03425612673163414, "terrain_level_mean": 3.03125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28710, "actor_lr": 2.0655284981150607e-06, "archive_windows": 100000, "env_steps": 28710, "total_transitions": 117596160, "num_steps_per_env": 1, "wm_loss": 0.48725053668022156, "actor_loss": -8.830720901489258, "critic_loss": 0.025346318259835243, "reward": 0.0712522491812706, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24393263459205627, 0.1570509821176529, 0.2593076527118683], "policy_updates": 28610, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3542.494706774, "contact_bce": 0.32529860734939575, "contact_force_loss": 0.033253349363803864, "terrain_level_mean": 3.03173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9998741149902344]} {"step": 28720, "actor_lr": 2.0614370442469884e-06, "archive_windows": 100000, "env_steps": 28720, "total_transitions": 117637120, "num_steps_per_env": 1, "wm_loss": 0.5081415176391602, "actor_loss": -8.753362655639648, "critic_loss": 0.03054974041879177, "reward": 0.07076731324195862, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24625438451766968, 0.15781748294830322, 0.2608058750629425], "policy_updates": 28620, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3546.004490837, "contact_bce": 0.3257836103439331, "contact_force_loss": 0.03300338238477707, "terrain_level_mean": 3.031494140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28730, "actor_lr": 2.0573772153991236e-06, "archive_windows": 100000, "env_steps": 28730, "total_transitions": 117678080, "num_steps_per_env": 1, "wm_loss": 0.47731852531433105, "actor_loss": -8.80233383178711, "critic_loss": 0.02076542191207409, "reward": 0.07121630758047104, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24513396620750427, 0.15973106026649475, 0.2591606676578522], "policy_updates": 28630, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3549.5226996330002, "contact_bce": 0.321291983127594, "contact_force_loss": 0.03197372704744339, "terrain_level_mean": 3.03076171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28740, "actor_lr": 2.053349016023567e-06, "archive_windows": 100000, "env_steps": 28740, "total_transitions": 117719040, "num_steps_per_env": 1, "wm_loss": 0.5026431679725647, "actor_loss": -8.778974533081055, "critic_loss": 0.0347948782145977, "reward": 0.07137719541788101, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24280524253845215, 0.1583641916513443, 0.2548881471157074], "policy_updates": 28640, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3553.050357518, "contact_bce": 0.32252785563468933, "contact_force_loss": 0.0333409309387207, "terrain_level_mean": 3.031494140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28750, "actor_lr": 2.0493524505377316e-06, "archive_windows": 100000, "env_steps": 28750, "total_transitions": 117760000, "num_steps_per_env": 1, "wm_loss": 0.5002653002738953, "actor_loss": -8.804763793945312, "critic_loss": 0.028088876977562904, "reward": 0.07136324048042297, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2391703873872757, 0.15370215475559235, 0.25131669640541077], "policy_updates": 28650, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3556.593669099, "contact_bce": 0.32947906851768494, "contact_force_loss": 0.0330347865819931, "terrain_level_mean": 3.03271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28760, "actor_lr": 2.0453875233243417e-06, "archive_windows": 100000, "env_steps": 28760, "total_transitions": 117800960, "num_steps_per_env": 1, "wm_loss": 0.5092133283615112, "actor_loss": -8.838622093200684, "critic_loss": 0.03224019333720207, "reward": 0.07084276527166367, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24415896832942963, 0.15251868963241577, 0.2539527714252472], "policy_updates": 28660, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3560.112740498, "contact_bce": 0.317542165517807, "contact_force_loss": 0.03304906561970711, "terrain_level_mean": 3.03369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28770, "actor_lr": 2.041454238731423e-06, "archive_windows": 100000, "env_steps": 28770, "total_transitions": 117841920, "num_steps_per_env": 1, "wm_loss": 0.49993696808815, "actor_loss": -8.752899169921875, "critic_loss": 0.023290637880563736, "reward": 0.0717492550611496, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23150868713855743, 0.15268903970718384, 0.24640661478042603], "policy_updates": 28670, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3563.642635536, "contact_bce": 0.326690137386322, "contact_force_loss": 0.0332021601498127, "terrain_level_mean": 3.0341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28780, "actor_lr": 2.0375526010723075e-06, "archive_windows": 100000, "env_steps": 28780, "total_transitions": 117882880, "num_steps_per_env": 1, "wm_loss": 0.4879469871520996, "actor_loss": -8.817096710205078, "critic_loss": 0.030533621087670326, "reward": 0.0712369903922081, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23256398737430573, 0.15269678831100464, 0.24666470289230347], "policy_updates": 28680, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3567.191495504, "contact_bce": 0.3252231776714325, "contact_force_loss": 0.03309530019760132, "terrain_level_mean": 3.034423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28790, "actor_lr": 2.03368261462562e-06, "archive_windows": 100000, "env_steps": 28790, "total_transitions": 117923840, "num_steps_per_env": 1, "wm_loss": 0.543196976184845, "actor_loss": -8.835627555847168, "critic_loss": 0.023051872849464417, "reward": 0.07118027657270432, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23234914243221283, 0.1523747444152832, 0.24900326132774353], "policy_updates": 28690, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3570.727337546, "contact_bce": 0.32250475883483887, "contact_force_loss": 0.03330975025892258, "terrain_level_mean": 3.03515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9998137950897217, 0.9997775554656982, 2.9991445541381836]} {"step": 28800, "actor_lr": 2.0298442836352767e-06, "archive_windows": 100000, "env_steps": 28800, "total_transitions": 117964800, "num_steps_per_env": 1, "wm_loss": 0.49469131231307983, "actor_loss": -8.771943092346191, "critic_loss": 0.028726661577820778, "reward": 0.07084177434444427, "falls": 10, "interval_steps": 10, "velocity_mae": [0.23165322840213776, 0.1530122011899948, 0.2527025640010834], "policy_updates": 28700, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3574.260483431, "contact_bce": 0.32483986020088196, "contact_force_loss": 0.032991923391819, "terrain_level_mean": 3.033935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9982264041900635, 0.9997775554656982, 2.9991445541381836]} {"step": 28810, "actor_lr": 2.0260376123104717e-06, "archive_windows": 100000, "env_steps": 28810, "total_transitions": 118005760, "num_steps_per_env": 1, "wm_loss": 0.48144328594207764, "actor_loss": -8.753278732299805, "critic_loss": 0.037264641374349594, "reward": 0.07091344147920609, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23374013602733612, 0.1523449420928955, 0.2529730796813965], "policy_updates": 28710, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3577.810452111, "contact_bce": 0.329559862613678, "contact_force_loss": 0.033767737448215485, "terrain_level_mean": 3.034423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9982264041900635, 0.9997775554656982, 2.9991445541381836]} {"step": 28820, "actor_lr": 2.022262604825694e-06, "archive_windows": 100000, "env_steps": 28820, "total_transitions": 118046720, "num_steps_per_env": 1, "wm_loss": 0.4850556254386902, "actor_loss": -8.807334899902344, "critic_loss": 0.031830258667469025, "reward": 0.0711376890540123, "falls": 2, "interval_steps": 10, "velocity_mae": [0.236036017537117, 0.15371552109718323, 0.2519244849681854], "policy_updates": 28720, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3581.353269729, "contact_bce": 0.31675460934638977, "contact_force_loss": 0.03235853463411331, "terrain_level_mean": 3.03515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9982264041900635, 0.9997775554656982, 2.9991445541381836]} {"step": 28830, "actor_lr": 2.0185192653206966e-06, "archive_windows": 100000, "env_steps": 28830, "total_transitions": 118087680, "num_steps_per_env": 1, "wm_loss": 0.5175827741622925, "actor_loss": -8.795341491699219, "critic_loss": 0.026236707344651222, "reward": 0.07108211517333984, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23307809233665466, 0.1555468589067459, 0.2502172589302063], "policy_updates": 28730, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3584.897205804, "contact_bce": 0.32481732964515686, "contact_force_loss": 0.032815925776958466, "terrain_level_mean": 3.033935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9982264041900635, 0.9997775554656982, 2.9991445541381836]} {"step": 28840, "actor_lr": 2.0148075979005113e-06, "archive_windows": 100000, "env_steps": 28840, "total_transitions": 118128640, "num_steps_per_env": 1, "wm_loss": 0.514186441898346, "actor_loss": -8.84970760345459, "critic_loss": 0.023885533213615417, "reward": 0.07114274799823761, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2323063462972641, 0.15445446968078613, 0.24965834617614746], "policy_updates": 28740, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3588.4320998480002, "contact_bce": 0.32444530725479126, "contact_force_loss": 0.03296119347214699, "terrain_level_mean": 3.03466796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9982264041900635, 0.9997775554656982, 2.9991445541381836]} {"step": 28850, "actor_lr": 2.011127606635442e-06, "archive_windows": 100000, "env_steps": 28850, "total_transitions": 118169600, "num_steps_per_env": 1, "wm_loss": 0.47478705644607544, "actor_loss": -8.794342041015625, "critic_loss": 0.024530697613954544, "reward": 0.07118290662765503, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23651240766048431, 0.1546488255262375, 0.2540612816810608], "policy_updates": 28750, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3591.971740405, "contact_bce": 0.3224230706691742, "contact_force_loss": 0.03273528814315796, "terrain_level_mean": 3.035888671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9982264041900635, 0.9997775554656982, 2.9991445541381836]} {"step": 28860, "actor_lr": 2.007479295561044e-06, "archive_windows": 100000, "env_steps": 28860, "total_transitions": 118210560, "num_steps_per_env": 1, "wm_loss": 0.47529229521751404, "actor_loss": -8.79726791381836, "critic_loss": 0.042467255145311356, "reward": 0.07097669690847397, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24321715533733368, 0.15536782145500183, 0.25388291478157043], "policy_updates": 28760, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3595.512472226, "contact_bce": 0.3277686536312103, "contact_force_loss": 0.03342512995004654, "terrain_level_mean": 3.036376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9982264041900635, 0.9997775554656982, 2.9991445541381836]} {"step": 28870, "actor_lr": 2.003862668678137e-06, "archive_windows": 100000, "env_steps": 28870, "total_transitions": 118251520, "num_steps_per_env": 1, "wm_loss": 0.49024513363838196, "actor_loss": -8.7888765335083, "critic_loss": 0.02558441273868084, "reward": 0.07100994884967804, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23974905908107758, 0.15724220871925354, 0.25349316000938416], "policy_updates": 28770, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3599.052411256, "contact_bce": 0.3306659460067749, "contact_force_loss": 0.03296121209859848, "terrain_level_mean": 3.037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9987404346466064, 0.9997775554656982, 2.9991445541381836]} {"step": 28880, "actor_lr": 2.0002777299528017e-06, "archive_windows": 100000, "env_steps": 28880, "total_transitions": 118292480, "num_steps_per_env": 1, "wm_loss": 0.4730716049671173, "actor_loss": -8.80500316619873, "critic_loss": 0.02894684672355652, "reward": 0.07110504060983658, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24231216311454773, 0.1552901417016983, 0.2530546486377716], "policy_updates": 28780, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3602.594886894, "contact_bce": 0.32039231061935425, "contact_force_loss": 0.03292948380112648, "terrain_level_mean": 3.03662109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9987404346466064, 0.9997775554656982, 2.9991445541381836]} {"step": 28890, "actor_lr": 1.9967244833163586e-06, "archive_windows": 100000, "env_steps": 28890, "total_transitions": 118333440, "num_steps_per_env": 1, "wm_loss": 0.5528945326805115, "actor_loss": -8.8104829788208, "critic_loss": 0.028018994256854057, "reward": 0.0712684765458107, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24256135523319244, 0.15345557034015656, 0.25368258357048035], "policy_updates": 28790, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3606.126024173, "contact_bce": 0.3228083848953247, "contact_force_loss": 0.03346582129597664, "terrain_level_mean": 3.036376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9987404346466064, 0.9997775554656982, 2.9991445541381836]} {"step": 28900, "actor_lr": 1.993202932665379e-06, "archive_windows": 100000, "env_steps": 28900, "total_transitions": 118374400, "num_steps_per_env": 1, "wm_loss": 0.48184213042259216, "actor_loss": -8.806364059448242, "critic_loss": 0.023027747869491577, "reward": 0.07143985480070114, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2386103719472885, 0.15191173553466797, 0.2532493770122528], "policy_updates": 28800, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3609.6544273570003, "contact_bce": 0.32357561588287354, "contact_force_loss": 0.03311111778020859, "terrain_level_mean": 3.03759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9987404346466064, 0.9997775554656982, 2.9991445541381836]} {"step": 28910, "actor_lr": 1.9897130818616804e-06, "archive_windows": 100000, "env_steps": 28910, "total_transitions": 118415360, "num_steps_per_env": 1, "wm_loss": 0.468728244304657, "actor_loss": -8.786376953125, "critic_loss": 0.026794278994202614, "reward": 0.07148758322000504, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23852787911891937, 0.15147796273231506, 0.25126147270202637], "policy_updates": 28810, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3613.186587325, "contact_bce": 0.3170056641101837, "contact_force_loss": 0.032959841191768646, "terrain_level_mean": 3.0380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9987404346466064, 0.9997775554656982, 2.9991445541381836]} {"step": 28920, "actor_lr": 1.9862549347323012e-06, "archive_windows": 100000, "env_steps": 28920, "total_transitions": 118456320, "num_steps_per_env": 1, "wm_loss": 0.47340527176856995, "actor_loss": -8.792919158935547, "critic_loss": 0.02775164321064949, "reward": 0.07088422030210495, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24205005168914795, 0.15344122052192688, 0.2551034986972809], "policy_updates": 28820, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3616.709842756, "contact_bce": 0.31920814514160156, "contact_force_loss": 0.032727714627981186, "terrain_level_mean": 3.038818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9987404346466064, 0.9997775554656982, 2.9991445541381836]} {"step": 28930, "actor_lr": 1.9828284950695313e-06, "archive_windows": 100000, "env_steps": 28930, "total_transitions": 118497280, "num_steps_per_env": 1, "wm_loss": 0.4617403447628021, "actor_loss": -8.806081771850586, "critic_loss": 0.019416749477386475, "reward": 0.0707906112074852, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24374142289161682, 0.15759211778640747, 0.2554319202899933], "policy_updates": 28830, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3620.216812868, "contact_bce": 0.32182225584983826, "contact_force_loss": 0.0322093665599823, "terrain_level_mean": 3.039306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9987404346466064, 0.9997775554656982, 2.9991445541381836]} {"step": 28940, "actor_lr": 1.979433766630882e-06, "archive_windows": 100000, "env_steps": 28940, "total_transitions": 118538240, "num_steps_per_env": 1, "wm_loss": 0.47233879566192627, "actor_loss": -8.798192977905273, "critic_loss": 0.02150922827422619, "reward": 0.0711681917309761, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24043872952461243, 0.1565771847963333, 0.2541694939136505], "policy_updates": 28840, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3623.784662, "contact_bce": 0.3261457681655884, "contact_force_loss": 0.033211980015039444, "terrain_level_mean": 3.041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9991445541381836]} {"step": 28950, "actor_lr": 1.9760707531390876e-06, "archive_windows": 100000, "env_steps": 28950, "total_transitions": 118579200, "num_steps_per_env": 1, "wm_loss": 0.4712439477443695, "actor_loss": -8.82491683959961, "critic_loss": 0.02532016672194004, "reward": 0.07127249240875244, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2424289882183075, 0.15738491714000702, 0.2540430426597595], "policy_updates": 28850, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3627.305610885, "contact_bce": 0.32442227005958557, "contact_force_loss": 0.03341900557279587, "terrain_level_mean": 3.041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9991445541381836]} {"step": 28960, "actor_lr": 1.972739458282104e-06, "archive_windows": 100000, "env_steps": 28960, "total_transitions": 118620160, "num_steps_per_env": 1, "wm_loss": 0.4796532690525055, "actor_loss": -8.790167808532715, "critic_loss": 0.02144654095172882, "reward": 0.07130544632673264, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24537985026836395, 0.15605029463768005, 0.2536955177783966], "policy_updates": 28860, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3630.8307304, "contact_bce": 0.3225424885749817, "contact_force_loss": 0.03311940282583237, "terrain_level_mean": 3.042724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9994635581970215]} {"step": 28970, "actor_lr": 1.969439885713103e-06, "archive_windows": 100000, "env_steps": 28970, "total_transitions": 118661120, "num_steps_per_env": 1, "wm_loss": 0.4875292181968689, "actor_loss": -8.82408332824707, "critic_loss": 0.021271079778671265, "reward": 0.0711015909910202, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24131153523921967, 0.15472476184368134, 0.2526529133319855], "policy_updates": 28870, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3634.363788638, "contact_bce": 0.3198681175708771, "contact_force_loss": 0.03204473853111267, "terrain_level_mean": 3.04296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9994635581970215]} {"step": 28980, "actor_lr": 1.9661720390504753e-06, "archive_windows": 100000, "env_steps": 28980, "total_transitions": 118702080, "num_steps_per_env": 1, "wm_loss": 0.4567967653274536, "actor_loss": -8.835569381713867, "critic_loss": 0.023293742910027504, "reward": 0.0714976117014885, "falls": 1, "interval_steps": 10, "velocity_mae": [0.237310990691185, 0.1566392481327057, 0.2551918625831604], "policy_updates": 28880, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3637.873111469, "contact_bce": 0.3203941285610199, "contact_force_loss": 0.03231380507349968, "terrain_level_mean": 3.04443359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9994635581970215]} {"step": 28990, "actor_lr": 1.9629359218778125e-06, "archive_windows": 100000, "env_steps": 28990, "total_transitions": 118743040, "num_steps_per_env": 1, "wm_loss": 0.4570917785167694, "actor_loss": -8.83224868774414, "critic_loss": 0.022165542468428612, "reward": 0.07099039107561111, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24193868041038513, 0.15686336159706116, 0.25725826621055603], "policy_updates": 28890, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3641.399631997, "contact_bce": 0.3228759765625, "contact_force_loss": 0.032703932374715805, "terrain_level_mean": 3.0439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9994635581970215]} {"step": 29000, "actor_lr": 1.9597315377439118e-06, "archive_windows": 100000, "env_steps": 29000, "total_transitions": 118784000, "num_steps_per_env": 1, "wm_loss": 0.509246289730072, "actor_loss": -8.85342025756836, "critic_loss": 0.027571169659495354, "reward": 0.07094796746969223, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2465743124485016, 0.15835295617580414, 0.25805288553237915], "policy_updates": 28900, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3644.914781777, "contact_bce": 0.3290919363498688, "contact_force_loss": 0.03400923311710358, "terrain_level_mean": 3.04443359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9994635581970215]} {"step": 29010, "actor_lr": 1.9565588901627788e-06, "archive_windows": 100000, "env_steps": 29010, "total_transitions": 118824960, "num_steps_per_env": 1, "wm_loss": 0.491532564163208, "actor_loss": -8.791378021240234, "critic_loss": 0.022582251578569412, "reward": 0.07134217768907547, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2446436733007431, 0.15627197921276093, 0.2574938237667084], "policy_updates": 28910, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3648.4697021, "contact_bce": 0.3192588686943054, "contact_force_loss": 0.03262367099523544, "terrain_level_mean": 3.0458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9994635581970215]} {"step": 29020, "actor_lr": 1.953417982613609e-06, "archive_windows": 100000, "env_steps": 29020, "total_transitions": 118865920, "num_steps_per_env": 1, "wm_loss": 0.4961731433868408, "actor_loss": -8.844915390014648, "critic_loss": 0.021578986197710037, "reward": 0.07127117365598679, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24309003353118896, 0.15616406500339508, 0.25709429383277893], "policy_updates": 28920, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3652.0065207000002, "contact_bce": 0.3233086168766022, "contact_force_loss": 0.03282339125871658, "terrain_level_mean": 3.046142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9991519451141357, 0.9997775554656982, 2.9994635581970215]} {"step": 29030, "actor_lr": 1.9503088185407884e-06, "archive_windows": 100000, "env_steps": 29030, "total_transitions": 118906880, "num_steps_per_env": 1, "wm_loss": 0.5410290956497192, "actor_loss": -8.768458366394043, "critic_loss": 0.020655518397688866, "reward": 0.0708223506808281, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24878790974617004, 0.15866360068321228, 0.2591550350189209], "policy_updates": 28930, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3655.547040549, "contact_bce": 0.3261135220527649, "contact_force_loss": 0.033890243619680405, "terrain_level_mean": 3.046630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29040, "actor_lr": 1.947231401353898e-06, "archive_windows": 100000, "env_steps": 29040, "total_transitions": 118947840, "num_steps_per_env": 1, "wm_loss": 0.4906201660633087, "actor_loss": -8.821378707885742, "critic_loss": 0.018373167142271996, "reward": 0.07085676491260529, "falls": 7, "interval_steps": 10, "velocity_mae": [0.250277042388916, 0.16042949259281158, 0.2600754201412201], "policy_updates": 28940, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3659.321302641, "contact_bce": 0.3208217918872833, "contact_force_loss": 0.032444097101688385, "terrain_level_mean": 3.046630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29050, "actor_lr": 1.944185734427707e-06, "archive_windows": 100000, "env_steps": 29050, "total_transitions": 118988800, "num_steps_per_env": 1, "wm_loss": 0.45463111996650696, "actor_loss": -8.783745765686035, "critic_loss": 0.027194662019610405, "reward": 0.07077135145664215, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24640291929244995, 0.15890979766845703, 0.2610413432121277], "policy_updates": 28950, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3662.831960009, "contact_bce": 0.3245374858379364, "contact_force_loss": 0.03300393000245094, "terrain_level_mean": 3.047607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29060, "actor_lr": 1.941171821102157e-06, "archive_windows": 100000, "env_steps": 29060, "total_transitions": 119029760, "num_steps_per_env": 1, "wm_loss": 0.4752337634563446, "actor_loss": -8.824213027954102, "critic_loss": 0.021874353289604187, "reward": 0.07094825059175491, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2468573898077011, 0.16294440627098083, 0.26109570264816284], "policy_updates": 28960, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3666.342708646, "contact_bce": 0.3244064748287201, "contact_force_loss": 0.03319810330867767, "terrain_level_mean": 3.048583984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29070, "actor_lr": 1.938189664682379e-06, "archive_windows": 100000, "env_steps": 29070, "total_transitions": 119070720, "num_steps_per_env": 1, "wm_loss": 0.4734002947807312, "actor_loss": -8.810169219970703, "critic_loss": 0.016611529514193535, "reward": 0.07080017030239105, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24796132743358612, 0.16283832490444183, 0.26398026943206787], "policy_updates": 28970, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3669.851679273, "contact_bce": 0.3247804045677185, "contact_force_loss": 0.03233589604496956, "terrain_level_mean": 3.04931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29080, "actor_lr": 1.935239268438673e-06, "archive_windows": 100000, "env_steps": 29080, "total_transitions": 119111680, "num_steps_per_env": 1, "wm_loss": 0.503781795501709, "actor_loss": -8.788556098937988, "critic_loss": 0.02775392308831215, "reward": 0.07056540250778198, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2502155303955078, 0.16352076828479767, 0.26501479744911194], "policy_updates": 28980, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3673.378071564, "contact_bce": 0.3216231167316437, "contact_force_loss": 0.03311162814497948, "terrain_level_mean": 3.04931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29090, "actor_lr": 1.932320635606504e-06, "archive_windows": 100000, "env_steps": 29090, "total_transitions": 119152640, "num_steps_per_env": 1, "wm_loss": 0.5049230456352234, "actor_loss": -8.830634117126465, "critic_loss": 0.026534730568528175, "reward": 0.0705891028046608, "falls": 9, "interval_steps": 10, "velocity_mae": [0.25376608967781067, 0.160832941532135, 0.2580779492855072], "policy_updates": 28990, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3676.9068974790002, "contact_bce": 0.32287317514419556, "contact_force_loss": 0.032697893679142, "terrain_level_mean": 3.048583984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29100, "actor_lr": 1.9294337693865173e-06, "archive_windows": 100000, "env_steps": 29100, "total_transitions": 119193600, "num_steps_per_env": 1, "wm_loss": 0.46982279419898987, "actor_loss": -8.785436630249023, "critic_loss": 0.02158832736313343, "reward": 0.07127578556537628, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24959002435207367, 0.15764839947223663, 0.25952786207199097], "policy_updates": 29000, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3680.434356445, "contact_bce": 0.3212966322898865, "contact_force_loss": 0.03289639949798584, "terrain_level_mean": 3.0478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29110, "actor_lr": 1.926578672944511e-06, "archive_windows": 100000, "env_steps": 29110, "total_transitions": 119234560, "num_steps_per_env": 1, "wm_loss": 0.4964313209056854, "actor_loss": -8.838325500488281, "critic_loss": 0.02127174101769924, "reward": 0.07181007415056229, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24327312409877777, 0.15645436942577362, 0.25631317496299744], "policy_updates": 29010, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3683.961804266, "contact_bce": 0.32518771290779114, "contact_force_loss": 0.032739296555519104, "terrain_level_mean": 3.04833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29120, "actor_lr": 1.923755349411449e-06, "archive_windows": 100000, "env_steps": 29120, "total_transitions": 119275520, "num_steps_per_env": 1, "wm_loss": 0.4674682915210724, "actor_loss": -8.826539993286133, "critic_loss": 0.018910503014922142, "reward": 0.0712667927145958, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24686861038208008, 0.15976323187351227, 0.2576572895050049], "policy_updates": 29020, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3687.497725907, "contact_bce": 0.31915175914764404, "contact_force_loss": 0.03168734908103943, "terrain_level_mean": 3.049072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29130, "actor_lr": 1.920963801883458e-06, "archive_windows": 100000, "env_steps": 29130, "total_transitions": 119316480, "num_steps_per_env": 1, "wm_loss": 0.4830879867076874, "actor_loss": -8.872729301452637, "critic_loss": 0.02445807494223118, "reward": 0.07073242962360382, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2482367306947708, 0.16143487393856049, 0.2631230652332306], "policy_updates": 29030, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3691.101489871, "contact_bce": 0.3223239481449127, "contact_force_loss": 0.03309865668416023, "terrain_level_mean": 3.047607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9991519451141357, 0.9991205930709839, 2.9994635581970215]} {"step": 29140, "actor_lr": 1.918204033421803e-06, "archive_windows": 100000, "env_steps": 29140, "total_transitions": 119357440, "num_steps_per_env": 1, "wm_loss": 0.4789849817752838, "actor_loss": -8.824751853942871, "critic_loss": 0.027471287176012993, "reward": 0.0713476911187172, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24486422538757324, 0.16146431863307953, 0.2604496479034424], "policy_updates": 29040, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3694.787308561, "contact_bce": 0.322137713432312, "contact_force_loss": 0.032460421323776245, "terrain_level_mean": 3.048095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9982819557189941, 0.9991205930709839, 2.9994635581970215]} {"step": 29150, "actor_lr": 1.915476047052913e-06, "archive_windows": 100000, "env_steps": 29150, "total_transitions": 119398400, "num_steps_per_env": 1, "wm_loss": 0.4991912543773651, "actor_loss": -8.779781341552734, "critic_loss": 0.01936967484652996, "reward": 0.0712280198931694, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24225780367851257, 0.16286267340183258, 0.2600167989730835], "policy_updates": 29050, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3698.314498447, "contact_bce": 0.3245134651660919, "contact_force_loss": 0.033110301941633224, "terrain_level_mean": 3.04833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9994635581970215]} {"step": 29160, "actor_lr": 1.912779845768362e-06, "archive_windows": 100000, "env_steps": 29160, "total_transitions": 119439360, "num_steps_per_env": 1, "wm_loss": 0.4668862223625183, "actor_loss": -8.78519344329834, "critic_loss": 0.028268415480852127, "reward": 0.07132529467344284, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2440258264541626, 0.16065652668476105, 0.2580394446849823], "policy_updates": 29060, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3701.8432714230003, "contact_bce": 0.3226475417613983, "contact_force_loss": 0.03217567875981331, "terrain_level_mean": 3.04736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9994635581970215]} {"step": 29170, "actor_lr": 1.910115432524863e-06, "archive_windows": 100000, "env_steps": 29170, "total_transitions": 119480320, "num_steps_per_env": 1, "wm_loss": 0.47754141688346863, "actor_loss": -8.793895721435547, "critic_loss": 0.020674491301178932, "reward": 0.07168985903263092, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24294456839561462, 0.1630024015903473, 0.2562396824359894], "policy_updates": 29070, "skipped_updates": 0, "invalid_env_resets": 19, "elapsed_s": 3705.373172618, "contact_bce": 0.32046619057655334, "contact_force_loss": 0.032115064561367035, "terrain_level_mean": 3.0478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9994635581970215]} RECOVERY reset 1 invalid environments; first IDs=[2502] {"step": 29180, "actor_lr": 1.90748281024427e-06, "archive_windows": 100000, "env_steps": 29180, "total_transitions": 119521280, "num_steps_per_env": 1, "wm_loss": 0.48424169421195984, "actor_loss": -8.825260162353516, "critic_loss": 0.027712160721421242, "reward": 0.07152918726205826, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24339352548122406, 0.16250349581241608, 0.2580699920654297], "policy_updates": 29080, "skipped_updates": 0, "invalid_env_resets": 20, "elapsed_s": 3708.930412838, "contact_bce": 0.32359787821769714, "contact_force_loss": 0.03404676541686058, "terrain_level_mean": 3.047607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9994635581970215]} {"step": 29190, "actor_lr": 1.9048819818135774e-06, "archive_windows": 100000, "env_steps": 29190, "total_transitions": 119562240, "num_steps_per_env": 1, "wm_loss": 0.4912397563457489, "actor_loss": -8.866236686706543, "critic_loss": 0.021118924021720886, "reward": 0.07136792689561844, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24808400869369507, 0.16097089648246765, 0.2545730173587799], "policy_updates": 29090, "skipped_updates": 0, "invalid_env_resets": 20, "elapsed_s": 3712.461829061, "contact_bce": 0.3307495713233948, "contact_force_loss": 0.033576712012290955, "terrain_level_mean": 3.047607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9994635581970215]} RECOVERY reset 1 invalid environments; first IDs=[893] {"step": 29200, "actor_lr": 1.902312950084913e-06, "archive_windows": 100000, "env_steps": 29200, "total_transitions": 119603200, "num_steps_per_env": 1, "wm_loss": 0.5081523060798645, "actor_loss": -8.773279190063477, "critic_loss": 0.0239176657050848, "reward": 0.07174364477396011, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24467994272708893, 0.15943345427513123, 0.2534995377063751], "policy_updates": 29100, "skipped_updates": 0, "invalid_env_resets": 21, "elapsed_s": 3716.003687089, "contact_bce": 0.32286301255226135, "contact_force_loss": 0.03313412889838219, "terrain_level_mean": 3.04833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9994635581970215]} {"step": 29210, "actor_lr": 1.8997757178755349e-06, "archive_windows": 100000, "env_steps": 29210, "total_transitions": 119644160, "num_steps_per_env": 1, "wm_loss": 0.48565489053726196, "actor_loss": -8.761119842529297, "critic_loss": 0.023639490827918053, "reward": 0.07195142656564713, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2435097098350525, 0.15791304409503937, 0.25470611453056335], "policy_updates": 29110, "skipped_updates": 0, "invalid_env_resets": 21, "elapsed_s": 3719.545288928, "contact_bce": 0.3211023807525635, "contact_force_loss": 0.032897643744945526, "terrain_level_mean": 3.050048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9986720085144043]} {"step": 29220, "actor_lr": 1.897270287967829e-06, "archive_windows": 100000, "env_steps": 29220, "total_transitions": 119685120, "num_steps_per_env": 1, "wm_loss": 0.4741326570510864, "actor_loss": -8.79074764251709, "critic_loss": 0.028203709051012993, "reward": 0.07130013406276703, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24682587385177612, 0.16196106374263763, 0.2612406313419342], "policy_updates": 29120, "skipped_updates": 0, "invalid_env_resets": 21, "elapsed_s": 3723.076668652, "contact_bce": 0.31982481479644775, "contact_force_loss": 0.03313524276018143, "terrain_level_mean": 3.05078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9986720085144043]} {"step": 29230, "actor_lr": 1.8947966631093049e-06, "archive_windows": 100000, "env_steps": 29230, "total_transitions": 119726080, "num_steps_per_env": 1, "wm_loss": 0.48295754194259644, "actor_loss": -8.824308395385742, "critic_loss": 0.021378789097070694, "reward": 0.07115113735198975, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24906860291957855, 0.16300971806049347, 0.258000910282135], "policy_updates": 29130, "skipped_updates": 0, "invalid_env_resets": 21, "elapsed_s": 3726.622045129, "contact_bce": 0.3257431387901306, "contact_force_loss": 0.03330226242542267, "terrain_level_mean": 3.051025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9986720085144043]} {"step": 29240, "actor_lr": 1.8923548460125996e-06, "archive_windows": 100000, "env_steps": 29240, "total_transitions": 119767040, "num_steps_per_env": 1, "wm_loss": 0.45732057094573975, "actor_loss": -8.763757705688477, "critic_loss": 0.023252395913004875, "reward": 0.0716785117983818, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2428620457649231, 0.1588677316904068, 0.2562791407108307], "policy_updates": 29140, "skipped_updates": 0, "invalid_env_resets": 21, "elapsed_s": 3730.164060433, "contact_bce": 0.3205888867378235, "contact_force_loss": 0.0325830839574337, "terrain_level_mean": 3.049560546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9986720085144043]} {"step": 29250, "actor_lr": 1.8899448393554614e-06, "archive_windows": 100000, "env_steps": 29250, "total_transitions": 119808000, "num_steps_per_env": 1, "wm_loss": 0.47484225034713745, "actor_loss": -8.811120986938477, "critic_loss": 0.023054588586091995, "reward": 0.07188206911087036, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24296808242797852, 0.15799136459827423, 0.25446322560310364], "policy_updates": 29150, "skipped_updates": 0, "invalid_env_resets": 21, "elapsed_s": 3733.716638011, "contact_bce": 0.3234408497810364, "contact_force_loss": 0.03340285271406174, "terrain_level_mean": 3.050048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9986720085144043]} {"step": 29260, "actor_lr": 1.887566645780759e-06, "archive_windows": 100000, "env_steps": 29260, "total_transitions": 119848960, "num_steps_per_env": 1, "wm_loss": 0.4834437370300293, "actor_loss": -8.785515785217285, "critic_loss": 0.023811595514416695, "reward": 0.07155134528875351, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24537014961242676, 0.15605051815509796, 0.2519700825214386], "policy_updates": 29160, "skipped_updates": 0, "invalid_env_resets": 21, "elapsed_s": 3737.427899806, "contact_bce": 0.3200571537017822, "contact_force_loss": 0.032467909157276154, "terrain_level_mean": 3.0498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9986720085144043]} RECOVERY reset 1 invalid environments; first IDs=[1495] {"step": 29270, "actor_lr": 1.885220267896473e-06, "archive_windows": 100000, "env_steps": 29270, "total_transitions": 119889920, "num_steps_per_env": 1, "wm_loss": 0.4892057180404663, "actor_loss": -8.85389518737793, "critic_loss": 0.018172917887568474, "reward": 0.07191332429647446, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24514508247375488, 0.15693621337413788, 0.25336992740631104], "policy_updates": 29170, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3741.044148024, "contact_bce": 0.3258107304573059, "contact_force_loss": 0.03353414312005043, "terrain_level_mean": 3.050537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.998833417892456, 0.9991205930709839, 2.9986720085144043]} {"step": 29280, "actor_lr": 1.8829057082756973e-06, "archive_windows": 100000, "env_steps": 29280, "total_transitions": 119930880, "num_steps_per_env": 1, "wm_loss": 0.4861548840999603, "actor_loss": -8.804195404052734, "critic_loss": 0.01950899511575699, "reward": 0.07113056629896164, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24831834435462952, 0.1589430421590805, 0.25615060329437256], "policy_updates": 29180, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3744.688574589, "contact_bce": 0.32075268030166626, "contact_force_loss": 0.03261863812804222, "terrain_level_mean": 3.05078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.998833417892456, 0.9991564750671387, 2.9986720085144043]} {"step": 29290, "actor_lr": 1.8806229694566251e-06, "archive_windows": 100000, "env_steps": 29290, "total_transitions": 119971840, "num_steps_per_env": 1, "wm_loss": 0.4885329604148865, "actor_loss": -8.852861404418945, "critic_loss": 0.017854634672403336, "reward": 0.07073857635259628, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24573612213134766, 0.1616404950618744, 0.2614690661430359], "policy_updates": 29190, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3748.353424574, "contact_bce": 0.32022735476493835, "contact_force_loss": 0.03262254223227501, "terrain_level_mean": 3.05029296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.998833417892456, 0.9995908141136169, 2.9986720085144043]} {"step": 29300, "actor_lr": 1.8783720539425633e-06, "archive_windows": 100000, "env_steps": 29300, "total_transitions": 120012800, "num_steps_per_env": 1, "wm_loss": 0.4771849811077118, "actor_loss": -8.832091331481934, "critic_loss": 0.02460663951933384, "reward": 0.07142826169729233, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24088215827941895, 0.15932485461235046, 0.2572506368160248], "policy_updates": 29200, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3751.959892009, "contact_bce": 0.3212237060070038, "contact_force_loss": 0.032749418169260025, "terrain_level_mean": 3.04931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.998833417892456, 0.9995908141136169, 2.9986720085144043]} {"step": 29310, "actor_lr": 1.8761529642019174e-06, "archive_windows": 100000, "env_steps": 29310, "total_transitions": 120053760, "num_steps_per_env": 1, "wm_loss": 0.5077382922172546, "actor_loss": -8.832315444946289, "critic_loss": 0.027078935876488686, "reward": 0.07090012729167938, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2501625716686249, 0.15984241664409637, 0.25991278886795044], "policy_updates": 29210, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3755.586356123, "contact_bce": 0.321686327457428, "contact_force_loss": 0.033046696335077286, "terrain_level_mean": 3.04931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.998833417892456, 0.9995908141136169, 2.9958109855651855]} {"step": 29320, "actor_lr": 1.8739657026681875e-06, "archive_windows": 100000, "env_steps": 29320, "total_transitions": 120094720, "num_steps_per_env": 1, "wm_loss": 0.4740205407142639, "actor_loss": -8.790061950683594, "critic_loss": 0.0249757319688797, "reward": 0.07103116065263748, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25326016545295715, 0.160086989402771, 0.26259729266166687], "policy_updates": 29220, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3759.1212680520002, "contact_bce": 0.3236421048641205, "contact_force_loss": 0.03278917074203491, "terrain_level_mean": 3.04931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.998833417892456, 0.9995908141136169, 2.9958109855651855]} {"step": 29330, "actor_lr": 1.871810271739975e-06, "archive_windows": 100000, "env_steps": 29330, "total_transitions": 120135680, "num_steps_per_env": 1, "wm_loss": 0.4929353594779968, "actor_loss": -8.86767864227295, "critic_loss": 0.02456057444214821, "reward": 0.07138852030038834, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2490922212600708, 0.1591411978006363, 0.26110297441482544], "policy_updates": 29230, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3762.649126993, "contact_bce": 0.32828855514526367, "contact_force_loss": 0.033296991139650345, "terrain_level_mean": 3.050048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.998477816581726, 0.9995908141136169, 2.9958109855651855]} {"step": 29340, "actor_lr": 1.8696866737809776e-06, "archive_windows": 100000, "env_steps": 29340, "total_transitions": 120176640, "num_steps_per_env": 1, "wm_loss": 0.48859792947769165, "actor_loss": -8.782772064208984, "critic_loss": 0.025780176743865013, "reward": 0.07148503512144089, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2521231472492218, 0.16182954609394073, 0.2590414881706238], "policy_updates": 29240, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3766.1849938600003, "contact_bce": 0.3277433216571808, "contact_force_loss": 0.03365902602672577, "terrain_level_mean": 3.051025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.998477816581726, 0.9995908141136169, 2.9958109855651855]} {"step": 29350, "actor_lr": 1.8675949111199799e-06, "archive_windows": 100000, "env_steps": 29350, "total_transitions": 120217600, "num_steps_per_env": 1, "wm_loss": 0.4831300675868988, "actor_loss": -8.799097061157227, "critic_loss": 0.018285809084773064, "reward": 0.07149723917245865, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2491752803325653, 0.16032002866268158, 0.25383687019348145], "policy_updates": 29250, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3769.722051706, "contact_bce": 0.3230167031288147, "contact_force_loss": 0.03298116847872734, "terrain_level_mean": 3.051025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.998477816581726, 0.9995908141136169, 2.9958109855651855]} {"step": 29360, "actor_lr": 1.8655349860508523e-06, "archive_windows": 100000, "env_steps": 29360, "total_transitions": 120258560, "num_steps_per_env": 1, "wm_loss": 0.5294986367225647, "actor_loss": -8.77904987335205, "critic_loss": 0.02619720809161663, "reward": 0.07197865098714828, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24064089357852936, 0.15959404408931732, 0.25399497151374817], "policy_updates": 29260, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3773.287651151, "contact_bce": 0.3200353682041168, "contact_force_loss": 0.03350630775094032, "terrain_level_mean": 3.05126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.998477816581726, 0.9995908141136169, 2.9958109855651855]} {"step": 29370, "actor_lr": 1.8635069008325606e-06, "archive_windows": 100000, "env_steps": 29370, "total_transitions": 120299520, "num_steps_per_env": 1, "wm_loss": 0.4921766519546509, "actor_loss": -8.818380355834961, "critic_loss": 0.01882590912282467, "reward": 0.07193668931722641, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23906677961349487, 0.15603980422019958, 0.2518501877784729], "policy_updates": 29270, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3776.812605211, "contact_bce": 0.328164666891098, "contact_force_loss": 0.03352583944797516, "terrain_level_mean": 3.05078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.998477816581726, 0.9995908141136169, 2.9958109855651855]} {"step": 29380, "actor_lr": 1.861510657689143e-06, "archive_windows": 100000, "env_steps": 29380, "total_transitions": 120340480, "num_steps_per_env": 1, "wm_loss": 0.4688335657119751, "actor_loss": -8.792159080505371, "critic_loss": 0.024397743865847588, "reward": 0.07170942425727844, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23800097405910492, 0.15622834861278534, 0.2602190375328064], "policy_updates": 29280, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3780.3350947910003, "contact_bce": 0.32248932123184204, "contact_force_loss": 0.033214982599020004, "terrain_level_mean": 3.050537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29390, "actor_lr": 1.8595462588097288e-06, "archive_windows": 100000, "env_steps": 29390, "total_transitions": 120381440, "num_steps_per_env": 1, "wm_loss": 0.46769043803215027, "actor_loss": -8.796844482421875, "critic_loss": 0.025643274188041687, "reward": 0.07143449038267136, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2413564771413803, 0.15728750824928284, 0.2588602602481842], "policy_updates": 29290, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3783.867437872, "contact_bce": 0.3261110782623291, "contact_force_loss": 0.033722974359989166, "terrain_level_mean": 3.05029296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29400, "actor_lr": 1.8576137063485233e-06, "archive_windows": 100000, "env_steps": 29400, "total_transitions": 120422400, "num_steps_per_env": 1, "wm_loss": 0.48679396510124207, "actor_loss": -8.770790100097656, "critic_loss": 0.026382988318800926, "reward": 0.07139167934656143, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2391941398382187, 0.1580347865819931, 0.2573413550853729], "policy_updates": 29300, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3787.413505559, "contact_bce": 0.3223394751548767, "contact_force_loss": 0.0337512344121933, "terrain_level_mean": 3.05126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29410, "actor_lr": 1.8557130024248046e-06, "archive_windows": 100000, "env_steps": 29410, "total_transitions": 120463360, "num_steps_per_env": 1, "wm_loss": 0.49780675768852234, "actor_loss": -8.808173179626465, "critic_loss": 0.017245734110474586, "reward": 0.07134523242712021, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2358420044183731, 0.16026879847049713, 0.25745344161987305], "policy_updates": 29310, "skipped_updates": 0, "invalid_env_resets": 22, "elapsed_s": 3791.037741692, "contact_bce": 0.3252238929271698, "contact_force_loss": 0.0336138941347599, "terrain_level_mean": 3.051513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} RECOVERY reset 1 invalid environments; first IDs=[2762] {"step": 29420, "actor_lr": 1.8538441491229251e-06, "archive_windows": 100000, "env_steps": 29420, "total_transitions": 120504320, "num_steps_per_env": 1, "wm_loss": 0.4727795124053955, "actor_loss": -8.821409225463867, "critic_loss": 0.029405200853943825, "reward": 0.0713503360748291, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23596537113189697, 0.15984082221984863, 0.2584713399410248], "policy_updates": 29320, "skipped_updates": 0, "invalid_env_resets": 23, "elapsed_s": 3794.586899682, "contact_bce": 0.3229752779006958, "contact_force_loss": 0.03345143049955368, "terrain_level_mean": 3.05126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29430, "actor_lr": 1.8520071484923177e-06, "archive_windows": 100000, "env_steps": 29430, "total_transitions": 120545280, "num_steps_per_env": 1, "wm_loss": 0.4934695065021515, "actor_loss": -8.766336441040039, "critic_loss": 0.025646287947893143, "reward": 0.0710388645529747, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2369937002658844, 0.1602211445569992, 0.26271310448646545], "policy_updates": 29330, "skipped_updates": 0, "invalid_env_resets": 23, "elapsed_s": 3798.1369933260003, "contact_bce": 0.32107478380203247, "contact_force_loss": 0.03236538916826248, "terrain_level_mean": 3.0517578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29440, "actor_lr": 1.8502020025474767e-06, "archive_windows": 100000, "env_steps": 29440, "total_transitions": 120586240, "num_steps_per_env": 1, "wm_loss": 0.5030298829078674, "actor_loss": -8.799039840698242, "critic_loss": 0.028407800942659378, "reward": 0.07090570777654648, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23677189648151398, 0.16052068769931793, 0.26379239559173584], "policy_updates": 29340, "skipped_updates": 0, "invalid_env_resets": 23, "elapsed_s": 3801.687112747, "contact_bce": 0.32019245624542236, "contact_force_loss": 0.03302357345819473, "terrain_level_mean": 3.050537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29450, "actor_lr": 1.8484287132679631e-06, "archive_windows": 100000, "env_steps": 29450, "total_transitions": 120627200, "num_steps_per_env": 1, "wm_loss": 0.4690958261489868, "actor_loss": -8.825177192687988, "critic_loss": 0.01849229820072651, "reward": 0.07137312740087509, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23697161674499512, 0.15911611914634705, 0.26066774129867554], "policy_updates": 29350, "skipped_updates": 0, "invalid_env_resets": 23, "elapsed_s": 3805.1949043120003, "contact_bce": 0.31902122497558594, "contact_force_loss": 0.033103033900260925, "terrain_level_mean": 3.049560546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29460, "actor_lr": 1.8466872825984098e-06, "archive_windows": 100000, "env_steps": 29460, "total_transitions": 120668160, "num_steps_per_env": 1, "wm_loss": 0.500296413898468, "actor_loss": -8.811805725097656, "critic_loss": 0.022055482491850853, "reward": 0.07120802253484726, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2412586510181427, 0.15990391373634338, 0.2588599920272827], "policy_updates": 29360, "skipped_updates": 0, "invalid_env_resets": 23, "elapsed_s": 3808.7263025400002, "contact_bce": 0.32498762011528015, "contact_force_loss": 0.03396904096007347, "terrain_level_mean": 3.048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9958109855651855]} {"step": 29470, "actor_lr": 1.8449777124485058e-06, "archive_windows": 100000, "env_steps": 29470, "total_transitions": 120709120, "num_steps_per_env": 1, "wm_loss": 0.4892573356628418, "actor_loss": -8.840648651123047, "critic_loss": 0.018584920093417168, "reward": 0.07088325172662735, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24093623459339142, 0.15899257361888885, 0.2588958144187927], "policy_updates": 29370, "skipped_updates": 0, "invalid_env_resets": 23, "elapsed_s": 3812.250284871, "contact_bce": 0.32327911257743835, "contact_force_loss": 0.03283725678920746, "terrain_level_mean": 3.0478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.995706796646118]} RECOVERY reset 1 invalid environments; first IDs=[1499] {"step": 29480, "actor_lr": 1.843300004693007e-06, "archive_windows": 100000, "env_steps": 29480, "total_transitions": 120750080, "num_steps_per_env": 1, "wm_loss": 0.5229498744010925, "actor_loss": -8.835865020751953, "critic_loss": 0.029397517442703247, "reward": 0.07124263048171997, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23750947415828705, 0.1584208607673645, 0.2559313476085663], "policy_updates": 29380, "skipped_updates": 0, "invalid_env_resets": 24, "elapsed_s": 3815.7873106380002, "contact_bce": 0.32633835077285767, "contact_force_loss": 0.033744070678949356, "terrain_level_mean": 3.046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.995706796646118]} RECOVERY reset 1 invalid environments; first IDs=[2217] {"step": 29490, "actor_lr": 1.841654161171724e-06, "archive_windows": 100000, "env_steps": 29490, "total_transitions": 120791040, "num_steps_per_env": 1, "wm_loss": 0.5041620135307312, "actor_loss": -8.7727632522583, "critic_loss": 0.019503826275467873, "reward": 0.07102234661579132, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23280945420265198, 0.1591968983411789, 0.258992463350296], "policy_updates": 29390, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3819.327752356, "contact_bce": 0.3232938349246979, "contact_force_loss": 0.03313123434782028, "terrain_level_mean": 3.046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9991116523742676]} {"step": 29500, "actor_lr": 1.840040183689525e-06, "archive_windows": 100000, "env_steps": 29500, "total_transitions": 120832000, "num_steps_per_env": 1, "wm_loss": 0.48406314849853516, "actor_loss": -8.795306205749512, "critic_loss": 0.030189422890543938, "reward": 0.07079004496335983, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23241707682609558, 0.15857359766960144, 0.25721514225006104], "policy_updates": 29400, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3822.836703738, "contact_bce": 0.3224497139453888, "contact_force_loss": 0.03339662775397301, "terrain_level_mean": 3.04736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.999758243560791, 0.9995908141136169, 2.9991116523742676]} {"step": 29510, "actor_lr": 1.83845807401634e-06, "archive_windows": 100000, "env_steps": 29510, "total_transitions": 120872960, "num_steps_per_env": 1, "wm_loss": 0.4804859161376953, "actor_loss": -8.794275283813477, "critic_loss": 0.0261112991720438, "reward": 0.07119324058294296, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23707173764705658, 0.15594303607940674, 0.2546241581439972], "policy_updates": 29410, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3826.403626714, "contact_bce": 0.321201354265213, "contact_force_loss": 0.03337820991873741, "terrain_level_mean": 3.048095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.999758243560791, 0.9997456073760986, 2.9991116523742676]} {"step": 29520, "actor_lr": 1.8369078338871394e-06, "archive_windows": 100000, "env_steps": 29520, "total_transitions": 120913920, "num_steps_per_env": 1, "wm_loss": 0.5037111043930054, "actor_loss": -8.785569190979004, "critic_loss": 0.025323664769530296, "reward": 0.07106765359640121, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2406632900238037, 0.1544986069202423, 0.25398004055023193], "policy_updates": 29420, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3829.937156432, "contact_bce": 0.3255251944065094, "contact_force_loss": 0.03285800665616989, "terrain_level_mean": 3.04736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.999758243560791, 0.9997456073760986, 2.9991116523742676]} {"step": 29530, "actor_lr": 1.835389465001953e-06, "archive_windows": 100000, "env_steps": 29530, "total_transitions": 120954880, "num_steps_per_env": 1, "wm_loss": 0.49968624114990234, "actor_loss": -8.75575065612793, "critic_loss": 0.04374571517109871, "reward": 0.07091977447271347, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2411959320306778, 0.1520315706729889, 0.25707918405532837], "policy_updates": 29430, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3833.724229125, "contact_bce": 0.31915244460105896, "contact_force_loss": 0.032976776361465454, "terrain_level_mean": 3.04638671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35888671875, "command_abs_max": [1.999758243560791, 0.9997456073760986, 2.9991116523742676]} {"step": 29540, "actor_lr": 1.8339029690258608e-06, "archive_windows": 100000, "env_steps": 29540, "total_transitions": 120995840, "num_steps_per_env": 1, "wm_loss": 0.4901104271411896, "actor_loss": -8.796813011169434, "critic_loss": 0.035648323595523834, "reward": 0.07099118083715439, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2406197339296341, 0.15190747380256653, 0.2582628130912781], "policy_updates": 29440, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3837.248543051, "contact_bce": 0.32121583819389343, "contact_force_loss": 0.03301401808857918, "terrain_level_mean": 3.045654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361572265625, "command_abs_max": [1.999758243560791, 0.9997456073760986, 2.9991116523742676]} {"step": 29550, "actor_lr": 1.8324483475889881e-06, "archive_windows": 100000, "env_steps": 29550, "total_transitions": 121036800, "num_steps_per_env": 1, "wm_loss": 0.48163318634033203, "actor_loss": -8.782978057861328, "critic_loss": 0.024539712816476822, "reward": 0.07072988897562027, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2427341192960739, 0.15366236865520477, 0.2578482925891876], "policy_updates": 29450, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3840.785917083, "contact_bce": 0.32377931475639343, "contact_force_loss": 0.03337983787059784, "terrain_level_mean": 3.04638671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.999758243560791, 0.9997456073760986, 2.9991116523742676]} {"step": 29560, "actor_lr": 1.8310256022865017e-06, "archive_windows": 100000, "env_steps": 29560, "total_transitions": 121077760, "num_steps_per_env": 1, "wm_loss": 0.4765816330909729, "actor_loss": -8.833866119384766, "critic_loss": 0.02690240740776062, "reward": 0.07090049237012863, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2444695085287094, 0.15622210502624512, 0.25744661688804626], "policy_updates": 29460, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3844.460570213, "contact_bce": 0.3231920897960663, "contact_force_loss": 0.03314247727394104, "terrain_level_mean": 3.046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999758243560791, 0.9997456073760986, 2.9991116523742676]} {"step": 29570, "actor_lr": 1.8296347346786208e-06, "archive_windows": 100000, "env_steps": 29570, "total_transitions": 121118720, "num_steps_per_env": 1, "wm_loss": 0.4741293489933014, "actor_loss": -8.824666976928711, "critic_loss": 0.017758039757609367, "reward": 0.07026859372854233, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24538448452949524, 0.1570022851228714, 0.2587251365184784], "policy_updates": 29470, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3848.756097755, "contact_bce": 0.3244677484035492, "contact_force_loss": 0.03336262330412865, "terrain_level_mean": 3.047119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.999758243560791, 0.9997456073760986, 2.9991116523742676]} {"step": 29580, "actor_lr": 1.8282757462906007e-06, "archive_windows": 100000, "env_steps": 29580, "total_transitions": 121159680, "num_steps_per_env": 1, "wm_loss": 0.513917863368988, "actor_loss": -8.787643432617188, "critic_loss": 0.026185914874076843, "reward": 0.07075781375169754, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24644634127616882, 0.15563291311264038, 0.2567903995513916], "policy_updates": 29480, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3853.027752784, "contact_bce": 0.3232041895389557, "contact_force_loss": 0.03400612249970436, "terrain_level_mean": 3.047119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9990215301513672, 0.9997456073760986, 2.9991116523742676]} {"step": 29590, "actor_lr": 1.8269486386127382e-06, "archive_windows": 100000, "env_steps": 29590, "total_transitions": 121200640, "num_steps_per_env": 1, "wm_loss": 0.5080949664115906, "actor_loss": -8.811019897460938, "critic_loss": 0.022340886294841766, "reward": 0.07122313976287842, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24123257398605347, 0.15456104278564453, 0.2579796016216278], "policy_updates": 29490, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3857.31456207, "contact_bce": 0.32198819518089294, "contact_force_loss": 0.033191606402397156, "terrain_level_mean": 3.046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9990215301513672, 0.9997456073760986, 2.9991116523742676]} {"step": 29600, "actor_lr": 1.825653413100369e-06, "archive_windows": 100000, "env_steps": 29600, "total_transitions": 121241600, "num_steps_per_env": 1, "wm_loss": 0.49483567476272583, "actor_loss": -8.776847839355469, "critic_loss": 0.026094594970345497, "reward": 0.07126971334218979, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23985542356967926, 0.1541476547718048, 0.2572229504585266], "policy_updates": 29500, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3861.57779716, "contact_bce": 0.32627594470977783, "contact_force_loss": 0.03390786424279213, "terrain_level_mean": 3.046630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9990215301513672, 0.9997456073760986, 2.9991116523742676]} {"step": 29610, "actor_lr": 1.8243900711738695e-06, "archive_windows": 100000, "env_steps": 29610, "total_transitions": 121282560, "num_steps_per_env": 1, "wm_loss": 0.4649925231933594, "actor_loss": -8.832659721374512, "critic_loss": 0.021709801629185677, "reward": 0.0715031549334526, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2374948114156723, 0.15468049049377441, 0.25344765186309814], "policy_updates": 29510, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3865.893420251, "contact_bce": 0.31993094086647034, "contact_force_loss": 0.03264173865318298, "terrain_level_mean": 3.04833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9990215301513672, 0.9997456073760986, 2.9991116523742676]} {"step": 29620, "actor_lr": 1.8231586142186463e-06, "archive_windows": 100000, "env_steps": 29620, "total_transitions": 121323520, "num_steps_per_env": 1, "wm_loss": 0.5050445795059204, "actor_loss": -8.812165260314941, "critic_loss": 0.019653333351016045, "reward": 0.07123857736587524, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23621855676174164, 0.15329718589782715, 0.257802277803421], "policy_updates": 29520, "skipped_updates": 0, "invalid_env_resets": 25, "elapsed_s": 3870.2364337, "contact_bce": 0.32833409309387207, "contact_force_loss": 0.033134911209344864, "terrain_level_mean": 3.047607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9986906051635742, 0.9997456073760986, 2.9991116523742676]} RECOVERY reset 1 invalid environments; first IDs=[1542] {"step": 29630, "actor_lr": 1.8219590435851423e-06, "archive_windows": 100000, "env_steps": 29630, "total_transitions": 121364480, "num_steps_per_env": 1, "wm_loss": 0.4487038850784302, "actor_loss": -8.727588653564453, "critic_loss": 0.030025649815797806, "reward": 0.07126572728157043, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23616929352283478, 0.15572211146354675, 0.25679996609687805], "policy_updates": 29530, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3874.5339666990003, "contact_bce": 0.31732040643692017, "contact_force_loss": 0.03214398771524429, "terrain_level_mean": 3.0478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29640, "actor_lr": 1.820791360588835e-06, "archive_windows": 100000, "env_steps": 29640, "total_transitions": 121405440, "num_steps_per_env": 1, "wm_loss": 0.4816865026950836, "actor_loss": -8.834474563598633, "critic_loss": 0.02043229155242443, "reward": 0.07059746235609055, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23833249509334564, 0.15976157784461975, 0.25998595356941223], "policy_updates": 29540, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3878.875146749, "contact_bce": 0.3246462047100067, "contact_force_loss": 0.03293020278215408, "terrain_level_mean": 3.04736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29650, "actor_lr": 1.819655566510235e-06, "archive_windows": 100000, "env_steps": 29650, "total_transitions": 121446400, "num_steps_per_env": 1, "wm_loss": 0.49668213725090027, "actor_loss": -8.769698143005371, "critic_loss": 0.033791542053222656, "reward": 0.07031857222318649, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24393333494663239, 0.15688566863536835, 0.264912873506546], "policy_updates": 29550, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3883.258836091, "contact_bce": 0.32393771409988403, "contact_force_loss": 0.033018313348293304, "terrain_level_mean": 3.0478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29660, "actor_lr": 1.8185516625948734e-06, "archive_windows": 100000, "env_steps": 29660, "total_transitions": 121487360, "num_steps_per_env": 1, "wm_loss": 0.5095866918563843, "actor_loss": -8.806375503540039, "critic_loss": 0.022195497527718544, "reward": 0.07027005404233932, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2466060370206833, 0.1571536660194397, 0.2629653215408325], "policy_updates": 29560, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3887.6761303450003, "contact_bce": 0.3229878544807434, "contact_force_loss": 0.033298760652542114, "terrain_level_mean": 3.04931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29670, "actor_lr": 1.8174796500533214e-06, "archive_windows": 100000, "env_steps": 29670, "total_transitions": 121528320, "num_steps_per_env": 1, "wm_loss": 0.5076549649238586, "actor_loss": -8.812089920043945, "critic_loss": 0.023256942629814148, "reward": 0.07066136598587036, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24473999440670013, 0.15819388628005981, 0.25661501288414], "policy_updates": 29570, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3892.13164443, "contact_bce": 0.3235336244106293, "contact_force_loss": 0.03374359384179115, "terrain_level_mean": 3.0498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29680, "actor_lr": 1.8164395300611714e-06, "archive_windows": 100000, "env_steps": 29680, "total_transitions": 121569280, "num_steps_per_env": 1, "wm_loss": 0.4837692677974701, "actor_loss": -8.775771141052246, "critic_loss": 0.026217712089419365, "reward": 0.07094059139490128, "falls": 5, "interval_steps": 10, "velocity_mae": [0.240797221660614, 0.15738005936145782, 0.2544082701206207], "policy_updates": 29580, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3896.54491563, "contact_bce": 0.3254108428955078, "contact_force_loss": 0.033561959862709045, "terrain_level_mean": 3.051025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29690, "actor_lr": 1.8154313037590389e-06, "archive_windows": 100000, "env_steps": 29690, "total_transitions": 121610240, "num_steps_per_env": 1, "wm_loss": 0.48426440358161926, "actor_loss": -8.836763381958008, "critic_loss": 0.02342018112540245, "reward": 0.0708477720618248, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2417268455028534, 0.15973667800426483, 0.25474029779434204], "policy_updates": 29590, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3900.9412133319997, "contact_bce": 0.32403698563575745, "contact_force_loss": 0.03296772018074989, "terrain_level_mean": 3.051513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29700, "actor_lr": 1.8144549722525737e-06, "archive_windows": 100000, "env_steps": 29700, "total_transitions": 121651200, "num_steps_per_env": 1, "wm_loss": 0.47286635637283325, "actor_loss": -8.809652328491211, "critic_loss": 0.0210818350315094, "reward": 0.07088207453489304, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24483339488506317, 0.15882223844528198, 0.2533036470413208], "policy_updates": 29600, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3905.3789671460004, "contact_bce": 0.3194481134414673, "contact_force_loss": 0.03257361426949501, "terrain_level_mean": 3.05322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_029700.mp4 {"step": 29710, "actor_lr": 1.8135105366124363e-06, "archive_windows": 100000, "env_steps": 29710, "total_transitions": 121692160, "num_steps_per_env": 1, "wm_loss": 0.4804344177246094, "actor_loss": -8.735832214355469, "critic_loss": 0.03545844927430153, "reward": 0.07087749242782593, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2451014667749405, 0.15806320309638977, 0.2536602020263672], "policy_updates": 29610, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3916.674633391, "contact_bce": 0.32645681500434875, "contact_force_loss": 0.03280792012810707, "terrain_level_mean": 3.054443359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29720, "actor_lr": 1.8125979978743242e-06, "archive_windows": 100000, "env_steps": 29720, "total_transitions": 121733120, "num_steps_per_env": 1, "wm_loss": 0.4440610408782959, "actor_loss": -8.780858993530273, "critic_loss": 0.034933045506477356, "reward": 0.07102318108081818, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24625596404075623, 0.15895619988441467, 0.2594234049320221], "policy_updates": 29620, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3921.2646306419997, "contact_bce": 0.3164860010147095, "contact_force_loss": 0.032532643526792526, "terrain_level_mean": 3.05419921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29730, "actor_lr": 1.811717357038939e-06, "archive_windows": 100000, "env_steps": 29730, "total_transitions": 121774080, "num_steps_per_env": 1, "wm_loss": 0.4962049424648285, "actor_loss": -8.763484954833984, "critic_loss": 0.02704201079905033, "reward": 0.07121338695287704, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23927035927772522, 0.15853597223758698, 0.2583155930042267], "policy_updates": 29630, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3925.7888436380003, "contact_bce": 0.3258817791938782, "contact_force_loss": 0.03405669704079628, "terrain_level_mean": 3.05322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29740, "actor_lr": 1.8108686150720165e-06, "archive_windows": 100000, "env_steps": 29740, "total_transitions": 121815040, "num_steps_per_env": 1, "wm_loss": 0.4511829912662506, "actor_loss": -8.801836013793945, "critic_loss": 0.027151674032211304, "reward": 0.07088913768529892, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23992453515529633, 0.16046984493732452, 0.25845545530319214], "policy_updates": 29640, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3930.239123447, "contact_bce": 0.3164692223072052, "contact_force_loss": 0.03252050280570984, "terrain_level_mean": 3.05419921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29750, "actor_lr": 1.810051772904306e-06, "archive_windows": 100000, "env_steps": 29750, "total_transitions": 121856000, "num_steps_per_env": 1, "wm_loss": 0.4963686466217041, "actor_loss": -8.799522399902344, "critic_loss": 0.022534983232617378, "reward": 0.07110675424337387, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24273593723773956, 0.15616095066070557, 0.2567107677459717], "policy_updates": 29650, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3934.697623107, "contact_bce": 0.3251311779022217, "contact_force_loss": 0.03380373492836952, "terrain_level_mean": 3.054443359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29760, "actor_lr": 1.809266831431575e-06, "archive_windows": 100000, "env_steps": 29760, "total_transitions": 121896960, "num_steps_per_env": 1, "wm_loss": 0.5008528828620911, "actor_loss": -8.770242691040039, "critic_loss": 0.023152856156229973, "reward": 0.0715922936797142, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24346837401390076, 0.1536395400762558, 0.25752967596054077], "policy_updates": 29660, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3939.049452652, "contact_bce": 0.32270413637161255, "contact_force_loss": 0.03303227946162224, "terrain_level_mean": 3.055419921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9986906051635742, 0.9998952746391296, 2.9991116523742676]} {"step": 29770, "actor_lr": 1.808513791514608e-06, "archive_windows": 100000, "env_steps": 29770, "total_transitions": 121937920, "num_steps_per_env": 1, "wm_loss": 0.4810248017311096, "actor_loss": -8.793378829956055, "critic_loss": 0.029827361926436424, "reward": 0.0711291953921318, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2461499571800232, 0.15429407358169556, 0.2628270089626312], "policy_updates": 29670, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3943.4649978310003, "contact_bce": 0.31913208961486816, "contact_force_loss": 0.03245783969759941, "terrain_level_mean": 3.056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9957026243209839, 0.9998952746391296, 2.9991116523742676]} {"step": 29780, "actor_lr": 1.8077926539792072e-06, "archive_windows": 100000, "env_steps": 29780, "total_transitions": 121978880, "num_steps_per_env": 1, "wm_loss": 0.5032157897949219, "actor_loss": -8.852788925170898, "critic_loss": 0.02262074127793312, "reward": 0.0703611895442009, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2493741363286972, 0.157113716006279, 0.2653588354587555], "policy_updates": 29680, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3947.868186067, "contact_bce": 0.32183921337127686, "contact_force_loss": 0.03380855917930603, "terrain_level_mean": 3.056396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9957196712493896, 0.9998952746391296, 2.9991116523742676]} {"step": 29790, "actor_lr": 1.8071034196161822e-06, "archive_windows": 100000, "env_steps": 29790, "total_transitions": 122019840, "num_steps_per_env": 1, "wm_loss": 0.47095391154289246, "actor_loss": -8.760303497314453, "critic_loss": 0.020402012392878532, "reward": 0.07071476429700851, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24328283965587616, 0.16056543588638306, 0.26166877150535583], "policy_updates": 29690, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3952.2490028220004, "contact_bce": 0.3217131495475769, "contact_force_loss": 0.033221978694200516, "terrain_level_mean": 3.05615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9957196712493896, 0.9998952746391296, 2.9989192485809326]} {"step": 29800, "actor_lr": 1.80644608918137e-06, "archive_windows": 100000, "env_steps": 29800, "total_transitions": 122060800, "num_steps_per_env": 1, "wm_loss": 0.49375152587890625, "actor_loss": -8.839860916137695, "critic_loss": 0.019318390637636185, "reward": 0.07090239226818085, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2422502636909485, 0.16038131713867188, 0.26219096779823303], "policy_updates": 29700, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3956.6545345110003, "contact_bce": 0.3252233862876892, "contact_force_loss": 0.03323451802134514, "terrain_level_mean": 3.056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9957196712493896, 0.9998952746391296, 2.9989192485809326]} {"step": 29810, "actor_lr": 1.805820663395612e-06, "archive_windows": 100000, "env_steps": 29810, "total_transitions": 122101760, "num_steps_per_env": 1, "wm_loss": 0.5453485250473022, "actor_loss": -8.777688026428223, "critic_loss": 0.0202433280646801, "reward": 0.07095231860876083, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2419852316379547, 0.16161540150642395, 0.2632007896900177], "policy_updates": 29710, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3960.985651388, "contact_bce": 0.32232531905174255, "contact_force_loss": 0.033302173018455505, "terrain_level_mean": 3.05712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9957196712493896, 0.9998952746391296, 2.9989192485809326]} {"step": 29820, "actor_lr": 1.8052271429447612e-06, "archive_windows": 100000, "env_steps": 29820, "total_transitions": 122142720, "num_steps_per_env": 1, "wm_loss": 0.49717018008232117, "actor_loss": -8.767363548278809, "critic_loss": 0.03197772055864334, "reward": 0.07050415128469467, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24872834980487823, 0.16129256784915924, 0.2628370523452759], "policy_updates": 29720, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3965.4021231310003, "contact_bce": 0.32790303230285645, "contact_force_loss": 0.033758435398340225, "terrain_level_mean": 3.056884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9985147714614868, 0.9998952746391296, 2.9989192485809326]} {"step": 29830, "actor_lr": 1.8046655284796902e-06, "archive_windows": 100000, "env_steps": 29830, "total_transitions": 122183680, "num_steps_per_env": 1, "wm_loss": 0.5150477886199951, "actor_loss": -8.758005142211914, "critic_loss": 0.024778926745057106, "reward": 0.06992508471012115, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24724790453910828, 0.16086332499980927, 0.2600467801094055], "policy_updates": 29730, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3969.807954536, "contact_bce": 0.32332122325897217, "contact_force_loss": 0.03330554813146591, "terrain_level_mean": 3.05615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9985147714614868, 0.9998952746391296, 2.9989192485809326]} {"step": 29840, "actor_lr": 1.8041358206162736e-06, "archive_windows": 100000, "env_steps": 29840, "total_transitions": 122224640, "num_steps_per_env": 1, "wm_loss": 0.47807589173316956, "actor_loss": -8.799783706665039, "critic_loss": 0.025318294763565063, "reward": 0.06972189992666245, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24665966629981995, 0.16232068836688995, 0.25659337639808655], "policy_updates": 29740, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3974.228135244, "contact_bce": 0.3203941881656647, "contact_force_loss": 0.03269113227725029, "terrain_level_mean": 3.05615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9985147714614868, 0.9998952746391296, 2.9989192485809326]} {"step": 29850, "actor_lr": 1.8036380199354032e-06, "archive_windows": 100000, "env_steps": 29850, "total_transitions": 122265600, "num_steps_per_env": 1, "wm_loss": 0.5027862191200256, "actor_loss": -8.80609130859375, "critic_loss": 0.026838956400752068, "reward": 0.07017887383699417, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24781067669391632, 0.1613747775554657, 0.25631359219551086], "policy_updates": 29750, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3978.6411383010004, "contact_bce": 0.3206736445426941, "contact_force_loss": 0.0335828922688961, "terrain_level_mean": 3.055908203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9985147714614868, 0.9998952746391296, 2.9989192485809326]} {"step": 29860, "actor_lr": 1.8031721269829788e-06, "archive_windows": 100000, "env_steps": 29860, "total_transitions": 122306560, "num_steps_per_env": 1, "wm_loss": 0.4692044258117676, "actor_loss": -8.808528900146484, "critic_loss": 0.034143511205911636, "reward": 0.07032030820846558, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24627268314361572, 0.15919607877731323, 0.2569473683834076], "policy_updates": 29760, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3983.0534528949997, "contact_bce": 0.31304386258125305, "contact_force_loss": 0.03312448039650917, "terrain_level_mean": 3.057861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9985147714614868, 0.9998952746391296, 2.9989192485809326]} {"step": 29870, "actor_lr": 1.8027381422699113e-06, "archive_windows": 100000, "env_steps": 29870, "total_transitions": 122347520, "num_steps_per_env": 1, "wm_loss": 0.48247116804122925, "actor_loss": -8.795976638793945, "critic_loss": 0.03250047191977501, "reward": 0.06988441944122314, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2518469989299774, 0.1609271615743637, 0.2585517168045044], "policy_updates": 29770, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3987.5019700220005, "contact_bce": 0.32307422161102295, "contact_force_loss": 0.032490428537130356, "terrain_level_mean": 3.058349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9985147714614868, 0.9998952746391296, 2.999647378921509]} {"step": 29880, "actor_lr": 1.802336066272112e-06, "archive_windows": 100000, "env_steps": 29880, "total_transitions": 122388480, "num_steps_per_env": 1, "wm_loss": 0.5263109803199768, "actor_loss": -8.764264106750488, "critic_loss": 0.03141053393483162, "reward": 0.07020992040634155, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25049495697021484, 0.1591719388961792, 0.2601836323738098], "policy_updates": 29780, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3991.917610252, "contact_bce": 0.3199033737182617, "contact_force_loss": 0.03336503356695175, "terrain_level_mean": 3.058349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29890, "actor_lr": 1.801965899430511e-06, "archive_windows": 100000, "env_steps": 29890, "total_transitions": 122429440, "num_steps_per_env": 1, "wm_loss": 0.4838715195655823, "actor_loss": -8.819486618041992, "critic_loss": 0.027905231341719627, "reward": 0.07006632536649704, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25149983167648315, 0.15751951932907104, 0.25784826278686523], "policy_updates": 29790, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 3996.3289806610005, "contact_bce": 0.31743353605270386, "contact_force_loss": 0.03341110050678253, "terrain_level_mean": 3.05810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29900, "actor_lr": 1.8016276421510418e-06, "archive_windows": 100000, "env_steps": 29900, "total_transitions": 122470400, "num_steps_per_env": 1, "wm_loss": 0.49488794803619385, "actor_loss": -8.761344909667969, "critic_loss": 0.027735909447073936, "reward": 0.07038798183202744, "falls": 12, "interval_steps": 10, "velocity_mae": [0.24564363062381744, 0.15532006323337555, 0.25645285844802856], "policy_updates": 29800, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4000.728476228, "contact_bce": 0.32364422082901, "contact_force_loss": 0.03286878764629364, "terrain_level_mean": 3.056396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29910, "actor_lr": 1.801321294804646e-06, "archive_windows": 100000, "env_steps": 29910, "total_transitions": 122511360, "num_steps_per_env": 1, "wm_loss": 0.49461379647254944, "actor_loss": -8.82509994506836, "critic_loss": 0.024472717195749283, "reward": 0.07072965055704117, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2455693483352661, 0.1539037525653839, 0.25445041060447693], "policy_updates": 29810, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4005.1657818870003, "contact_bce": 0.322234183549881, "contact_force_loss": 0.033065684139728546, "terrain_level_mean": 3.056884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29920, "actor_lr": 1.8010468577272668e-06, "archive_windows": 100000, "env_steps": 29920, "total_transitions": 122552320, "num_steps_per_env": 1, "wm_loss": 0.48694801330566406, "actor_loss": -8.81402587890625, "critic_loss": 0.020463062450289726, "reward": 0.0706210508942604, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24723005294799805, 0.15386979281902313, 0.2547972500324249], "policy_updates": 29820, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4009.508905254, "contact_bce": 0.3209645450115204, "contact_force_loss": 0.032523006200790405, "terrain_level_mean": 3.056884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29930, "actor_lr": 1.800804331219858e-06, "archive_windows": 100000, "env_steps": 29930, "total_transitions": 122593280, "num_steps_per_env": 1, "wm_loss": 0.4731999933719635, "actor_loss": -8.809623718261719, "critic_loss": 0.019518157467246056, "reward": 0.07043439894914627, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2543752193450928, 0.15476493537425995, 0.2580254375934601], "policy_updates": 29830, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4013.8177696810003, "contact_bce": 0.31817349791526794, "contact_force_loss": 0.032627370208501816, "terrain_level_mean": 3.0576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29940, "actor_lr": 1.8005937155483847e-06, "archive_windows": 100000, "env_steps": 29940, "total_transitions": 122634240, "num_steps_per_env": 1, "wm_loss": 0.47508203983306885, "actor_loss": -8.793536186218262, "critic_loss": 0.02767336368560791, "reward": 0.07027062773704529, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25027021765708923, 0.15607422590255737, 0.25613412261009216], "policy_updates": 29840, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4018.1151870569997, "contact_bce": 0.3286479115486145, "contact_force_loss": 0.03344542905688286, "terrain_level_mean": 3.05810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29950, "actor_lr": 1.80041501094381e-06, "archive_windows": 100000, "env_steps": 29950, "total_transitions": 122675200, "num_steps_per_env": 1, "wm_loss": 0.4907292425632477, "actor_loss": -8.770658493041992, "critic_loss": 0.033068448305130005, "reward": 0.07037278264760971, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24312636256217957, 0.15464113652706146, 0.25558367371559143], "policy_updates": 29850, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4022.417639306, "contact_bce": 0.32565590739250183, "contact_force_loss": 0.033696454018354416, "terrain_level_mean": 3.0576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9975881576538086, 0.9998952746391296, 2.999647378921509]} {"step": 29960, "actor_lr": 1.8002682176021044e-06, "archive_windows": 100000, "env_steps": 29960, "total_transitions": 122716160, "num_steps_per_env": 1, "wm_loss": 0.4799002707004547, "actor_loss": -8.754875183105469, "critic_loss": 0.037611670792102814, "reward": 0.0706029161810875, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24275757372379303, 0.1558084636926651, 0.2547513246536255], "policy_updates": 29860, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4026.7574679599998, "contact_bce": 0.3226982355117798, "contact_force_loss": 0.033109068870544434, "terrain_level_mean": 3.059326171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9975881576538086, 0.9970918893814087, 2.999647378921509]} {"step": 29970, "actor_lr": 1.8001533356842467e-06, "archive_windows": 100000, "env_steps": 29970, "total_transitions": 122757120, "num_steps_per_env": 1, "wm_loss": 0.4710705280303955, "actor_loss": -8.792028427124023, "critic_loss": 0.028835413977503777, "reward": 0.07059746235609055, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2402326762676239, 0.1542643904685974, 0.2524515986442566], "policy_updates": 29870, "skipped_updates": 0, "invalid_env_resets": 26, "elapsed_s": 4031.1498778640002, "contact_bce": 0.32147157192230225, "contact_force_loss": 0.03267410397529602, "terrain_level_mean": 3.060302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9975881576538086, 0.9970918893814087, 2.999647378921509]} RECOVERY reset 1 invalid environments; first IDs=[1999] {"step": 29980, "actor_lr": 1.8000703653162197e-06, "archive_windows": 100000, "env_steps": 29980, "total_transitions": 122798080, "num_steps_per_env": 1, "wm_loss": 0.4683934152126312, "actor_loss": -8.853609085083008, "critic_loss": 0.025674400851130486, "reward": 0.07073270529508591, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24104119837284088, 0.1548209935426712, 0.2548946142196655], "policy_updates": 29880, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4035.567536098, "contact_bce": 0.31832385063171387, "contact_force_loss": 0.033192794770002365, "terrain_level_mean": 3.060302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9975881576538086, 0.9970918893814087, 2.999647378921509]} {"step": 29990, "actor_lr": 1.800019306589008e-06, "archive_windows": 100000, "env_steps": 29990, "total_transitions": 122839040, "num_steps_per_env": 1, "wm_loss": 0.4746953248977661, "actor_loss": -8.830575942993164, "critic_loss": 0.02249247021973133, "reward": 0.0711437463760376, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23998074233531952, 0.1559331715106964, 0.25723353028297424], "policy_updates": 29890, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4039.8939079570005, "contact_bce": 0.3150627911090851, "contact_force_loss": 0.03261226415634155, "terrain_level_mean": 3.06005859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9975881576538086, 0.9970918893814087, 2.999647378921509]} {"step": 30000, "actor_lr": 1.8000001595586034e-06, "archive_windows": 100000, "env_steps": 30000, "total_transitions": 122880000, "num_steps_per_env": 1, "wm_loss": 0.47698071599006653, "actor_loss": -8.774795532226562, "critic_loss": 0.03724442422389984, "reward": 0.07114148885011673, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24373722076416016, 0.16069914400577545, 0.2581322491168976], "policy_updates": 29900, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4044.220163433, "contact_bce": 0.3231373727321625, "contact_force_loss": 0.03281762823462486, "terrain_level_mean": 3.06103515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9975881576538086, 0.9970918893814087, 2.999647378921509]} {"step": 30010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30010, "total_transitions": 122920960, "num_steps_per_env": 1, "wm_loss": 0.487384557723999, "actor_loss": -8.797956466674805, "critic_loss": 0.0374835729598999, "reward": 0.07115980237722397, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24289147555828094, 0.16161903738975525, 0.25244203209877014], "policy_updates": 29910, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4048.6984660640005, "contact_bce": 0.3235552906990051, "contact_force_loss": 0.032844774425029755, "terrain_level_mean": 3.060302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9975881576538086, 0.9970918893814087, 2.999647378921509]} {"step": 30020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30020, "total_transitions": 122961920, "num_steps_per_env": 1, "wm_loss": 0.45102566480636597, "actor_loss": -8.825733184814453, "critic_loss": 0.02316758967936039, "reward": 0.07144349068403244, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24184557795524597, 0.1584310382604599, 0.25617849826812744], "policy_updates": 29920, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4053.387176775, "contact_bce": 0.3202408254146576, "contact_force_loss": 0.03254372254014015, "terrain_level_mean": 3.0615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9975881576538086, 0.9970918893814087, 2.999647378921509]} {"step": 30030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30030, "total_transitions": 123002880, "num_steps_per_env": 1, "wm_loss": 0.4872872233390808, "actor_loss": -8.830028533935547, "critic_loss": 0.017796147614717484, "reward": 0.07133368402719498, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24075619876384735, 0.15815933048725128, 0.2573339343070984], "policy_updates": 29930, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4057.733934575, "contact_bce": 0.31777459383010864, "contact_force_loss": 0.03310699760913849, "terrain_level_mean": 3.060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9975881576538086, 0.9975380897521973, 2.999647378921509]} {"step": 30040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30040, "total_transitions": 123043840, "num_steps_per_env": 1, "wm_loss": 0.475167840719223, "actor_loss": -8.735306739807129, "critic_loss": 0.02688789740204811, "reward": 0.07177295535802841, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24495680630207062, 0.15680794417858124, 0.2557540833950043], "policy_updates": 29940, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4062.0657077319997, "contact_bce": 0.3194482624530792, "contact_force_loss": 0.03282617777585983, "terrain_level_mean": 3.060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9975881576538086, 0.9975380897521973, 2.999647378921509]} {"step": 30050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30050, "total_transitions": 123084800, "num_steps_per_env": 1, "wm_loss": 0.49059197306632996, "actor_loss": -8.797188758850098, "critic_loss": 0.03633030131459236, "reward": 0.07154480367898941, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24465326964855194, 0.15687592327594757, 0.25939294695854187], "policy_updates": 29950, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4066.3636793480005, "contact_bce": 0.3169024586677551, "contact_force_loss": 0.03360304236412048, "terrain_level_mean": 3.062255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9975881576538086, 0.9975380897521973, 2.999647378921509]} {"step": 30060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30060, "total_transitions": 123125760, "num_steps_per_env": 1, "wm_loss": 0.4902786612510681, "actor_loss": -8.780899047851562, "critic_loss": 0.029992450028657913, "reward": 0.07128989696502686, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2444380819797516, 0.15700821578502655, 0.2564278542995453], "policy_updates": 29960, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4070.6958726770004, "contact_bce": 0.32116958498954773, "contact_force_loss": 0.03320041671395302, "terrain_level_mean": 3.063232421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30070, "total_transitions": 123166720, "num_steps_per_env": 1, "wm_loss": 0.47070130705833435, "actor_loss": -8.779640197753906, "critic_loss": 0.03267595171928406, "reward": 0.07115420699119568, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24594134092330933, 0.15779095888137817, 0.25785505771636963], "policy_updates": 29970, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4075.0289976219997, "contact_bce": 0.3235703706741333, "contact_force_loss": 0.03317539021372795, "terrain_level_mean": 3.06396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30080, "total_transitions": 123207680, "num_steps_per_env": 1, "wm_loss": 0.47901639342308044, "actor_loss": -8.742740631103516, "critic_loss": 0.02899099886417389, "reward": 0.07101910561323166, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24519091844558716, 0.1602441817522049, 0.25714579224586487], "policy_updates": 29980, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4079.339975311, "contact_bce": 0.31873390078544617, "contact_force_loss": 0.03290203586220741, "terrain_level_mean": 3.06396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30090, "total_transitions": 123248640, "num_steps_per_env": 1, "wm_loss": 0.4864058792591095, "actor_loss": -8.796773910522461, "critic_loss": 0.022309014573693275, "reward": 0.07083543390035629, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24755741655826569, 0.1616968810558319, 0.2599380612373352], "policy_updates": 29990, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4083.6781303660005, "contact_bce": 0.3233862817287445, "contact_force_loss": 0.032946690917015076, "terrain_level_mean": 3.063720703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30100, "total_transitions": 123289600, "num_steps_per_env": 1, "wm_loss": 0.4825255870819092, "actor_loss": -8.78969955444336, "critic_loss": 0.037350501865148544, "reward": 0.0705673024058342, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25430062413215637, 0.1560937464237213, 0.2612372934818268], "policy_updates": 30000, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4088.023139048, "contact_bce": 0.32227641344070435, "contact_force_loss": 0.03285810351371765, "terrain_level_mean": 3.06298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30110, "total_transitions": 123330560, "num_steps_per_env": 1, "wm_loss": 0.4809105098247528, "actor_loss": -8.77181625366211, "critic_loss": 0.03785112500190735, "reward": 0.07010947912931442, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2522538900375366, 0.1579529345035553, 0.25986820459365845], "policy_updates": 30010, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4092.3658245170004, "contact_bce": 0.3203887343406677, "contact_force_loss": 0.033003829419612885, "terrain_level_mean": 3.0615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30120, "total_transitions": 123371520, "num_steps_per_env": 1, "wm_loss": 0.4939367175102234, "actor_loss": -8.84354019165039, "critic_loss": 0.02115376852452755, "reward": 0.07033807784318924, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24938158690929413, 0.1588079035282135, 0.2595144212245941], "policy_updates": 30020, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4096.714995757, "contact_bce": 0.31646594405174255, "contact_force_loss": 0.03288720175623894, "terrain_level_mean": 3.063232421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30130, "total_transitions": 123412480, "num_steps_per_env": 1, "wm_loss": 0.46580469608306885, "actor_loss": -8.767823219299316, "critic_loss": 0.02556222677230835, "reward": 0.06997760385274887, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2502535879611969, 0.15855062007904053, 0.26133882999420166], "policy_updates": 30030, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4101.090038914, "contact_bce": 0.32153835892677307, "contact_force_loss": 0.032702457159757614, "terrain_level_mean": 3.062744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30140, "total_transitions": 123453440, "num_steps_per_env": 1, "wm_loss": 0.48243147134780884, "actor_loss": -8.78717041015625, "critic_loss": 0.02344789169728756, "reward": 0.07018791884183884, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24327661097049713, 0.1551053524017334, 0.259780615568161], "policy_updates": 30040, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4105.534208245, "contact_bce": 0.3193909823894501, "contact_force_loss": 0.03282320871949196, "terrain_level_mean": 3.062255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.999647378921509]} {"step": 30150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30150, "total_transitions": 123494400, "num_steps_per_env": 1, "wm_loss": 0.49978193640708923, "actor_loss": -8.822893142700195, "critic_loss": 0.025570077821612358, "reward": 0.07060278207063675, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2427612841129303, 0.15451429784297943, 0.25838354229927063], "policy_updates": 30050, "skipped_updates": 0, "invalid_env_resets": 27, "elapsed_s": 4109.937053258999, "contact_bce": 0.32368573546409607, "contact_force_loss": 0.03369425609707832, "terrain_level_mean": 3.061767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.995748996734619]} RECOVERY reset 1 invalid environments; first IDs=[485] {"step": 30160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30160, "total_transitions": 123535360, "num_steps_per_env": 1, "wm_loss": 0.4784630835056305, "actor_loss": -8.7814302444458, "critic_loss": 0.028521645814180374, "reward": 0.07072938978672028, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24456261098384857, 0.15385572612285614, 0.2547941207885742], "policy_updates": 30060, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4114.370707886, "contact_bce": 0.32503247261047363, "contact_force_loss": 0.0330488421022892, "terrain_level_mean": 3.0615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.995748996734619]} {"step": 30170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30170, "total_transitions": 123576320, "num_steps_per_env": 1, "wm_loss": 0.47533896565437317, "actor_loss": -8.806001663208008, "critic_loss": 0.021872127428650856, "reward": 0.07099415361881256, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23910658061504364, 0.15700265765190125, 0.25283658504486084], "policy_updates": 30070, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4118.7367712939995, "contact_bce": 0.3259944021701813, "contact_force_loss": 0.03207217901945114, "terrain_level_mean": 3.062744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.995748996734619]} {"step": 30180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30180, "total_transitions": 123617280, "num_steps_per_env": 1, "wm_loss": 0.4612368047237396, "actor_loss": -8.787240982055664, "critic_loss": 0.02376510016620159, "reward": 0.07082979381084442, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2384701669216156, 0.15816371142864227, 0.2522001564502716], "policy_updates": 30080, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4122.2662745259995, "contact_bce": 0.319672167301178, "contact_force_loss": 0.03274776041507721, "terrain_level_mean": 3.06298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.995748996734619]} {"step": 30190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30190, "total_transitions": 123658240, "num_steps_per_env": 1, "wm_loss": 0.4989781081676483, "actor_loss": -8.797179222106934, "critic_loss": 0.023361632600426674, "reward": 0.07097920030355453, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23729118704795837, 0.15711313486099243, 0.2562958002090454], "policy_updates": 30090, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4125.798799945, "contact_bce": 0.32114139199256897, "contact_force_loss": 0.03269270807504654, "terrain_level_mean": 3.063720703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33154296875, "command_abs_max": [1.9993579387664795, 0.9975380897521973, 2.995748996734619]} {"step": 30200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30200, "total_transitions": 123699200, "num_steps_per_env": 1, "wm_loss": 0.4857182204723358, "actor_loss": -8.820192337036133, "critic_loss": 0.025776250287890434, "reward": 0.07073993980884552, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23940330743789673, 0.15891200304031372, 0.2591060400009155], "policy_updates": 30100, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4129.336407270999, "contact_bce": 0.32527729868888855, "contact_force_loss": 0.03371741250157356, "terrain_level_mean": 3.064208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9993579387664795, 0.9979156851768494, 2.995748996734619]} {"step": 30210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30210, "total_transitions": 123740160, "num_steps_per_env": 1, "wm_loss": 0.47804972529411316, "actor_loss": -8.812780380249023, "critic_loss": 0.03786861523985863, "reward": 0.07041575759649277, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2399614304304123, 0.1584419161081314, 0.2598266303539276], "policy_updates": 30110, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4132.872563391, "contact_bce": 0.31518426537513733, "contact_force_loss": 0.03293060511350632, "terrain_level_mean": 3.0625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328125, "command_abs_max": [1.9993579387664795, 0.9979156851768494, 2.995748996734619]} {"step": 30220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30220, "total_transitions": 123781120, "num_steps_per_env": 1, "wm_loss": 0.4869684875011444, "actor_loss": -8.867926597595215, "critic_loss": 0.030466556549072266, "reward": 0.07093002647161484, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23924154043197632, 0.15652020275592804, 0.25446081161499023], "policy_updates": 30120, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4136.399759416, "contact_bce": 0.3227193057537079, "contact_force_loss": 0.033439893275499344, "terrain_level_mean": 3.061767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9993579387664795, 0.9979156851768494, 2.995748996734619]} {"step": 30230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30230, "total_transitions": 123822080, "num_steps_per_env": 1, "wm_loss": 0.45621877908706665, "actor_loss": -8.702981948852539, "critic_loss": 0.029545513913035393, "reward": 0.07132083922624588, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23919478058815002, 0.15446342527866364, 0.2559741139411926], "policy_updates": 30130, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4139.925511398999, "contact_bce": 0.3227274715900421, "contact_force_loss": 0.032488152384757996, "terrain_level_mean": 3.06201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9993579387664795, 0.9979156851768494, 2.995748996734619]} {"step": 30240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30240, "total_transitions": 123863040, "num_steps_per_env": 1, "wm_loss": 0.48203983902931213, "actor_loss": -8.812276840209961, "critic_loss": 0.023681044578552246, "reward": 0.07094936817884445, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2369631975889206, 0.15481269359588623, 0.25600820779800415], "policy_updates": 30140, "skipped_updates": 0, "invalid_env_resets": 28, "elapsed_s": 4143.451797224, "contact_bce": 0.3190595209598541, "contact_force_loss": 0.032678984105587006, "terrain_level_mean": 3.061767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} RECOVERY reset 1 invalid environments; first IDs=[977] {"step": 30250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30250, "total_transitions": 123904000, "num_steps_per_env": 1, "wm_loss": 0.4719618260860443, "actor_loss": -8.771045684814453, "critic_loss": 0.030193639919161797, "reward": 0.07108304649591446, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23541979491710663, 0.15630072355270386, 0.25322481989860535], "policy_updates": 30150, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4146.979190661999, "contact_bce": 0.322421133518219, "contact_force_loss": 0.033221982419490814, "terrain_level_mean": 3.060791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30260, "total_transitions": 123944960, "num_steps_per_env": 1, "wm_loss": 0.46409332752227783, "actor_loss": -8.808478355407715, "critic_loss": 0.03129556030035019, "reward": 0.07075835019350052, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23644642531871796, 0.15682467818260193, 0.25251471996307373], "policy_updates": 30160, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4150.490642266, "contact_bce": 0.3205485939979553, "contact_force_loss": 0.033105164766311646, "terrain_level_mean": 3.060302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30270, "total_transitions": 123985920, "num_steps_per_env": 1, "wm_loss": 0.47447213530540466, "actor_loss": -8.777292251586914, "critic_loss": 0.03315013274550438, "reward": 0.07079573720693588, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2379220873117447, 0.1573040932416916, 0.25126904249191284], "policy_updates": 30170, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4154.019200375, "contact_bce": 0.3268795311450958, "contact_force_loss": 0.03292292729020119, "terrain_level_mean": 3.060791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30280, "total_transitions": 124026880, "num_steps_per_env": 1, "wm_loss": 0.4531181752681732, "actor_loss": -8.801698684692383, "critic_loss": 0.038512103259563446, "reward": 0.07045000046491623, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24413244426250458, 0.1574866771697998, 0.25503280758857727], "policy_updates": 30180, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4157.552205821999, "contact_bce": 0.3193395733833313, "contact_force_loss": 0.03273340314626694, "terrain_level_mean": 3.059814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30290, "total_transitions": 124067840, "num_steps_per_env": 1, "wm_loss": 0.47157204151153564, "actor_loss": -8.724757194519043, "critic_loss": 0.022573068737983704, "reward": 0.07082592695951462, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24190352857112885, 0.15563492476940155, 0.2528359889984131], "policy_updates": 30190, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4161.075535845999, "contact_bce": 0.3226628601551056, "contact_force_loss": 0.032212890684604645, "terrain_level_mean": 3.05908203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30300, "total_transitions": 124108800, "num_steps_per_env": 1, "wm_loss": 0.4734925627708435, "actor_loss": -8.749137878417969, "critic_loss": 0.03621184453368187, "reward": 0.07175719738006592, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23958314955234528, 0.15390756726264954, 0.254825234413147], "policy_updates": 30200, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4164.604037122999, "contact_bce": 0.32525208592414856, "contact_force_loss": 0.03429476544260979, "terrain_level_mean": 3.058349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30310, "total_transitions": 124149760, "num_steps_per_env": 1, "wm_loss": 0.5074076652526855, "actor_loss": -8.795982360839844, "critic_loss": 0.021586528047919273, "reward": 0.07202503085136414, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2405194193124771, 0.1544475257396698, 0.2534862160682678], "policy_updates": 30210, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4168.135095496999, "contact_bce": 0.32332220673561096, "contact_force_loss": 0.033589739352464676, "terrain_level_mean": 3.0595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30320, "total_transitions": 124190720, "num_steps_per_env": 1, "wm_loss": 0.5170182585716248, "actor_loss": -8.814628601074219, "critic_loss": 0.025031430646777153, "reward": 0.07151197642087936, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23794783651828766, 0.15632301568984985, 0.2528335154056549], "policy_updates": 30220, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4171.65877189, "contact_bce": 0.3275125026702881, "contact_force_loss": 0.034026190638542175, "terrain_level_mean": 3.060302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30330, "total_transitions": 124231680, "num_steps_per_env": 1, "wm_loss": 0.4971482753753662, "actor_loss": -8.798704147338867, "critic_loss": 0.02242981642484665, "reward": 0.07165016978979111, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2338726967573166, 0.15468263626098633, 0.2510091960430145], "policy_updates": 30230, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4175.182143749, "contact_bce": 0.3148791491985321, "contact_force_loss": 0.03258989378809929, "terrain_level_mean": 3.060791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30340, "total_transitions": 124272640, "num_steps_per_env": 1, "wm_loss": 0.4597824811935425, "actor_loss": -8.806201934814453, "critic_loss": 0.025021135807037354, "reward": 0.07206211984157562, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22918424010276794, 0.15452994406223297, 0.25488707423210144], "policy_updates": 30240, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4178.698430551, "contact_bce": 0.31965887546539307, "contact_force_loss": 0.03292794153094292, "terrain_level_mean": 3.0615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30350, "total_transitions": 124313600, "num_steps_per_env": 1, "wm_loss": 0.5157226324081421, "actor_loss": -8.825150489807129, "critic_loss": 0.02229633927345276, "reward": 0.07182221859693527, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2337254136800766, 0.15412691235542297, 0.2509024739265442], "policy_updates": 30250, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4182.219648902999, "contact_bce": 0.3188266456127167, "contact_force_loss": 0.03213481232523918, "terrain_level_mean": 3.06103515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30360, "total_transitions": 124354560, "num_steps_per_env": 1, "wm_loss": 0.46777161955833435, "actor_loss": -8.785842895507812, "critic_loss": 0.02881142497062683, "reward": 0.07206685841083527, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2336263507604599, 0.1565653681755066, 0.25078707933425903], "policy_updates": 30260, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4185.739867447, "contact_bce": 0.3199312686920166, "contact_force_loss": 0.0323980376124382, "terrain_level_mean": 3.060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30370, "total_transitions": 124395520, "num_steps_per_env": 1, "wm_loss": 0.4579033851623535, "actor_loss": -8.780388832092285, "critic_loss": 0.022711141034960747, "reward": 0.07198724150657654, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23200123012065887, 0.15497684478759766, 0.2506966292858124], "policy_updates": 30270, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4189.257542863999, "contact_bce": 0.3144911527633667, "contact_force_loss": 0.032470956444740295, "terrain_level_mean": 3.0625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30380, "total_transitions": 124436480, "num_steps_per_env": 1, "wm_loss": 0.44582873582839966, "actor_loss": -8.781708717346191, "critic_loss": 0.025900674983859062, "reward": 0.07201889902353287, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2337230145931244, 0.1528071016073227, 0.2508525848388672], "policy_updates": 30280, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4192.77913937, "contact_bce": 0.3178527057170868, "contact_force_loss": 0.03313157334923744, "terrain_level_mean": 3.06298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30390, "total_transitions": 124477440, "num_steps_per_env": 1, "wm_loss": 0.45681917667388916, "actor_loss": -8.779348373413086, "critic_loss": 0.02157195843756199, "reward": 0.0717221051454544, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23820176720619202, 0.1522093266248703, 0.25260674953460693], "policy_updates": 30290, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4196.303796736, "contact_bce": 0.317184716463089, "contact_force_loss": 0.03376081958413124, "terrain_level_mean": 3.063232421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30400, "total_transitions": 124518400, "num_steps_per_env": 1, "wm_loss": 0.46700939536094666, "actor_loss": -8.860642433166504, "critic_loss": 0.017397193238139153, "reward": 0.0713920071721077, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2340434342622757, 0.15386629104614258, 0.2569945454597473], "policy_updates": 30300, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4199.822765221999, "contact_bce": 0.32081830501556396, "contact_force_loss": 0.03262535110116005, "terrain_level_mean": 3.06298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30410, "total_transitions": 124559360, "num_steps_per_env": 1, "wm_loss": 0.4639423191547394, "actor_loss": -8.763568878173828, "critic_loss": 0.027111053466796875, "reward": 0.07129556685686111, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23466257750988007, 0.15512965619564056, 0.2528884708881378], "policy_updates": 30310, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4203.3483071129995, "contact_bce": 0.31878912448883057, "contact_force_loss": 0.03255068510770798, "terrain_level_mean": 3.0625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9993579387664795, 0.9979848861694336, 2.995748996734619]} {"step": 30420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30420, "total_transitions": 124600320, "num_steps_per_env": 1, "wm_loss": 0.45067206025123596, "actor_loss": -8.805624008178711, "critic_loss": 0.0214220117777586, "reward": 0.07143280655145645, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23450972139835358, 0.15818046033382416, 0.25048384070396423], "policy_updates": 30320, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4206.878730013, "contact_bce": 0.3175490200519562, "contact_force_loss": 0.0326707698404789, "terrain_level_mean": 3.062744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9987483024597168, 0.9979848861694336, 2.995748996734619]} {"step": 30430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30430, "total_transitions": 124641280, "num_steps_per_env": 1, "wm_loss": 0.4505210518836975, "actor_loss": -8.845966339111328, "critic_loss": 0.02347605489194393, "reward": 0.07113175839185715, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23618212342262268, 0.15679311752319336, 0.25099360942840576], "policy_updates": 30330, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4210.407170592, "contact_bce": 0.3167249262332916, "contact_force_loss": 0.031311195343732834, "terrain_level_mean": 3.062255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9987483024597168, 0.9988193511962891, 2.995748996734619]} {"step": 30440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30440, "total_transitions": 124682240, "num_steps_per_env": 1, "wm_loss": 0.48035648465156555, "actor_loss": -8.793648719787598, "critic_loss": 0.0326932929456234, "reward": 0.07117953896522522, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23633697628974915, 0.1556529551744461, 0.25507277250289917], "policy_updates": 30340, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4213.9284818119995, "contact_bce": 0.3120264708995819, "contact_force_loss": 0.032787028700113297, "terrain_level_mean": 3.060791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9978833198547363, 0.9988193511962891, 2.995748996734619]} {"step": 30450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30450, "total_transitions": 124723200, "num_steps_per_env": 1, "wm_loss": 0.4749997854232788, "actor_loss": -8.825618743896484, "critic_loss": 0.03540134057402611, "reward": 0.07157402485609055, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23941799998283386, 0.15437841415405273, 0.25464221835136414], "policy_updates": 30350, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4217.448441676999, "contact_bce": 0.3267821967601776, "contact_force_loss": 0.03345519304275513, "terrain_level_mean": 3.06201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9978833198547363, 0.9988193511962891, 2.995748996734619]} {"step": 30460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30460, "total_transitions": 124764160, "num_steps_per_env": 1, "wm_loss": 0.5071713328361511, "actor_loss": -8.795291900634766, "critic_loss": 0.029217272996902466, "reward": 0.07120208442211151, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23662155866622925, 0.15693145990371704, 0.2562166154384613], "policy_updates": 30360, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4220.976888325, "contact_bce": 0.32551175355911255, "contact_force_loss": 0.03444745019078255, "terrain_level_mean": 3.06298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9995336532592773, 0.9988193511962891, 2.9934873580932617]} {"step": 30470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30470, "total_transitions": 124805120, "num_steps_per_env": 1, "wm_loss": 0.46350565552711487, "actor_loss": -8.822121620178223, "critic_loss": 0.02358834445476532, "reward": 0.07094182819128036, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24134337902069092, 0.15747274458408356, 0.25705865025520325], "policy_updates": 30370, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4224.503461288, "contact_bce": 0.32108837366104126, "contact_force_loss": 0.03246857970952988, "terrain_level_mean": 3.064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9995336532592773, 0.9988193511962891, 2.9934873580932617]} {"step": 30480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30480, "total_transitions": 124846080, "num_steps_per_env": 1, "wm_loss": 0.44842812418937683, "actor_loss": -8.800182342529297, "critic_loss": 0.02336060255765915, "reward": 0.07105592638254166, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24103952944278717, 0.15900056064128876, 0.2557794749736786], "policy_updates": 30380, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4228.029159205999, "contact_bce": 0.3220023512840271, "contact_force_loss": 0.03239603713154793, "terrain_level_mean": 3.065673828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9995336532592773, 0.9988193511962891, 2.9934873580932617]} {"step": 30490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30490, "total_transitions": 124887040, "num_steps_per_env": 1, "wm_loss": 0.45052844285964966, "actor_loss": -8.75513744354248, "critic_loss": 0.025483930483460426, "reward": 0.0711851567029953, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24081914126873016, 0.15937894582748413, 0.2528752386569977], "policy_updates": 30390, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4231.555134001, "contact_bce": 0.32448339462280273, "contact_force_loss": 0.032855018973350525, "terrain_level_mean": 3.066162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9995336532592773, 0.9988193511962891, 2.9894156455993652]} {"step": 30500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30500, "total_transitions": 124928000, "num_steps_per_env": 1, "wm_loss": 0.4578721225261688, "actor_loss": -8.80301284790039, "critic_loss": 0.03382272273302078, "reward": 0.07097304612398148, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2430410087108612, 0.15802748501300812, 0.25309643149375916], "policy_updates": 30400, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4235.066346127, "contact_bce": 0.32427844405174255, "contact_force_loss": 0.03315122053027153, "terrain_level_mean": 3.06640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9995336532592773, 0.9988193511962891, 2.9894156455993652]} {"step": 30510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30510, "total_transitions": 124968960, "num_steps_per_env": 1, "wm_loss": 0.4381616413593292, "actor_loss": -8.796418190002441, "critic_loss": 0.020012957975268364, "reward": 0.07086958736181259, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2545927166938782, 0.15752722322940826, 0.253688246011734], "policy_updates": 30410, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4238.626350687, "contact_bce": 0.3136034905910492, "contact_force_loss": 0.031575191766023636, "terrain_level_mean": 3.065185546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9995336532592773, 0.9979848861694336, 2.9894156455993652]} {"step": 30520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30520, "total_transitions": 125009920, "num_steps_per_env": 1, "wm_loss": 0.4756416082382202, "actor_loss": -8.739954948425293, "critic_loss": 0.02959730103611946, "reward": 0.07114227861166, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24581488966941833, 0.15572099387645721, 0.25308549404144287], "policy_updates": 30420, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4242.169148622, "contact_bce": 0.3231121897697449, "contact_force_loss": 0.032555144280195236, "terrain_level_mean": 3.065185546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9995336532592773, 0.9979848861694336, 2.9894156455993652]} {"step": 30530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30530, "total_transitions": 125050880, "num_steps_per_env": 1, "wm_loss": 0.49605005979537964, "actor_loss": -8.75765609741211, "critic_loss": 0.029551371932029724, "reward": 0.07153889536857605, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24198134243488312, 0.15714286267757416, 0.2526720464229584], "policy_updates": 30430, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4245.944638147999, "contact_bce": 0.3197951316833496, "contact_force_loss": 0.03211518004536629, "terrain_level_mean": 3.0654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9995336532592773, 0.9979848861694336, 2.9894156455993652]} {"step": 30540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30540, "total_transitions": 125091840, "num_steps_per_env": 1, "wm_loss": 0.4629494547843933, "actor_loss": -8.838953018188477, "critic_loss": 0.026359492912888527, "reward": 0.07183471322059631, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23676379024982452, 0.15619347989559174, 0.25043684244155884], "policy_updates": 30440, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4249.470828109999, "contact_bce": 0.31859251856803894, "contact_force_loss": 0.03268847614526749, "terrain_level_mean": 3.066162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9995336532592773, 0.9976869821548462, 2.9894156455993652]} {"step": 30550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30550, "total_transitions": 125132800, "num_steps_per_env": 1, "wm_loss": 0.4680713713169098, "actor_loss": -8.814151763916016, "critic_loss": 0.027354810386896133, "reward": 0.07188341021537781, "falls": 10, "interval_steps": 10, "velocity_mae": [0.23571482300758362, 0.1543537825345993, 0.2532733678817749], "policy_updates": 30450, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4252.986796540999, "contact_bce": 0.32135531306266785, "contact_force_loss": 0.032739538699388504, "terrain_level_mean": 3.065185546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894156455993652]} {"step": 30560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30560, "total_transitions": 125173760, "num_steps_per_env": 1, "wm_loss": 0.47403112053871155, "actor_loss": -8.775339126586914, "critic_loss": 0.03497878834605217, "reward": 0.07171627134084702, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2372184693813324, 0.1574098914861679, 0.25544407963752747], "policy_updates": 30460, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4256.504059718, "contact_bce": 0.3176843822002411, "contact_force_loss": 0.03298993781208992, "terrain_level_mean": 3.065673828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894156455993652]} {"step": 30570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30570, "total_transitions": 125214720, "num_steps_per_env": 1, "wm_loss": 0.48001086711883545, "actor_loss": -8.795645713806152, "critic_loss": 0.01664888672530651, "reward": 0.07158258557319641, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23877444863319397, 0.15789903700351715, 0.25098496675491333], "policy_updates": 30470, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4260.026435453, "contact_bce": 0.31732940673828125, "contact_force_loss": 0.03316798061132431, "terrain_level_mean": 3.06640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894156455993652]} {"step": 30580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30580, "total_transitions": 125255680, "num_steps_per_env": 1, "wm_loss": 0.45672523975372314, "actor_loss": -8.724695205688477, "critic_loss": 0.029936647042632103, "reward": 0.07183799147605896, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23720824718475342, 0.15759426355361938, 0.2517250180244446], "policy_updates": 30480, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4263.558364834, "contact_bce": 0.3125346601009369, "contact_force_loss": 0.03226987272500992, "terrain_level_mean": 3.068115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894156455993652]} {"step": 30590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30590, "total_transitions": 125296640, "num_steps_per_env": 1, "wm_loss": 0.467536985874176, "actor_loss": -8.757492065429688, "critic_loss": 0.030379850417375565, "reward": 0.07117297500371933, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24154096841812134, 0.16113297641277313, 0.2547496259212494], "policy_updates": 30490, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4267.085906626, "contact_bce": 0.3197569251060486, "contact_force_loss": 0.03247445449233055, "terrain_level_mean": 3.068603515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894771575927734]} {"step": 30600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30600, "total_transitions": 125337600, "num_steps_per_env": 1, "wm_loss": 0.46113571524620056, "actor_loss": -8.780011177062988, "critic_loss": 0.029056156054139137, "reward": 0.0712963417172432, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24299918115139008, 0.16104887425899506, 0.2550797462463379], "policy_updates": 30500, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4270.602383799999, "contact_bce": 0.32225093245506287, "contact_force_loss": 0.03270137310028076, "terrain_level_mean": 3.06982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894771575927734]} {"step": 30610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30610, "total_transitions": 125378560, "num_steps_per_env": 1, "wm_loss": 0.45080772042274475, "actor_loss": -8.809732437133789, "critic_loss": 0.025675011798739433, "reward": 0.07126832008361816, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24454137682914734, 0.15942959487438202, 0.25108012557029724], "policy_updates": 30510, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4274.122863271, "contact_bce": 0.32151034474372864, "contact_force_loss": 0.032597947865724564, "terrain_level_mean": 3.070556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894771575927734]} {"step": 30620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30620, "total_transitions": 125419520, "num_steps_per_env": 1, "wm_loss": 0.4784705936908722, "actor_loss": -8.834218978881836, "critic_loss": 0.023723818361759186, "reward": 0.07127510011196136, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2460029423236847, 0.15907804667949677, 0.2539650499820709], "policy_updates": 30520, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4277.634758603, "contact_bce": 0.3243153691291809, "contact_force_loss": 0.03311944380402565, "terrain_level_mean": 3.06982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894771575927734]} {"step": 30630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30630, "total_transitions": 125460480, "num_steps_per_env": 1, "wm_loss": 0.4781506359577179, "actor_loss": -8.789365768432617, "critic_loss": 0.02532641403377056, "reward": 0.07098351418972015, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2439946085214615, 0.15950588881969452, 0.25263240933418274], "policy_updates": 30530, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4281.145790168, "contact_bce": 0.3247945308685303, "contact_force_loss": 0.03291414678096771, "terrain_level_mean": 3.0693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894771575927734]} {"step": 30640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30640, "total_transitions": 125501440, "num_steps_per_env": 1, "wm_loss": 0.46785083413124084, "actor_loss": -8.772725105285645, "critic_loss": 0.022543370723724365, "reward": 0.07077332586050034, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24293826520442963, 0.15925157070159912, 0.2564008831977844], "policy_updates": 30540, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4284.6548678809995, "contact_bce": 0.3193572461605072, "contact_force_loss": 0.03250718489289284, "terrain_level_mean": 3.070556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9991035461425781, 0.9979400634765625, 2.9894771575927734]} {"step": 30650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30650, "total_transitions": 125542400, "num_steps_per_env": 1, "wm_loss": 0.4536425471305847, "actor_loss": -8.844348907470703, "critic_loss": 0.026284385472536087, "reward": 0.07102790474891663, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24266870319843292, 0.15769997239112854, 0.2554972767829895], "policy_updates": 30550, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4288.164959899, "contact_bce": 0.3197575509548187, "contact_force_loss": 0.032753340899944305, "terrain_level_mean": 3.0703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9991035461425781, 0.9996627569198608, 2.9923183917999268]} {"step": 30660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30660, "total_transitions": 125583360, "num_steps_per_env": 1, "wm_loss": 0.4635713994503021, "actor_loss": -8.807685852050781, "critic_loss": 0.02791283093392849, "reward": 0.07079610228538513, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2438400834798813, 0.15870709717273712, 0.2529999911785126], "policy_updates": 30560, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4291.680459271, "contact_bce": 0.3220639228820801, "contact_force_loss": 0.0324147529900074, "terrain_level_mean": 3.071044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9991035461425781, 0.9996627569198608, 2.9923183917999268]} {"step": 30670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30670, "total_transitions": 125624320, "num_steps_per_env": 1, "wm_loss": 0.4443608522415161, "actor_loss": -8.775360107421875, "critic_loss": 0.024492323398590088, "reward": 0.07096252590417862, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2448813021183014, 0.15949077904224396, 0.2528019845485687], "policy_updates": 30570, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4295.201115303999, "contact_bce": 0.31922629475593567, "contact_force_loss": 0.032551415264606476, "terrain_level_mean": 3.071044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9991035461425781, 0.9996627569198608, 2.9923183917999268]} {"step": 30680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30680, "total_transitions": 125665280, "num_steps_per_env": 1, "wm_loss": 0.4546266794204712, "actor_loss": -8.819252014160156, "critic_loss": 0.027050424367189407, "reward": 0.07094158977270126, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23913496732711792, 0.15870428085327148, 0.25440046191215515], "policy_updates": 30580, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4298.725692616999, "contact_bce": 0.31353580951690674, "contact_force_loss": 0.03241116181015968, "terrain_level_mean": 3.07177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30690, "total_transitions": 125706240, "num_steps_per_env": 1, "wm_loss": 0.4656594395637512, "actor_loss": -8.812765121459961, "critic_loss": 0.02022552862763405, "reward": 0.0710962638258934, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24409954249858856, 0.15851463377475739, 0.2556057870388031], "policy_updates": 30590, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4302.238563145, "contact_bce": 0.3202061355113983, "contact_force_loss": 0.03281671181321144, "terrain_level_mean": 3.0712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30700, "total_transitions": 125747200, "num_steps_per_env": 1, "wm_loss": 0.4702642858028412, "actor_loss": -8.793724060058594, "critic_loss": 0.0281631238758564, "reward": 0.07101815193891525, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2447749376296997, 0.16016417741775513, 0.25332871079444885], "policy_updates": 30600, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4305.759055721999, "contact_bce": 0.318226158618927, "contact_force_loss": 0.03189839795231819, "terrain_level_mean": 3.07275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30710, "total_transitions": 125788160, "num_steps_per_env": 1, "wm_loss": 0.4650629162788391, "actor_loss": -8.85167121887207, "critic_loss": 0.0188021007925272, "reward": 0.07075826823711395, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2418147772550583, 0.15939709544181824, 0.2552242577075958], "policy_updates": 30610, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4309.290620817, "contact_bce": 0.31702277064323425, "contact_force_loss": 0.03278827667236328, "terrain_level_mean": 3.07177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30720, "total_transitions": 125829120, "num_steps_per_env": 1, "wm_loss": 0.477092444896698, "actor_loss": -8.838150024414062, "critic_loss": 0.02583644725382328, "reward": 0.07091859728097916, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2421063929796219, 0.15837331116199493, 0.2567470967769623], "policy_updates": 30620, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4312.817557484999, "contact_bce": 0.31995320320129395, "contact_force_loss": 0.03376924246549606, "terrain_level_mean": 3.072509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30730, "total_transitions": 125870080, "num_steps_per_env": 1, "wm_loss": 0.47145652770996094, "actor_loss": -8.859045028686523, "critic_loss": 0.023543884977698326, "reward": 0.07128896564245224, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24417737126350403, 0.1600363850593567, 0.2540208399295807], "policy_updates": 30630, "skipped_updates": 0, "invalid_env_resets": 29, "elapsed_s": 4316.3384731999995, "contact_bce": 0.3270389437675476, "contact_force_loss": 0.03352247178554535, "terrain_level_mean": 3.072509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} Warning: EPA horizon = 24 isn't large enough. RECOVERY reset 1 invalid environments; first IDs=[1010] {"step": 30740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30740, "total_transitions": 125911040, "num_steps_per_env": 1, "wm_loss": 0.44752418994903564, "actor_loss": -8.834010124206543, "critic_loss": 0.020883604884147644, "reward": 0.07150211930274963, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2390490472316742, 0.15942063927650452, 0.25579968094825745], "policy_updates": 30640, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4319.873998462999, "contact_bce": 0.31949371099472046, "contact_force_loss": 0.03297226503491402, "terrain_level_mean": 3.072509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30750, "total_transitions": 125952000, "num_steps_per_env": 1, "wm_loss": 0.4837728440761566, "actor_loss": -8.760038375854492, "critic_loss": 0.024106619879603386, "reward": 0.07126736640930176, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24337373673915863, 0.1592148393392563, 0.25860586762428284], "policy_updates": 30650, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4323.392941421, "contact_bce": 0.3192097544670105, "contact_force_loss": 0.03238479048013687, "terrain_level_mean": 3.073486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30760, "total_transitions": 125992960, "num_steps_per_env": 1, "wm_loss": 0.45985347032546997, "actor_loss": -8.822447776794434, "critic_loss": 0.024559838697314262, "reward": 0.07121949642896652, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24579362571239471, 0.1582363247871399, 0.2580174505710602], "policy_updates": 30660, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4326.898859575999, "contact_bce": 0.3182644248008728, "contact_force_loss": 0.03319172188639641, "terrain_level_mean": 3.072021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30770, "total_transitions": 126033920, "num_steps_per_env": 1, "wm_loss": 0.4932388663291931, "actor_loss": -8.800293922424316, "critic_loss": 0.023496055975556374, "reward": 0.0709061548113823, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24631699919700623, 0.15899501740932465, 0.2588895261287689], "policy_updates": 30670, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4330.417617372999, "contact_bce": 0.320163369178772, "contact_force_loss": 0.03254979848861694, "terrain_level_mean": 3.072021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30780, "total_transitions": 126074880, "num_steps_per_env": 1, "wm_loss": 0.47515302896499634, "actor_loss": -8.805797576904297, "critic_loss": 0.028081027790904045, "reward": 0.07111716270446777, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24560248851776123, 0.15915586054325104, 0.25507014989852905], "policy_updates": 30680, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4333.928835778999, "contact_bce": 0.3196924030780792, "contact_force_loss": 0.03343837335705757, "terrain_level_mean": 3.07177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30790, "total_transitions": 126115840, "num_steps_per_env": 1, "wm_loss": 0.44989341497421265, "actor_loss": -8.773319244384766, "critic_loss": 0.030295444652438164, "reward": 0.07088683545589447, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2418784648180008, 0.1599663347005844, 0.2526126503944397], "policy_updates": 30690, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4337.439019373, "contact_bce": 0.32341381907463074, "contact_force_loss": 0.033141810446977615, "terrain_level_mean": 3.07421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30800, "total_transitions": 126156800, "num_steps_per_env": 1, "wm_loss": 0.504150390625, "actor_loss": -8.769150733947754, "critic_loss": 0.027507290244102478, "reward": 0.07091598212718964, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2448890656232834, 0.16039854288101196, 0.2589356601238251], "policy_updates": 30700, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4340.951520977, "contact_bce": 0.3237847089767456, "contact_force_loss": 0.0332925021648407, "terrain_level_mean": 3.0751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30810, "total_transitions": 126197760, "num_steps_per_env": 1, "wm_loss": 0.44493067264556885, "actor_loss": -8.812811851501465, "critic_loss": 0.035328056663274765, "reward": 0.07107266783714294, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24458174407482147, 0.1580728143453598, 0.25579360127449036], "policy_updates": 30710, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4344.467951457, "contact_bce": 0.3206750154495239, "contact_force_loss": 0.03295869007706642, "terrain_level_mean": 3.075927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9969663619995117, 0.9996627569198608, 2.9923183917999268]} {"step": 30820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30820, "total_transitions": 126238720, "num_steps_per_env": 1, "wm_loss": 0.4553816616535187, "actor_loss": -8.75775146484375, "critic_loss": 0.02407233975827694, "reward": 0.07055352628231049, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24412411451339722, 0.15686845779418945, 0.25550881028175354], "policy_updates": 30720, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4347.9768483279995, "contact_bce": 0.3215414881706238, "contact_force_loss": 0.03286748751997948, "terrain_level_mean": 3.076171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9937056303024292, 0.9996627569198608, 2.9923183917999268]} {"step": 30830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30830, "total_transitions": 126279680, "num_steps_per_env": 1, "wm_loss": 0.46512213349342346, "actor_loss": -8.824922561645508, "critic_loss": 0.02222673036158085, "reward": 0.07090400904417038, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2448388636112213, 0.15798339247703552, 0.2554178833961487], "policy_updates": 30730, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4351.506013077, "contact_bce": 0.32214587926864624, "contact_force_loss": 0.0334513820707798, "terrain_level_mean": 3.076904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9935102462768555, 0.9996627569198608, 2.9923183917999268]} {"step": 30840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30840, "total_transitions": 126320640, "num_steps_per_env": 1, "wm_loss": 0.4907034933567047, "actor_loss": -8.82452392578125, "critic_loss": 0.027389591559767723, "reward": 0.07128100842237473, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2431018203496933, 0.15629859268665314, 0.24994058907032013], "policy_updates": 30740, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4355.036348779, "contact_bce": 0.3185391128063202, "contact_force_loss": 0.03239886462688446, "terrain_level_mean": 3.076904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.991145372390747, 0.9996627569198608, 2.9985175132751465]} {"step": 30850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30850, "total_transitions": 126361600, "num_steps_per_env": 1, "wm_loss": 0.5040774345397949, "actor_loss": -8.769502639770508, "critic_loss": 0.03773726150393486, "reward": 0.07055642455816269, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24594895541667938, 0.15669777989387512, 0.25457918643951416], "policy_updates": 30750, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4358.565939728999, "contact_bce": 0.3191142976284027, "contact_force_loss": 0.0332297720015049, "terrain_level_mean": 3.0771484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.991145372390747, 0.9996627569198608, 2.9985175132751465]} {"step": 30860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30860, "total_transitions": 126402560, "num_steps_per_env": 1, "wm_loss": 0.4911239445209503, "actor_loss": -8.848618507385254, "critic_loss": 0.02409832738339901, "reward": 0.07046321779489517, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24258972704410553, 0.15421931445598602, 0.2543899714946747], "policy_updates": 30760, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4362.0760819689995, "contact_bce": 0.3196645975112915, "contact_force_loss": 0.03265628591179848, "terrain_level_mean": 3.0771484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.991145372390747, 0.9996627569198608, 2.9985175132751465]} {"step": 30870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30870, "total_transitions": 126443520, "num_steps_per_env": 1, "wm_loss": 0.4691469669342041, "actor_loss": -8.799400329589844, "critic_loss": 0.02111470326781273, "reward": 0.07127160578966141, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23935675621032715, 0.15247665345668793, 0.2552148103713989], "policy_updates": 30770, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4365.5909759159995, "contact_bce": 0.3203190565109253, "contact_force_loss": 0.0326068252325058, "terrain_level_mean": 3.078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.991145372390747, 0.9996627569198608, 2.9985175132751465]} {"step": 30880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30880, "total_transitions": 126484480, "num_steps_per_env": 1, "wm_loss": 0.46702560782432556, "actor_loss": -8.754456520080566, "critic_loss": 0.036179523915052414, "reward": 0.07138171792030334, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24163444340229034, 0.15234136581420898, 0.25439998507499695], "policy_updates": 30780, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4369.104515546, "contact_bce": 0.32126086950302124, "contact_force_loss": 0.03204992786049843, "terrain_level_mean": 3.078369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.991145372390747, 0.9996627569198608, 2.9985175132751465]} {"step": 30890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30890, "total_transitions": 126525440, "num_steps_per_env": 1, "wm_loss": 0.4580526649951935, "actor_loss": -8.780786514282227, "critic_loss": 0.02744881622493267, "reward": 0.07116692513227463, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24368003010749817, 0.15527279675006866, 0.2529784142971039], "policy_updates": 30790, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4372.623478949, "contact_bce": 0.3247082233428955, "contact_force_loss": 0.03295883163809776, "terrain_level_mean": 3.078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9944350719451904, 0.9996627569198608, 2.9996860027313232]} {"step": 30900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30900, "total_transitions": 126566400, "num_steps_per_env": 1, "wm_loss": 0.48639827966690063, "actor_loss": -8.766971588134766, "critic_loss": 0.016522416844964027, "reward": 0.07101459801197052, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24577577412128448, 0.15675567090511322, 0.25409096479415894], "policy_updates": 30800, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4376.141184839999, "contact_bce": 0.31977444887161255, "contact_force_loss": 0.032606128603219986, "terrain_level_mean": 3.078369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9944350719451904, 0.9996627569198608, 2.9996860027313232]} {"step": 30910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30910, "total_transitions": 126607360, "num_steps_per_env": 1, "wm_loss": 0.5019868016242981, "actor_loss": -8.838762283325195, "critic_loss": 0.020356310531497, "reward": 0.07101672142744064, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24689939618110657, 0.1554717719554901, 0.25858694314956665], "policy_updates": 30810, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4379.654796213999, "contact_bce": 0.3217454254627228, "contact_force_loss": 0.03243376314640045, "terrain_level_mean": 3.079345703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9944350719451904, 0.9996627569198608, 2.9996860027313232]} {"step": 30920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30920, "total_transitions": 126648320, "num_steps_per_env": 1, "wm_loss": 0.4984890818595886, "actor_loss": -8.80411148071289, "critic_loss": 0.023327214643359184, "reward": 0.07101520150899887, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24760159850120544, 0.15913885831832886, 0.2561897337436676], "policy_updates": 30820, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4383.16636976, "contact_bce": 0.3183339834213257, "contact_force_loss": 0.03384069353342056, "terrain_level_mean": 3.07861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.999197244644165, 0.9996627569198608, 2.9996860027313232]} {"step": 30930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30930, "total_transitions": 126689280, "num_steps_per_env": 1, "wm_loss": 0.5161384344100952, "actor_loss": -8.842134475708008, "critic_loss": 0.02122192643582821, "reward": 0.07160896062850952, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24615395069122314, 0.1583133339881897, 0.25619640946388245], "policy_updates": 30830, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4386.672966300999, "contact_bce": 0.3243669867515564, "contact_force_loss": 0.03276263177394867, "terrain_level_mean": 3.077880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.999197244644165, 0.9996627569198608, 2.9996860027313232]} {"step": 30940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30940, "total_transitions": 126730240, "num_steps_per_env": 1, "wm_loss": 0.47680386900901794, "actor_loss": -8.777229309082031, "critic_loss": 0.022560684010386467, "reward": 0.07144258171319962, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24947015941143036, 0.15849564969539642, 0.25253409147262573], "policy_updates": 30840, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4390.188814855999, "contact_bce": 0.3212226927280426, "contact_force_loss": 0.03278621658682823, "terrain_level_mean": 3.0771484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359130859375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 30950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30950, "total_transitions": 126771200, "num_steps_per_env": 1, "wm_loss": 0.508110761642456, "actor_loss": -8.81406021118164, "critic_loss": 0.0245821513235569, "reward": 0.07131226360797882, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24705485999584198, 0.15571333467960358, 0.25485581159591675], "policy_updates": 30850, "skipped_updates": 0, "invalid_env_resets": 30, "elapsed_s": 4393.708935938, "contact_bce": 0.3208584785461426, "contact_force_loss": 0.03329341113567352, "terrain_level_mean": 3.076904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} RECOVERY reset 1 invalid environments; first IDs=[1685] {"step": 30960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30960, "total_transitions": 126812160, "num_steps_per_env": 1, "wm_loss": 0.4823852777481079, "actor_loss": -8.796384811401367, "critic_loss": 0.020686523988842964, "reward": 0.07087566703557968, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24707618355751038, 0.1574862152338028, 0.2535826563835144], "policy_updates": 30860, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4397.241024639, "contact_bce": 0.3261825442314148, "contact_force_loss": 0.033602651208639145, "terrain_level_mean": 3.077880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 30970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30970, "total_transitions": 126853120, "num_steps_per_env": 1, "wm_loss": 0.48823171854019165, "actor_loss": -8.811334609985352, "critic_loss": 0.01806323602795601, "reward": 0.07084329426288605, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24847948551177979, 0.15833336114883423, 0.2584986090660095], "policy_updates": 30870, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4400.771580393, "contact_bce": 0.3199796974658966, "contact_force_loss": 0.032334085553884506, "terrain_level_mean": 3.080322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 30980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30980, "total_transitions": 126894080, "num_steps_per_env": 1, "wm_loss": 0.4856143295764923, "actor_loss": -8.752227783203125, "critic_loss": 0.022382497787475586, "reward": 0.07078750431537628, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2501247823238373, 0.16145925223827362, 0.2607690393924713], "policy_updates": 30880, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4404.294124720999, "contact_bce": 0.32831233739852905, "contact_force_loss": 0.033531397581100464, "terrain_level_mean": 3.08056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 30990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 30990, "total_transitions": 126935040, "num_steps_per_env": 1, "wm_loss": 0.4956960678100586, "actor_loss": -8.76504135131836, "critic_loss": 0.02241366170346737, "reward": 0.07100160419940948, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2505190372467041, 0.1607753485441208, 0.2575993835926056], "policy_updates": 30890, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4407.803242446999, "contact_bce": 0.32416942715644836, "contact_force_loss": 0.03326954320073128, "terrain_level_mean": 3.080322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31000, "total_transitions": 126976000, "num_steps_per_env": 1, "wm_loss": 0.48388969898223877, "actor_loss": -8.786048889160156, "critic_loss": 0.023138606920838356, "reward": 0.07115258276462555, "falls": 2, "interval_steps": 10, "velocity_mae": [0.248184472322464, 0.15978844463825226, 0.25647982954978943], "policy_updates": 30900, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4411.320479149, "contact_bce": 0.32526910305023193, "contact_force_loss": 0.03364522382616997, "terrain_level_mean": 3.08154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31010, "total_transitions": 127016960, "num_steps_per_env": 1, "wm_loss": 0.5257653594017029, "actor_loss": -8.787092208862305, "critic_loss": 0.02722407877445221, "reward": 0.07114985585212708, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24922698736190796, 0.16221460700035095, 0.25345101952552795], "policy_updates": 30910, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4414.873071192999, "contact_bce": 0.32218170166015625, "contact_force_loss": 0.033885687589645386, "terrain_level_mean": 3.080810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31020, "total_transitions": 127057920, "num_steps_per_env": 1, "wm_loss": 0.4770002067089081, "actor_loss": -8.796972274780273, "critic_loss": 0.023429706692695618, "reward": 0.07114707678556442, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24777628481388092, 0.15966668725013733, 0.25455594062805176], "policy_updates": 30920, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4418.39808929, "contact_bce": 0.3234260380268097, "contact_force_loss": 0.03227192163467407, "terrain_level_mean": 3.08154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359130859375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31030, "total_transitions": 127098880, "num_steps_per_env": 1, "wm_loss": 0.44242364168167114, "actor_loss": -8.782686233520508, "critic_loss": 0.02973412349820137, "reward": 0.0710691437125206, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24675680696964264, 0.16099976003170013, 0.25404128432273865], "policy_updates": 30930, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4422.167431743999, "contact_bce": 0.3186449110507965, "contact_force_loss": 0.03230467811226845, "terrain_level_mean": 3.08056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36083984375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31040, "total_transitions": 127139840, "num_steps_per_env": 1, "wm_loss": 0.4751454293727875, "actor_loss": -8.768056869506836, "critic_loss": 0.027552759274840355, "reward": 0.07105164229869843, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24632218480110168, 0.16180235147476196, 0.2557063102722168], "policy_updates": 30940, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4425.681899372, "contact_bce": 0.3176948130130768, "contact_force_loss": 0.03224378451704979, "terrain_level_mean": 3.07958984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35986328125, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31050, "total_transitions": 127180800, "num_steps_per_env": 1, "wm_loss": 0.45618751645088196, "actor_loss": -8.8335542678833, "critic_loss": 0.021305207163095474, "reward": 0.07070312649011612, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24779513478279114, 0.1623828113079071, 0.2608717083930969], "policy_updates": 30950, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4429.203511144, "contact_bce": 0.3241633474826813, "contact_force_loss": 0.03267334774136543, "terrain_level_mean": 3.079345703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31060, "total_transitions": 127221760, "num_steps_per_env": 1, "wm_loss": 0.4765051603317261, "actor_loss": -8.73580551147461, "critic_loss": 0.03368221968412399, "reward": 0.07075773924589157, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24899928271770477, 0.16060379147529602, 0.2564587891101837], "policy_updates": 30960, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4432.732690387, "contact_bce": 0.3253422975540161, "contact_force_loss": 0.03318637236952782, "terrain_level_mean": 3.079833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3603515625, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31070, "total_transitions": 127262720, "num_steps_per_env": 1, "wm_loss": 0.47925111651420593, "actor_loss": -8.766178131103516, "critic_loss": 0.023486441001296043, "reward": 0.07071323692798615, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24869336187839508, 0.15926297008991241, 0.2553589344024658], "policy_updates": 30970, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4436.243611389, "contact_bce": 0.32080739736557007, "contact_force_loss": 0.03288400545716286, "terrain_level_mean": 3.080322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31080, "total_transitions": 127303680, "num_steps_per_env": 1, "wm_loss": 0.4540901184082031, "actor_loss": -8.77879810333252, "critic_loss": 0.020997634157538414, "reward": 0.07114944607019424, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24271352589130402, 0.15812014043331146, 0.2547948658466339], "policy_updates": 30980, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4439.758605256, "contact_bce": 0.32192304730415344, "contact_force_loss": 0.0330624133348465, "terrain_level_mean": 3.08056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31090, "total_transitions": 127344640, "num_steps_per_env": 1, "wm_loss": 0.4886327385902405, "actor_loss": -8.773674011230469, "critic_loss": 0.022478261962532997, "reward": 0.07104017585515976, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24578072130680084, 0.15820249915122986, 0.2575741410255432], "policy_updates": 30990, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4443.277154365999, "contact_bce": 0.3222528100013733, "contact_force_loss": 0.03267654404044151, "terrain_level_mean": 3.0810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31100, "total_transitions": 127385600, "num_steps_per_env": 1, "wm_loss": 0.49297112226486206, "actor_loss": -8.79613208770752, "critic_loss": 0.023661037907004356, "reward": 0.07093072682619095, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2523714005947113, 0.15848848223686218, 0.26148295402526855], "policy_updates": 31000, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4446.786330092, "contact_bce": 0.319051057100296, "contact_force_loss": 0.033032454550266266, "terrain_level_mean": 3.082763671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355712890625, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31110, "total_transitions": 127426560, "num_steps_per_env": 1, "wm_loss": 0.45471134781837463, "actor_loss": -8.762721061706543, "critic_loss": 0.024585893377661705, "reward": 0.07062666863203049, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25408220291137695, 0.1594073474407196, 0.2595910429954529], "policy_updates": 31010, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4450.298576493, "contact_bce": 0.3140641152858734, "contact_force_loss": 0.03184259310364723, "terrain_level_mean": 3.083251953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31120, "total_transitions": 127467520, "num_steps_per_env": 1, "wm_loss": 0.4678440988063812, "actor_loss": -8.775594711303711, "critic_loss": 0.01942901499569416, "reward": 0.07075674086809158, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24843251705169678, 0.15974105894565582, 0.2576479911804199], "policy_updates": 31020, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4453.817853554, "contact_bce": 0.3188222646713257, "contact_force_loss": 0.0329877994954586, "terrain_level_mean": 3.08251953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355712890625, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31130, "total_transitions": 127508480, "num_steps_per_env": 1, "wm_loss": 0.44520047307014465, "actor_loss": -8.79939079284668, "critic_loss": 0.02411063387989998, "reward": 0.07117800414562225, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2520960569381714, 0.15533088147640228, 0.25358685851097107], "policy_updates": 31030, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4457.3363272179995, "contact_bce": 0.32136866450309753, "contact_force_loss": 0.03262721002101898, "terrain_level_mean": 3.083251953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31140, "total_transitions": 127549440, "num_steps_per_env": 1, "wm_loss": 0.46561044454574585, "actor_loss": -8.720884323120117, "critic_loss": 0.029161006212234497, "reward": 0.07133609056472778, "falls": 1, "interval_steps": 10, "velocity_mae": [0.25373220443725586, 0.1558670550584793, 0.2538491189479828], "policy_updates": 31040, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4460.8479133129995, "contact_bce": 0.3227095603942871, "contact_force_loss": 0.03261579945683479, "terrain_level_mean": 3.084228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31150, "total_transitions": 127590400, "num_steps_per_env": 1, "wm_loss": 0.44937822222709656, "actor_loss": -8.785921096801758, "critic_loss": 0.02278173342347145, "reward": 0.07158490270376205, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25344547629356384, 0.1548178791999817, 0.2548440098762512], "policy_updates": 31050, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4464.370147256, "contact_bce": 0.3205890655517578, "contact_force_loss": 0.03243257850408554, "terrain_level_mean": 3.08447265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31160, "total_transitions": 127631360, "num_steps_per_env": 1, "wm_loss": 0.4475248157978058, "actor_loss": -8.770936012268066, "critic_loss": 0.023831378668546677, "reward": 0.07162129133939743, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24989981949329376, 0.15619850158691406, 0.25378865003585815], "policy_updates": 31060, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4467.88783419, "contact_bce": 0.32689225673675537, "contact_force_loss": 0.03284658119082451, "terrain_level_mean": 3.084716796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31170, "total_transitions": 127672320, "num_steps_per_env": 1, "wm_loss": 0.46186164021492004, "actor_loss": -8.793514251708984, "critic_loss": 0.02943817339837551, "reward": 0.07164128124713898, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2462558001279831, 0.15569014847278595, 0.2567040026187897], "policy_updates": 31070, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4471.403192508999, "contact_bce": 0.3190562129020691, "contact_force_loss": 0.03314751759171486, "terrain_level_mean": 3.085693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999197244644165, 0.9994666576385498, 2.9996860027313232]} {"step": 31180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31180, "total_transitions": 127713280, "num_steps_per_env": 1, "wm_loss": 0.4490915536880493, "actor_loss": -8.806987762451172, "critic_loss": 0.030036527663469315, "reward": 0.07154907286167145, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24375586211681366, 0.155760258436203, 0.25369155406951904], "policy_updates": 31080, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4474.917277146999, "contact_bce": 0.31755244731903076, "contact_force_loss": 0.03214167803525925, "terrain_level_mean": 3.085693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9996860027313232]} {"step": 31190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31190, "total_transitions": 127754240, "num_steps_per_env": 1, "wm_loss": 0.43565988540649414, "actor_loss": -8.835912704467773, "critic_loss": 0.028894944116473198, "reward": 0.07115153968334198, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24991782009601593, 0.15756092965602875, 0.25530877709388733], "policy_updates": 31090, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4478.438719488, "contact_bce": 0.3186444640159607, "contact_force_loss": 0.03179195895791054, "terrain_level_mean": 3.0849609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359375, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9996860027313232]} {"step": 31200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31200, "total_transitions": 127795200, "num_steps_per_env": 1, "wm_loss": 0.493394672870636, "actor_loss": -8.773482322692871, "critic_loss": 0.020892037078738213, "reward": 0.07155470550060272, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2470959573984146, 0.1576017588376999, 0.2550733685493469], "policy_updates": 31100, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4481.955396923, "contact_bce": 0.328548401594162, "contact_force_loss": 0.03331905975937843, "terrain_level_mean": 3.0849609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36279296875, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9996860027313232]} {"step": 31210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31210, "total_transitions": 127836160, "num_steps_per_env": 1, "wm_loss": 0.4323999285697937, "actor_loss": -8.791125297546387, "critic_loss": 0.020878851413726807, "reward": 0.07118981331586838, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2445274442434311, 0.15907415747642517, 0.25537362694740295], "policy_updates": 31110, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4485.471527987999, "contact_bce": 0.32044291496276855, "contact_force_loss": 0.03241192549467087, "terrain_level_mean": 3.08544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361328125, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9996860027313232]} {"step": 31220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31220, "total_transitions": 127877120, "num_steps_per_env": 1, "wm_loss": 0.4537685811519623, "actor_loss": -8.784900665283203, "critic_loss": 0.02603800594806671, "reward": 0.07126416265964508, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24832022190093994, 0.1597500443458557, 0.2566777169704437], "policy_updates": 31120, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4488.991615018999, "contact_bce": 0.31667354702949524, "contact_force_loss": 0.0325947068631649, "terrain_level_mean": 3.08544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36279296875, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9940133094787598]} {"step": 31230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31230, "total_transitions": 127918080, "num_steps_per_env": 1, "wm_loss": 0.47053757309913635, "actor_loss": -8.794618606567383, "critic_loss": 0.01986338198184967, "reward": 0.07114100456237793, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2504466772079468, 0.1591028869152069, 0.25701218843460083], "policy_updates": 31130, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4492.502516046, "contact_bce": 0.32601502537727356, "contact_force_loss": 0.0333041176199913, "terrain_level_mean": 3.085205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36376953125, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9940133094787598]} {"step": 31240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31240, "total_transitions": 127959040, "num_steps_per_env": 1, "wm_loss": 0.5085693597793579, "actor_loss": -8.77386474609375, "critic_loss": 0.02240397036075592, "reward": 0.07125373929738998, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25072818994522095, 0.1602218598127365, 0.25516602396965027], "policy_updates": 31140, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4496.004154812999, "contact_bce": 0.32634732127189636, "contact_force_loss": 0.03393945097923279, "terrain_level_mean": 3.085205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.362548828125, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9940133094787598]} {"step": 31250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31250, "total_transitions": 128000000, "num_steps_per_env": 1, "wm_loss": 0.45756927132606506, "actor_loss": -8.759622573852539, "critic_loss": 0.032917220145463943, "reward": 0.07111117988824844, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25060009956359863, 0.15906387567520142, 0.25422799587249756], "policy_updates": 31150, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4499.511242944, "contact_bce": 0.3222738802433014, "contact_force_loss": 0.03325342386960983, "terrain_level_mean": 3.0849609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36181640625, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9940133094787598]} {"step": 31260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31260, "total_transitions": 128040960, "num_steps_per_env": 1, "wm_loss": 0.47555285692214966, "actor_loss": -8.794862747192383, "critic_loss": 0.01863829977810383, "reward": 0.0704803392291069, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2565997838973999, 0.16219064593315125, 0.25572723150253296], "policy_updates": 31160, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4503.0143977729995, "contact_bce": 0.3243516981601715, "contact_force_loss": 0.033582158386707306, "terrain_level_mean": 3.086181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.364501953125, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9940133094787598]} {"step": 31270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31270, "total_transitions": 128081920, "num_steps_per_env": 1, "wm_loss": 0.4613615870475769, "actor_loss": -8.776917457580566, "critic_loss": 0.03257033973932266, "reward": 0.07029049843549728, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2528431713581085, 0.1635863482952118, 0.2584102153778076], "policy_updates": 31170, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4506.531155840999, "contact_bce": 0.32337284088134766, "contact_force_loss": 0.03360132873058319, "terrain_level_mean": 3.085693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3623046875, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9940133094787598]} {"step": 31280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31280, "total_transitions": 128122880, "num_steps_per_env": 1, "wm_loss": 0.4493085741996765, "actor_loss": -8.751594543457031, "critic_loss": 0.032288726419210434, "reward": 0.07072196155786514, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25363850593566895, 0.16098874807357788, 0.2543429732322693], "policy_updates": 31180, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4510.058477519, "contact_bce": 0.3205762803554535, "contact_force_loss": 0.03233741223812103, "terrain_level_mean": 3.0849609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359130859375, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9940133094787598]} {"step": 31290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31290, "total_transitions": 128163840, "num_steps_per_env": 1, "wm_loss": 0.47111815214157104, "actor_loss": -8.778221130371094, "critic_loss": 0.0196873489767313, "reward": 0.07135310024023056, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2504790127277374, 0.15801091492176056, 0.2492515593767166], "policy_updates": 31190, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4513.581232877, "contact_bce": 0.31805580854415894, "contact_force_loss": 0.03289957344532013, "terrain_level_mean": 3.084716796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359130859375, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9997668266296387]} {"step": 31300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31300, "total_transitions": 128204800, "num_steps_per_env": 1, "wm_loss": 0.47732779383659363, "actor_loss": -8.79183578491211, "critic_loss": 0.02692016400396824, "reward": 0.0712856724858284, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24842707812786102, 0.15778234601020813, 0.25054875016212463], "policy_updates": 31200, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4517.107605136, "contact_bce": 0.3257030248641968, "contact_force_loss": 0.03397573530673981, "terrain_level_mean": 3.08544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.999197244644165, 0.9995874166488647, 2.9997668266296387]} {"step": 31310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31310, "total_transitions": 128245760, "num_steps_per_env": 1, "wm_loss": 0.45503732562065125, "actor_loss": -8.717357635498047, "critic_loss": 0.0265902578830719, "reward": 0.07130729407072067, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24377034604549408, 0.1604861617088318, 0.25513559579849243], "policy_updates": 31210, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4520.611265729, "contact_bce": 0.3150062561035156, "contact_force_loss": 0.0318000353872776, "terrain_level_mean": 3.0859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.9973361492156982, 0.9995874166488647, 2.9997668266296387]} {"step": 31320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31320, "total_transitions": 128286720, "num_steps_per_env": 1, "wm_loss": 0.46827632188796997, "actor_loss": -8.80154800415039, "critic_loss": 0.018436327576637268, "reward": 0.07116655260324478, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24454477429389954, 0.16015426814556122, 0.26174646615982056], "policy_updates": 31220, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4524.116235607999, "contact_bce": 0.32311999797821045, "contact_force_loss": 0.03298899531364441, "terrain_level_mean": 3.0869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9962377548217773, 0.9995874166488647, 2.9997668266296387]} {"step": 31330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31330, "total_transitions": 128327680, "num_steps_per_env": 1, "wm_loss": 0.45355263352394104, "actor_loss": -8.771240234375, "critic_loss": 0.03223831579089165, "reward": 0.07149307429790497, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23941464722156525, 0.15811170637607574, 0.258004754781723], "policy_updates": 31230, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4527.623007591999, "contact_bce": 0.324298620223999, "contact_force_loss": 0.033296599984169006, "terrain_level_mean": 3.088134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9962377548217773, 0.9995874166488647, 2.9997668266296387]} {"step": 31340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31340, "total_transitions": 128368640, "num_steps_per_env": 1, "wm_loss": 0.47061866521835327, "actor_loss": -8.777002334594727, "critic_loss": 0.025668317452073097, "reward": 0.07173404097557068, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23953120410442352, 0.15891128778457642, 0.2538389563560486], "policy_updates": 31240, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4531.132183138, "contact_bce": 0.3189759850502014, "contact_force_loss": 0.03290354087948799, "terrain_level_mean": 3.089599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9962377548217773, 0.9988374710083008, 2.9997668266296387]} {"step": 31350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31350, "total_transitions": 128409600, "num_steps_per_env": 1, "wm_loss": 0.4344920217990875, "actor_loss": -8.732437133789062, "critic_loss": 0.036309897899627686, "reward": 0.0713614970445633, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2420779913663864, 0.1603902131319046, 0.25243547558784485], "policy_updates": 31250, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4534.6569687149995, "contact_bce": 0.31691595911979675, "contact_force_loss": 0.031728461384773254, "terrain_level_mean": 3.090087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31360, "total_transitions": 128450560, "num_steps_per_env": 1, "wm_loss": 0.45551085472106934, "actor_loss": -8.743175506591797, "critic_loss": 0.025181902572512627, "reward": 0.07095305621623993, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2424771934747696, 0.16081419587135315, 0.2534043788909912], "policy_updates": 31260, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4538.180017074999, "contact_bce": 0.3214873671531677, "contact_force_loss": 0.033327292650938034, "terrain_level_mean": 3.089111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31370, "total_transitions": 128491520, "num_steps_per_env": 1, "wm_loss": 0.47981756925582886, "actor_loss": -8.784433364868164, "critic_loss": 0.040507908910512924, "reward": 0.07092597335577011, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24275089800357819, 0.15862174332141876, 0.2530176639556885], "policy_updates": 31270, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4541.706194029, "contact_bce": 0.32434070110321045, "contact_force_loss": 0.03354749083518982, "terrain_level_mean": 3.09130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31380, "total_transitions": 128532480, "num_steps_per_env": 1, "wm_loss": 0.48856034874916077, "actor_loss": -8.821834564208984, "critic_loss": 0.023428404703736305, "reward": 0.07062660902738571, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24477016925811768, 0.1582394242286682, 0.2506243586540222], "policy_updates": 31280, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4545.231535518999, "contact_bce": 0.3233645558357239, "contact_force_loss": 0.03362538665533066, "terrain_level_mean": 3.091796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31390, "total_transitions": 128573440, "num_steps_per_env": 1, "wm_loss": 0.46499907970428467, "actor_loss": -8.781600952148438, "critic_loss": 0.02020988054573536, "reward": 0.07061994820833206, "falls": 5, "interval_steps": 10, "velocity_mae": [0.243669793009758, 0.15753605961799622, 0.2508755326271057], "policy_updates": 31290, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4548.753445824999, "contact_bce": 0.3166377544403076, "contact_force_loss": 0.0329887792468071, "terrain_level_mean": 3.091796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31400, "total_transitions": 128614400, "num_steps_per_env": 1, "wm_loss": 0.4636189043521881, "actor_loss": -8.785008430480957, "critic_loss": 0.020476751029491425, "reward": 0.07064897567033768, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24308153986930847, 0.15652157366275787, 0.2520086169242859], "policy_updates": 31300, "skipped_updates": 0, "invalid_env_resets": 31, "elapsed_s": 4552.265301437, "contact_bce": 0.31571537256240845, "contact_force_loss": 0.032524388283491135, "terrain_level_mean": 3.0908203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} RECOVERY reset 1 invalid environments; first IDs=[2226] {"step": 31410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31410, "total_transitions": 128655360, "num_steps_per_env": 1, "wm_loss": 0.4598097503185272, "actor_loss": -8.791501998901367, "critic_loss": 0.02437807060778141, "reward": 0.07078707963228226, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24037614464759827, 0.15494491159915924, 0.250568151473999], "policy_updates": 31310, "skipped_updates": 0, "invalid_env_resets": 32, "elapsed_s": 4555.792953235, "contact_bce": 0.31857845187187195, "contact_force_loss": 0.033081308007240295, "terrain_level_mean": 3.09228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31420, "total_transitions": 128696320, "num_steps_per_env": 1, "wm_loss": 0.45439985394477844, "actor_loss": -8.814204216003418, "critic_loss": 0.024039078503847122, "reward": 0.07118622213602066, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23845116794109344, 0.15528419613838196, 0.25399425625801086], "policy_updates": 31320, "skipped_updates": 0, "invalid_env_resets": 32, "elapsed_s": 4559.294366876, "contact_bce": 0.31612786650657654, "contact_force_loss": 0.032646238803863525, "terrain_level_mean": 3.09228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31430, "total_transitions": 128737280, "num_steps_per_env": 1, "wm_loss": 0.49080100655555725, "actor_loss": -8.772489547729492, "critic_loss": 0.023174945265054703, "reward": 0.07094167917966843, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2441755086183548, 0.15217064321041107, 0.2529691755771637], "policy_updates": 31330, "skipped_updates": 0, "invalid_env_resets": 32, "elapsed_s": 4562.805948577, "contact_bce": 0.32473888993263245, "contact_force_loss": 0.033334892243146896, "terrain_level_mean": 3.093994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} RECOVERY reset 1 invalid environments; first IDs=[1100] {"step": 31440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31440, "total_transitions": 128778240, "num_steps_per_env": 1, "wm_loss": 0.43515700101852417, "actor_loss": -8.799249649047852, "critic_loss": 0.026533860713243484, "reward": 0.07041824609041214, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24615469574928284, 0.1545913964509964, 0.25393715500831604], "policy_updates": 31340, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4566.326050521, "contact_bce": 0.32309433817863464, "contact_force_loss": 0.03300344944000244, "terrain_level_mean": 3.095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31450, "total_transitions": 128819200, "num_steps_per_env": 1, "wm_loss": 0.4336458742618561, "actor_loss": -8.77488899230957, "critic_loss": 0.02799188159406185, "reward": 0.07021724432706833, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24814863502979279, 0.15597285330295563, 0.25355762243270874], "policy_updates": 31350, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4569.836738784, "contact_bce": 0.31937241554260254, "contact_force_loss": 0.03250247240066528, "terrain_level_mean": 3.096923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31460, "total_transitions": 128860160, "num_steps_per_env": 1, "wm_loss": 0.4555593430995941, "actor_loss": -8.760663986206055, "critic_loss": 0.02696221135556698, "reward": 0.07041265070438385, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24567821621894836, 0.1562315672636032, 0.25523409247398376], "policy_updates": 31360, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4573.3574451019995, "contact_bce": 0.32141414284706116, "contact_force_loss": 0.032764188945293427, "terrain_level_mean": 3.096923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332275390625, "command_abs_max": [1.9996440410614014, 0.9988374710083008, 2.9997668266296387]} {"step": 31470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31470, "total_transitions": 128901120, "num_steps_per_env": 1, "wm_loss": 0.4244973063468933, "actor_loss": -8.80549144744873, "critic_loss": 0.019880816340446472, "reward": 0.07041922211647034, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24633774161338806, 0.15552499890327454, 0.254171758890152], "policy_updates": 31370, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4576.880501949, "contact_bce": 0.3189462125301361, "contact_force_loss": 0.0324164517223835, "terrain_level_mean": 3.097412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9996440410614014, 0.9998799562454224, 2.9997668266296387]} {"step": 31480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31480, "total_transitions": 128942080, "num_steps_per_env": 1, "wm_loss": 0.45209431648254395, "actor_loss": -8.793834686279297, "critic_loss": 0.017895830795168877, "reward": 0.0704684779047966, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24913175404071808, 0.15702280402183533, 0.2528582215309143], "policy_updates": 31380, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4580.392051164, "contact_bce": 0.3223894238471985, "contact_force_loss": 0.03300857171416283, "terrain_level_mean": 3.0986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330322265625, "command_abs_max": [1.9996440410614014, 0.9998799562454224, 2.9997668266296387]} {"step": 31490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31490, "total_transitions": 128983040, "num_steps_per_env": 1, "wm_loss": 0.4679321348667145, "actor_loss": -8.77735710144043, "critic_loss": 0.021764008328318596, "reward": 0.07045324146747589, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2485869973897934, 0.15607362985610962, 0.2533760964870453], "policy_updates": 31390, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4583.8957289459995, "contact_bce": 0.3136553168296814, "contact_force_loss": 0.032092850655317307, "terrain_level_mean": 3.097900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9996440410614014, 0.9998799562454224, 2.9997668266296387]} {"step": 31500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31500, "total_transitions": 129024000, "num_steps_per_env": 1, "wm_loss": 0.47298356890678406, "actor_loss": -8.775423049926758, "critic_loss": 0.027858754619956017, "reward": 0.07054222375154495, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2535562813282013, 0.15640538930892944, 0.2572517693042755], "policy_updates": 31400, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4587.40317954, "contact_bce": 0.32212764024734497, "contact_force_loss": 0.03309723362326622, "terrain_level_mean": 3.09619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9996440410614014, 0.9998799562454224, 2.9997668266296387]} {"step": 31510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31510, "total_transitions": 129064960, "num_steps_per_env": 1, "wm_loss": 0.4702403247356415, "actor_loss": -8.818073272705078, "critic_loss": 0.03576654568314552, "reward": 0.0703495666384697, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25574585795402527, 0.1565215289592743, 0.2556389570236206], "policy_updates": 31410, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4590.952245539999, "contact_bce": 0.3243821859359741, "contact_force_loss": 0.03282463550567627, "terrain_level_mean": 3.095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9996440410614014, 0.9987533092498779, 2.9997668266296387]} {"step": 31520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31520, "total_transitions": 129105920, "num_steps_per_env": 1, "wm_loss": 0.4912108778953552, "actor_loss": -8.747076034545898, "critic_loss": 0.02278914861381054, "reward": 0.07057593762874603, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25087693333625793, 0.156868577003479, 0.25818192958831787], "policy_updates": 31420, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4594.463685633999, "contact_bce": 0.323739230632782, "contact_force_loss": 0.033498551696538925, "terrain_level_mean": 3.094970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9996440410614014, 0.9987533092498779, 2.9997668266296387]} {"step": 31530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31530, "total_transitions": 129146880, "num_steps_per_env": 1, "wm_loss": 0.4501330256462097, "actor_loss": -8.776068687438965, "critic_loss": 0.026173004880547523, "reward": 0.07004863768815994, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25079211592674255, 0.15787306427955627, 0.2597764730453491], "policy_updates": 31430, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4598.236414464, "contact_bce": 0.32011350989341736, "contact_force_loss": 0.032513052225112915, "terrain_level_mean": 3.095458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9996440410614014, 0.9987533092498779, 2.9997668266296387]} {"step": 31540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31540, "total_transitions": 129187840, "num_steps_per_env": 1, "wm_loss": 0.43034616112709045, "actor_loss": -8.781095504760742, "critic_loss": 0.02546798065304756, "reward": 0.0697626993060112, "falls": 9, "interval_steps": 10, "velocity_mae": [0.25477394461631775, 0.15692070126533508, 0.2646028995513916], "policy_updates": 31440, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4601.760050014999, "contact_bce": 0.32057833671569824, "contact_force_loss": 0.03162025287747383, "terrain_level_mean": 3.09521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9996440410614014, 0.9987533092498779, 2.9997668266296387]} {"step": 31550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31550, "total_transitions": 129228800, "num_steps_per_env": 1, "wm_loss": 0.5074621438980103, "actor_loss": -8.810614585876465, "critic_loss": 0.03887241706252098, "reward": 0.07036424428224564, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2518223226070404, 0.15631577372550964, 0.2607414126396179], "policy_updates": 31450, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4605.259929532999, "contact_bce": 0.3180854618549347, "contact_force_loss": 0.03316124528646469, "terrain_level_mean": 3.0947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9996440410614014, 0.9987533092498779, 2.9997668266296387]} {"step": 31560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31560, "total_transitions": 129269760, "num_steps_per_env": 1, "wm_loss": 0.47087517380714417, "actor_loss": -8.789751052856445, "critic_loss": 0.020670484751462936, "reward": 0.07021337002515793, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25353386998176575, 0.15834973752498627, 0.25727379322052], "policy_updates": 31460, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4608.7670229059995, "contact_bce": 0.32341596484184265, "contact_force_loss": 0.03362778574228287, "terrain_level_mean": 3.09521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9996440410614014, 0.9987533092498779, 2.9997668266296387]} {"step": 31570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31570, "total_transitions": 129310720, "num_steps_per_env": 1, "wm_loss": 0.4618384540081024, "actor_loss": -8.728715896606445, "critic_loss": 0.026034388691186905, "reward": 0.07004047185182571, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2493489533662796, 0.15853436291217804, 0.25418904423713684], "policy_updates": 31470, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4612.301376887, "contact_bce": 0.318461149930954, "contact_force_loss": 0.032578080892562866, "terrain_level_mean": 3.095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} {"step": 31580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31580, "total_transitions": 129351680, "num_steps_per_env": 1, "wm_loss": 0.4520399570465088, "actor_loss": -8.781578063964844, "critic_loss": 0.0304744690656662, "reward": 0.07048075646162033, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24615637958049774, 0.15812698006629944, 0.25327742099761963], "policy_updates": 31480, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4615.824069779999, "contact_bce": 0.31976187229156494, "contact_force_loss": 0.032314661890268326, "terrain_level_mean": 3.095458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} {"step": 31590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31590, "total_transitions": 129392640, "num_steps_per_env": 1, "wm_loss": 0.5128885507583618, "actor_loss": -8.763876914978027, "critic_loss": 0.02454412914812565, "reward": 0.07087340205907822, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24437908828258514, 0.1570509672164917, 0.25104090571403503], "policy_updates": 31490, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4619.343817549, "contact_bce": 0.31747469305992126, "contact_force_loss": 0.0334295853972435, "terrain_level_mean": 3.09521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} {"step": 31600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31600, "total_transitions": 129433600, "num_steps_per_env": 1, "wm_loss": 0.478884756565094, "actor_loss": -8.766289710998535, "critic_loss": 0.017101125791668892, "reward": 0.07071175426244736, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24544721841812134, 0.15808264911174774, 0.25304463505744934], "policy_updates": 31500, "skipped_updates": 0, "invalid_env_resets": 33, "elapsed_s": 4622.8608228289995, "contact_bce": 0.32350754737854004, "contact_force_loss": 0.03333896026015282, "terrain_level_mean": 3.0947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} RECOVERY reset 1 invalid environments; first IDs=[2203] {"step": 31610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31610, "total_transitions": 129474560, "num_steps_per_env": 1, "wm_loss": 0.5074787139892578, "actor_loss": -8.727511405944824, "critic_loss": 0.029984384775161743, "reward": 0.07049165666103363, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24925358593463898, 0.1561959981918335, 0.25524696707725525], "policy_updates": 31510, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4626.395234912, "contact_bce": 0.3258345425128937, "contact_force_loss": 0.033396437764167786, "terrain_level_mean": 3.0947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} {"step": 31620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31620, "total_transitions": 129515520, "num_steps_per_env": 1, "wm_loss": 0.45488786697387695, "actor_loss": -8.808631896972656, "critic_loss": 0.03189524635672569, "reward": 0.07034658640623093, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2482861876487732, 0.15455810725688934, 0.2519437372684479], "policy_updates": 31520, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4629.923971274, "contact_bce": 0.31953924894332886, "contact_force_loss": 0.032629042863845825, "terrain_level_mean": 3.0947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} {"step": 31630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31630, "total_transitions": 129556480, "num_steps_per_env": 1, "wm_loss": 0.4734891355037689, "actor_loss": -8.77636432647705, "critic_loss": 0.034324195235967636, "reward": 0.07023508846759796, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2478993684053421, 0.15527881681919098, 0.25243327021598816], "policy_updates": 31530, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4633.448135901, "contact_bce": 0.3264309763908386, "contact_force_loss": 0.03306322544813156, "terrain_level_mean": 3.0966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} {"step": 31640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31640, "total_transitions": 129597440, "num_steps_per_env": 1, "wm_loss": 0.4275597929954529, "actor_loss": -8.792457580566406, "critic_loss": 0.025127535685896873, "reward": 0.07133032381534576, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2418670654296875, 0.1530209630727768, 0.24598976969718933], "policy_updates": 31540, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4636.966642476999, "contact_bce": 0.3159523606300354, "contact_force_loss": 0.03195035830140114, "terrain_level_mean": 3.09716796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9997668266296387]} {"step": 31650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31650, "total_transitions": 129638400, "num_steps_per_env": 1, "wm_loss": 0.4354415237903595, "actor_loss": -8.759090423583984, "critic_loss": 0.028013085946440697, "reward": 0.07132043689489365, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24440275132656097, 0.15275493264198303, 0.2480676770210266], "policy_updates": 31550, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4640.483736249, "contact_bce": 0.312052458524704, "contact_force_loss": 0.032417818903923035, "terrain_level_mean": 3.097900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31660, "total_transitions": 129679360, "num_steps_per_env": 1, "wm_loss": 0.45524126291275024, "actor_loss": -8.802444458007812, "critic_loss": 0.024981098249554634, "reward": 0.0712079256772995, "falls": 3, "interval_steps": 10, "velocity_mae": [0.243406280875206, 0.15734530985355377, 0.24975226819515228], "policy_updates": 31560, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4644.002897818999, "contact_bce": 0.31803232431411743, "contact_force_loss": 0.03240668773651123, "terrain_level_mean": 3.0986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31670, "total_transitions": 129720320, "num_steps_per_env": 1, "wm_loss": 0.47382062673568726, "actor_loss": -8.776992797851562, "critic_loss": 0.01774507574737072, "reward": 0.07123470306396484, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23872511088848114, 0.15731273591518402, 0.25141164660453796], "policy_updates": 31570, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4647.527643371, "contact_bce": 0.3170340955257416, "contact_force_loss": 0.033229097723960876, "terrain_level_mean": 3.098388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31680, "total_transitions": 129761280, "num_steps_per_env": 1, "wm_loss": 0.44635364413261414, "actor_loss": -8.75374984741211, "critic_loss": 0.03294379636645317, "reward": 0.07119738310575485, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2378770262002945, 0.15912093222141266, 0.2522599697113037], "policy_updates": 31580, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4651.053340384, "contact_bce": 0.3174121379852295, "contact_force_loss": 0.03228515014052391, "terrain_level_mean": 3.09814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31690, "total_transitions": 129802240, "num_steps_per_env": 1, "wm_loss": 0.4711829423904419, "actor_loss": -8.739006042480469, "critic_loss": 0.034596920013427734, "reward": 0.07084830850362778, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2431608885526657, 0.1605331301689148, 0.2550353407859802], "policy_updates": 31590, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4654.575073415999, "contact_bce": 0.3198396861553192, "contact_force_loss": 0.032967884093523026, "terrain_level_mean": 3.097900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31700, "total_transitions": 129843200, "num_steps_per_env": 1, "wm_loss": 0.47644898295402527, "actor_loss": -8.785907745361328, "critic_loss": 0.02582532726228237, "reward": 0.07014480233192444, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2482662945985794, 0.1624094694852829, 0.2537553310394287], "policy_updates": 31600, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4658.090942928, "contact_bce": 0.32170915603637695, "contact_force_loss": 0.033269744366407394, "terrain_level_mean": 3.096923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31710, "total_transitions": 129884160, "num_steps_per_env": 1, "wm_loss": 0.46707165241241455, "actor_loss": -8.783576965332031, "critic_loss": 0.019586272537708282, "reward": 0.070423923432827, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24636560678482056, 0.16263452172279358, 0.25270992517471313], "policy_updates": 31610, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4661.61337449, "contact_bce": 0.3244529366493225, "contact_force_loss": 0.03346392512321472, "terrain_level_mean": 3.096435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31720, "total_transitions": 129925120, "num_steps_per_env": 1, "wm_loss": 0.457105427980423, "actor_loss": -8.782820701599121, "critic_loss": 0.022734764963388443, "reward": 0.07034250348806381, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24702180922031403, 0.16169600188732147, 0.251657634973526], "policy_updates": 31620, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4665.128644654, "contact_bce": 0.32151639461517334, "contact_force_loss": 0.03339225798845291, "terrain_level_mean": 3.09619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31730, "total_transitions": 129966080, "num_steps_per_env": 1, "wm_loss": 0.47258105874061584, "actor_loss": -8.786699295043945, "critic_loss": 0.028462087735533714, "reward": 0.07043717801570892, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24776677787303925, 0.16202391684055328, 0.2533968389034271], "policy_updates": 31630, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4668.639442297, "contact_bce": 0.31502628326416016, "contact_force_loss": 0.03257234767079353, "terrain_level_mean": 3.095458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35986328125, "command_abs_max": [1.9996440410614014, 0.9989186525344849, 2.9956204891204834]} {"step": 31740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31740, "total_transitions": 130007040, "num_steps_per_env": 1, "wm_loss": 0.4480050206184387, "actor_loss": -8.783425331115723, "critic_loss": 0.023000521585345268, "reward": 0.07069041579961777, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24805840849876404, 0.16061526536941528, 0.25415948033332825], "policy_updates": 31640, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4672.161683116, "contact_bce": 0.3200596272945404, "contact_force_loss": 0.03262816742062569, "terrain_level_mean": 3.0966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.9996440410614014, 0.9991536736488342, 2.9956204891204834]} {"step": 31750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31750, "total_transitions": 130048000, "num_steps_per_env": 1, "wm_loss": 0.5162966251373291, "actor_loss": -8.785520553588867, "critic_loss": 0.021427839994430542, "reward": 0.07051679491996765, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24517722427845, 0.15997040271759033, 0.257633775472641], "policy_updates": 31650, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4675.681839084, "contact_bce": 0.3240707516670227, "contact_force_loss": 0.03452162444591522, "terrain_level_mean": 3.095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9956204891204834]} {"step": 31760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31760, "total_transitions": 130088960, "num_steps_per_env": 1, "wm_loss": 0.452510267496109, "actor_loss": -8.78648567199707, "critic_loss": 0.01714615896344185, "reward": 0.07055734843015671, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24143028259277344, 0.16195355355739594, 0.2566220164299011], "policy_updates": 31660, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4679.201283967999, "contact_bce": 0.31587257981300354, "contact_force_loss": 0.03223443403840065, "terrain_level_mean": 3.095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9986791610717773, 0.999610424041748, 2.9956204891204834]} {"step": 31770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31770, "total_transitions": 130129920, "num_steps_per_env": 1, "wm_loss": 0.45986080169677734, "actor_loss": -8.786123275756836, "critic_loss": 0.03298741206526756, "reward": 0.0705970749258995, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2436813861131668, 0.16251303255558014, 0.25391244888305664], "policy_updates": 31670, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4682.724321295999, "contact_bce": 0.31390029191970825, "contact_force_loss": 0.03235752135515213, "terrain_level_mean": 3.094970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9986791610717773, 0.999610424041748, 2.9956204891204834]} {"step": 31780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31780, "total_transitions": 130170880, "num_steps_per_env": 1, "wm_loss": 0.45526787638664246, "actor_loss": -8.761874198913574, "critic_loss": 0.027552349492907524, "reward": 0.070340096950531, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24500560760498047, 0.16081075370311737, 0.2554683983325958], "policy_updates": 31680, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4686.247405243999, "contact_bce": 0.31468939781188965, "contact_force_loss": 0.03220028057694435, "terrain_level_mean": 3.09423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9986791610717773, 0.999610424041748, 2.9951748847961426]} {"step": 31790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31790, "total_transitions": 130211840, "num_steps_per_env": 1, "wm_loss": 0.45276114344596863, "actor_loss": -8.73279094696045, "critic_loss": 0.031463272869586945, "reward": 0.0707847848534584, "falls": 3, "interval_steps": 10, "velocity_mae": [0.242325097322464, 0.16045016050338745, 0.25634363293647766], "policy_updates": 31690, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4689.769269134, "contact_bce": 0.31772324442863464, "contact_force_loss": 0.03244446590542793, "terrain_level_mean": 3.095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9986791610717773, 0.999610424041748, 2.9951748847961426]} {"step": 31800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31800, "total_transitions": 130252800, "num_steps_per_env": 1, "wm_loss": 0.46028465032577515, "actor_loss": -8.759202003479004, "critic_loss": 0.029487282037734985, "reward": 0.07076527178287506, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2458868771791458, 0.1598787158727646, 0.2536628842353821], "policy_updates": 31700, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4693.2958738219995, "contact_bce": 0.3253578543663025, "contact_force_loss": 0.033273495733737946, "terrain_level_mean": 3.095947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9986791610717773, 0.999610424041748, 2.9951748847961426]} {"step": 31810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31810, "total_transitions": 130293760, "num_steps_per_env": 1, "wm_loss": 0.44898292422294617, "actor_loss": -8.76876449584961, "critic_loss": 0.032870739698410034, "reward": 0.07087438553571701, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2504799962043762, 0.15960955619812012, 0.25694769620895386], "policy_updates": 31710, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4696.813446034, "contact_bce": 0.3178445100784302, "contact_force_loss": 0.03256048262119293, "terrain_level_mean": 3.096435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31820, "total_transitions": 130334720, "num_steps_per_env": 1, "wm_loss": 0.47625696659088135, "actor_loss": -8.737930297851562, "critic_loss": 0.03586959466338158, "reward": 0.07071761041879654, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2509302496910095, 0.16113795340061188, 0.26183098554611206], "policy_updates": 31720, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4700.333304760999, "contact_bce": 0.31575649976730347, "contact_force_loss": 0.03274928778409958, "terrain_level_mean": 3.09716796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31830, "total_transitions": 130375680, "num_steps_per_env": 1, "wm_loss": 0.48155486583709717, "actor_loss": -8.79629898071289, "critic_loss": 0.02693072520196438, "reward": 0.07067493349313736, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25099968910217285, 0.1583123654127121, 0.25859153270721436], "policy_updates": 31730, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4703.849752106999, "contact_bce": 0.31361281871795654, "contact_force_loss": 0.032470494508743286, "terrain_level_mean": 3.09765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31840, "total_transitions": 130416640, "num_steps_per_env": 1, "wm_loss": 0.4494774043560028, "actor_loss": -8.740053176879883, "critic_loss": 0.030506132170557976, "reward": 0.07072736322879791, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24164505302906036, 0.15637902915477753, 0.25495943427085876], "policy_updates": 31740, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4707.3683642529995, "contact_bce": 0.32383599877357483, "contact_force_loss": 0.03352201357483864, "terrain_level_mean": 3.097412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31850, "total_transitions": 130457600, "num_steps_per_env": 1, "wm_loss": 0.46723905205726624, "actor_loss": -8.712103843688965, "critic_loss": 0.026976292952895164, "reward": 0.07095859944820404, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23716893792152405, 0.1562967449426651, 0.25517207384109497], "policy_updates": 31750, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4710.887029367, "contact_bce": 0.3168342709541321, "contact_force_loss": 0.03262760490179062, "terrain_level_mean": 3.0986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31860, "total_transitions": 130498560, "num_steps_per_env": 1, "wm_loss": 0.4920598864555359, "actor_loss": -8.77446174621582, "critic_loss": 0.02591084875166416, "reward": 0.07073718309402466, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24111169576644897, 0.15707339346408844, 0.25792863965034485], "policy_updates": 31760, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4714.398448321999, "contact_bce": 0.3204011917114258, "contact_force_loss": 0.03306497260928154, "terrain_level_mean": 3.098388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31870, "total_transitions": 130539520, "num_steps_per_env": 1, "wm_loss": 0.4721417725086212, "actor_loss": -8.743637084960938, "critic_loss": 0.02596798539161682, "reward": 0.07058151066303253, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24516455829143524, 0.15877753496170044, 0.25989457964897156], "policy_updates": 31770, "skipped_updates": 0, "invalid_env_resets": 34, "elapsed_s": 4717.904422322, "contact_bce": 0.3257312476634979, "contact_force_loss": 0.03297109156847, "terrain_level_mean": 3.098876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} RECOVERY reset 1 invalid environments; first IDs=[2660] {"step": 31880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31880, "total_transitions": 130580480, "num_steps_per_env": 1, "wm_loss": 0.43110892176628113, "actor_loss": -8.796172142028809, "critic_loss": 0.024537747725844383, "reward": 0.07068159431219101, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24656158685684204, 0.1600007861852646, 0.2570617198944092], "policy_updates": 31780, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4721.436044002, "contact_bce": 0.318912148475647, "contact_force_loss": 0.032369215041399, "terrain_level_mean": 3.097900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31890, "total_transitions": 130621440, "num_steps_per_env": 1, "wm_loss": 0.46182960271835327, "actor_loss": -8.772884368896484, "critic_loss": 0.02756768837571144, "reward": 0.0705597922205925, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2468889206647873, 0.15948577225208282, 0.2539713978767395], "policy_updates": 31790, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4724.963102387999, "contact_bce": 0.32109448313713074, "contact_force_loss": 0.032752569764852524, "terrain_level_mean": 3.098876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31900, "total_transitions": 130662400, "num_steps_per_env": 1, "wm_loss": 0.44894224405288696, "actor_loss": -8.81939697265625, "critic_loss": 0.016702715307474136, "reward": 0.07039492577314377, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24625754356384277, 0.16073718667030334, 0.2518543004989624], "policy_updates": 31800, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4728.48348931, "contact_bce": 0.31769952178001404, "contact_force_loss": 0.032701026648283005, "terrain_level_mean": 3.099853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9951748847961426]} {"step": 31910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31910, "total_transitions": 130703360, "num_steps_per_env": 1, "wm_loss": 0.45746704936027527, "actor_loss": -8.770633697509766, "critic_loss": 0.0286452267318964, "reward": 0.07032574713230133, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24121616780757904, 0.16028831899166107, 0.25187525153160095], "policy_updates": 31810, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4731.995972629, "contact_bce": 0.3257178068161011, "contact_force_loss": 0.03241274505853653, "terrain_level_mean": 3.099365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.994969367980957]} {"step": 31920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31920, "total_transitions": 130744320, "num_steps_per_env": 1, "wm_loss": 0.45710790157318115, "actor_loss": -8.774999618530273, "critic_loss": 0.018422860652208328, "reward": 0.0706987977027893, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24028067290782928, 0.16420836746692657, 0.24969351291656494], "policy_updates": 31820, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4735.500670171999, "contact_bce": 0.3276682496070862, "contact_force_loss": 0.03292542323470116, "terrain_level_mean": 3.099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9968234300613403, 0.999610424041748, 2.9972996711730957]} {"step": 31930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31930, "total_transitions": 130785280, "num_steps_per_env": 1, "wm_loss": 0.4719740152359009, "actor_loss": -8.764698028564453, "critic_loss": 0.020762065425515175, "reward": 0.07067500799894333, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24007390439510345, 0.1640685647726059, 0.25273123383522034], "policy_updates": 31830, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4739.006823522999, "contact_bce": 0.32191532850265503, "contact_force_loss": 0.032917995005846024, "terrain_level_mean": 3.1015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9935557842254639, 0.999610424041748, 2.9972996711730957]} {"step": 31940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31940, "total_transitions": 130826240, "num_steps_per_env": 1, "wm_loss": 0.45549577474594116, "actor_loss": -8.74968433380127, "critic_loss": 0.028579354286193848, "reward": 0.07046275585889816, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24400103092193604, 0.16391023993492126, 0.25363513827323914], "policy_updates": 31840, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4742.520889169, "contact_bce": 0.31912145018577576, "contact_force_loss": 0.03329770639538765, "terrain_level_mean": 3.1015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9935557842254639, 0.999610424041748, 2.9972996711730957]} {"step": 31950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31950, "total_transitions": 130867200, "num_steps_per_env": 1, "wm_loss": 0.4717545211315155, "actor_loss": -8.752456665039062, "critic_loss": 0.020982271060347557, "reward": 0.0702984482049942, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24336466193199158, 0.16263380646705627, 0.25434234738349915], "policy_updates": 31850, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4746.039902433, "contact_bce": 0.3151760697364807, "contact_force_loss": 0.03251727297902107, "terrain_level_mean": 3.102294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9935557842254639, 0.999610424041748, 2.9972996711730957]} {"step": 31960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31960, "total_transitions": 130908160, "num_steps_per_env": 1, "wm_loss": 0.49430593848228455, "actor_loss": -8.761752128601074, "critic_loss": 0.025656048208475113, "reward": 0.0702945813536644, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24237936735153198, 0.1594891995191574, 0.2557825744152069], "policy_updates": 31860, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4749.55519121, "contact_bce": 0.3220214247703552, "contact_force_loss": 0.03330489993095398, "terrain_level_mean": 3.1005859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9935557842254639, 0.999610424041748, 2.9972996711730957]} {"step": 31970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31970, "total_transitions": 130949120, "num_steps_per_env": 1, "wm_loss": 0.45633164048194885, "actor_loss": -8.73476791381836, "critic_loss": 0.023135021328926086, "reward": 0.07007308304309845, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24047987163066864, 0.16073882579803467, 0.25971052050590515], "policy_updates": 31870, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4753.063627674, "contact_bce": 0.3140719532966614, "contact_force_loss": 0.03213808313012123, "terrain_level_mean": 3.10107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9978151321411133, 0.999610424041748, 2.9972996711730957]} {"step": 31980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31980, "total_transitions": 130990080, "num_steps_per_env": 1, "wm_loss": 0.5009689331054688, "actor_loss": -8.724313735961914, "critic_loss": 0.02326543629169464, "reward": 0.07017768174409866, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2453591227531433, 0.162088543176651, 0.2585390508174896], "policy_updates": 31880, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4756.5695131639995, "contact_bce": 0.3207949101924896, "contact_force_loss": 0.03365660086274147, "terrain_level_mean": 3.100830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9978151321411133, 0.999610424041748, 2.9972996711730957]} {"step": 31990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 31990, "total_transitions": 131031040, "num_steps_per_env": 1, "wm_loss": 0.44176679849624634, "actor_loss": -8.740110397338867, "critic_loss": 0.021435031667351723, "reward": 0.07040482014417648, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24459248781204224, 0.16203227639198303, 0.2584361433982849], "policy_updates": 31890, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4760.08192151, "contact_bce": 0.31597766280174255, "contact_force_loss": 0.03195453807711601, "terrain_level_mean": 3.10107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9978151321411133, 0.999610424041748, 2.9972996711730957]} {"step": 32000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32000, "total_transitions": 131072000, "num_steps_per_env": 1, "wm_loss": 0.4531785249710083, "actor_loss": -8.764163970947266, "critic_loss": 0.03461761772632599, "reward": 0.0708567425608635, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24560552835464478, 0.1593771129846573, 0.2542870044708252], "policy_updates": 31900, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4763.605221780999, "contact_bce": 0.31468820571899414, "contact_force_loss": 0.03201118856668472, "terrain_level_mean": 3.100830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9978151321411133, 0.999610424041748, 2.9972996711730957]} {"step": 32010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32010, "total_transitions": 131112960, "num_steps_per_env": 1, "wm_loss": 0.4763824939727783, "actor_loss": -8.775397300720215, "critic_loss": 0.024552715942263603, "reward": 0.07127679139375687, "falls": 3, "interval_steps": 10, "velocity_mae": [0.244219571352005, 0.1551685333251953, 0.25522127747535706], "policy_updates": 31910, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4767.157003218, "contact_bce": 0.31829962134361267, "contact_force_loss": 0.03307018429040909, "terrain_level_mean": 3.101806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9978151321411133, 0.999610424041748, 2.9972996711730957]} {"step": 32020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32020, "total_transitions": 131153920, "num_steps_per_env": 1, "wm_loss": 0.47338923811912537, "actor_loss": -8.750555992126465, "critic_loss": 0.024371352046728134, "reward": 0.07125344127416611, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24442081153392792, 0.15533092617988586, 0.2552647292613983], "policy_updates": 31920, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4770.676442434999, "contact_bce": 0.3126126825809479, "contact_force_loss": 0.032998234033584595, "terrain_level_mean": 3.10205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9978151321411133, 0.999610424041748, 2.9972996711730957]} {"step": 32030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32030, "total_transitions": 131194880, "num_steps_per_env": 1, "wm_loss": 0.49643874168395996, "actor_loss": -8.794795989990234, "critic_loss": 0.01912977360188961, "reward": 0.07108946889638901, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2443138062953949, 0.15857750177383423, 0.2568512260913849], "policy_updates": 31930, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4774.438568373999, "contact_bce": 0.3198994994163513, "contact_force_loss": 0.03338555246591568, "terrain_level_mean": 3.103271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.9972996711730957]} {"step": 32040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32040, "total_transitions": 131235840, "num_steps_per_env": 1, "wm_loss": 0.47513896226882935, "actor_loss": -8.790193557739258, "critic_loss": 0.040026381611824036, "reward": 0.07095285505056381, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24950067698955536, 0.1628115028142929, 0.25634706020355225], "policy_updates": 31940, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4777.9564247729995, "contact_bce": 0.31676939129829407, "contact_force_loss": 0.03254792466759682, "terrain_level_mean": 3.10302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32050, "total_transitions": 131276800, "num_steps_per_env": 1, "wm_loss": 0.48998767137527466, "actor_loss": -8.738566398620605, "critic_loss": 0.028499145060777664, "reward": 0.07137831300497055, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25071150064468384, 0.15993429720401764, 0.25446900725364685], "policy_updates": 31950, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4781.478981478, "contact_bce": 0.3205770254135132, "contact_force_loss": 0.032545655965805054, "terrain_level_mean": 3.1025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32060, "total_transitions": 131317760, "num_steps_per_env": 1, "wm_loss": 0.46272093057632446, "actor_loss": -8.786395072937012, "critic_loss": 0.026695597916841507, "reward": 0.07135610282421112, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25048983097076416, 0.16130907833576202, 0.25495290756225586], "policy_updates": 31960, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4784.998418097, "contact_bce": 0.31758245825767517, "contact_force_loss": 0.032439012080430984, "terrain_level_mean": 3.103515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32070, "total_transitions": 131358720, "num_steps_per_env": 1, "wm_loss": 0.49696752429008484, "actor_loss": -8.739277839660645, "critic_loss": 0.032102540135383606, "reward": 0.07118641585111618, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2498410940170288, 0.1609179973602295, 0.2605454623699188], "policy_updates": 31970, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4788.508893325, "contact_bce": 0.32050350308418274, "contact_force_loss": 0.03360280767083168, "terrain_level_mean": 3.103271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32080, "total_transitions": 131399680, "num_steps_per_env": 1, "wm_loss": 0.45799222588539124, "actor_loss": -8.78018569946289, "critic_loss": 0.024148045107722282, "reward": 0.07133284956216812, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24868585169315338, 0.15898264944553375, 0.2577279508113861], "policy_updates": 31980, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4792.030077589, "contact_bce": 0.3157341480255127, "contact_force_loss": 0.03231945261359215, "terrain_level_mean": 3.10302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32090, "total_transitions": 131440640, "num_steps_per_env": 1, "wm_loss": 0.45396581292152405, "actor_loss": -8.745162010192871, "critic_loss": 0.03070056438446045, "reward": 0.07162892073392868, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2425590604543686, 0.1595357209444046, 0.25264501571655273], "policy_updates": 31990, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4795.551253930999, "contact_bce": 0.3213491439819336, "contact_force_loss": 0.03243454173207283, "terrain_level_mean": 3.103759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32100, "total_transitions": 131481600, "num_steps_per_env": 1, "wm_loss": 0.49106767773628235, "actor_loss": -8.743019104003906, "critic_loss": 0.02692616544663906, "reward": 0.0712248906493187, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2454880028963089, 0.16082699596881866, 0.25529128313064575], "policy_updates": 32000, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4799.064201949, "contact_bce": 0.32331347465515137, "contact_force_loss": 0.03367557376623154, "terrain_level_mean": 3.104248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32110, "total_transitions": 131522560, "num_steps_per_env": 1, "wm_loss": 0.47142890095710754, "actor_loss": -8.799067497253418, "critic_loss": 0.022590145468711853, "reward": 0.07108718156814575, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2462085634469986, 0.16196328401565552, 0.2549804449081421], "policy_updates": 32010, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4802.579748962, "contact_bce": 0.318691223859787, "contact_force_loss": 0.032277729362249374, "terrain_level_mean": 3.10498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9989820718765259, 0.999610424041748, 2.997541666030884]} {"step": 32120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32120, "total_transitions": 131563520, "num_steps_per_env": 1, "wm_loss": 0.44207409024238586, "actor_loss": -8.741180419921875, "critic_loss": 0.024822821840643883, "reward": 0.0708763599395752, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24934789538383484, 0.1610998958349228, 0.2593686878681183], "policy_updates": 32020, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4806.093133599, "contact_bce": 0.31335219740867615, "contact_force_loss": 0.03321123868227005, "terrain_level_mean": 3.10498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9992979764938354, 0.999610424041748, 2.997541666030884]} {"step": 32130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32130, "total_transitions": 131604480, "num_steps_per_env": 1, "wm_loss": 0.45266610383987427, "actor_loss": -8.741336822509766, "critic_loss": 0.02271822653710842, "reward": 0.07071802765130997, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2483171820640564, 0.15956752002239227, 0.25767746567726135], "policy_updates": 32030, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4809.5968133569995, "contact_bce": 0.3242967128753662, "contact_force_loss": 0.03340631350874901, "terrain_level_mean": 3.104736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9992979764938354, 0.999610424041748, 2.997541666030884]} {"step": 32140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32140, "total_transitions": 131645440, "num_steps_per_env": 1, "wm_loss": 0.4656864404678345, "actor_loss": -8.769396781921387, "critic_loss": 0.024340981617569923, "reward": 0.07067697495222092, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24468031525611877, 0.16000549495220184, 0.25912413001060486], "policy_updates": 32040, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4813.0993896459995, "contact_bce": 0.3209075927734375, "contact_force_loss": 0.032777346670627594, "terrain_level_mean": 3.104248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9992979764938354, 0.9992828369140625, 2.997541666030884]} {"step": 32150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32150, "total_transitions": 131686400, "num_steps_per_env": 1, "wm_loss": 0.4565390348434448, "actor_loss": -8.77140998840332, "critic_loss": 0.020817674696445465, "reward": 0.07051780074834824, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24656382203102112, 0.16070610284805298, 0.2545434832572937], "policy_updates": 32050, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4816.620506538, "contact_bce": 0.31604328751564026, "contact_force_loss": 0.032890208065509796, "terrain_level_mean": 3.103515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9992979764938354, 0.9992828369140625, 2.997541666030884]} {"step": 32160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32160, "total_transitions": 131727360, "num_steps_per_env": 1, "wm_loss": 0.45662593841552734, "actor_loss": -8.804155349731445, "critic_loss": 0.025945330038666725, "reward": 0.07110612839460373, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24663573503494263, 0.16064727306365967, 0.25602245330810547], "policy_updates": 32060, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4820.145374492, "contact_bce": 0.31552189588546753, "contact_force_loss": 0.032827772200107574, "terrain_level_mean": 3.105224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9992979764938354, 0.9992828369140625, 2.997541666030884]} {"step": 32170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32170, "total_transitions": 131768320, "num_steps_per_env": 1, "wm_loss": 0.4891301989555359, "actor_loss": -8.769038200378418, "critic_loss": 0.025452107191085815, "reward": 0.07113730162382126, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24626967310905457, 0.15838877856731415, 0.2577344477176666], "policy_updates": 32070, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4823.659136857999, "contact_bce": 0.31999045610427856, "contact_force_loss": 0.032893210649490356, "terrain_level_mean": 3.10498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9992979764938354, 0.9992828369140625, 2.997541666030884]} {"step": 32180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32180, "total_transitions": 131809280, "num_steps_per_env": 1, "wm_loss": 0.49316859245300293, "actor_loss": -8.73847770690918, "critic_loss": 0.03419497236609459, "reward": 0.07103461772203445, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24730134010314941, 0.1591024547815323, 0.25726351141929626], "policy_updates": 32080, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4827.175649793, "contact_bce": 0.3202316164970398, "contact_force_loss": 0.033587414771318436, "terrain_level_mean": 3.105224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9995300769805908, 0.9992828369140625, 2.997541666030884]} {"step": 32190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32190, "total_transitions": 131850240, "num_steps_per_env": 1, "wm_loss": 0.4655120074748993, "actor_loss": -8.731098175048828, "critic_loss": 0.03895397484302521, "reward": 0.07120224088430405, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24607914686203003, 0.15822824835777283, 0.2513532042503357], "policy_updates": 32090, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4830.688859045999, "contact_bce": 0.32112088799476624, "contact_force_loss": 0.03322361409664154, "terrain_level_mean": 3.105712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9995300769805908, 0.9992828369140625, 2.997541666030884]} {"step": 32200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32200, "total_transitions": 131891200, "num_steps_per_env": 1, "wm_loss": 0.47731539607048035, "actor_loss": -8.773069381713867, "critic_loss": 0.019068589434027672, "reward": 0.07076827436685562, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24780036509037018, 0.15858450531959534, 0.2546323537826538], "policy_updates": 32100, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4834.195458059, "contact_bce": 0.31399795413017273, "contact_force_loss": 0.03235770761966705, "terrain_level_mean": 3.10693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9995300769805908, 0.9992828369140625, 2.997541666030884]} {"step": 32210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32210, "total_transitions": 131932160, "num_steps_per_env": 1, "wm_loss": 0.45312342047691345, "actor_loss": -8.767295837402344, "critic_loss": 0.027551764622330666, "reward": 0.07016853243112564, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2490725964307785, 0.15879203379154205, 0.2585403323173523], "policy_updates": 32110, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4837.711290212999, "contact_bce": 0.31301528215408325, "contact_force_loss": 0.032236721366643906, "terrain_level_mean": 3.106689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9995300769805908, 0.9973694086074829, 2.997541666030884]} {"step": 32220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32220, "total_transitions": 131973120, "num_steps_per_env": 1, "wm_loss": 0.4896722733974457, "actor_loss": -8.734956741333008, "critic_loss": 0.027756381779909134, "reward": 0.07047183811664581, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2490113377571106, 0.15828937292099, 0.256915420293808], "policy_updates": 32120, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4841.2360889209995, "contact_bce": 0.31985917687416077, "contact_force_loss": 0.03327804431319237, "terrain_level_mean": 3.107666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9995300769805908, 0.9973694086074829, 2.997541666030884]} {"step": 32230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32230, "total_transitions": 132014080, "num_steps_per_env": 1, "wm_loss": 0.49762028455734253, "actor_loss": -8.744071960449219, "critic_loss": 0.029622619971632957, "reward": 0.0707535520195961, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25500810146331787, 0.15671829879283905, 0.25629860162734985], "policy_updates": 32130, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4844.753622517, "contact_bce": 0.32030048966407776, "contact_force_loss": 0.03352528437972069, "terrain_level_mean": 3.107177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9995300769805908, 0.9973694086074829, 2.997541666030884]} {"step": 32240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32240, "total_transitions": 132055040, "num_steps_per_env": 1, "wm_loss": 0.48145586252212524, "actor_loss": -8.81052017211914, "critic_loss": 0.022927721962332726, "reward": 0.07034279406070709, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25577741861343384, 0.15719230473041534, 0.258978009223938], "policy_updates": 32140, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4848.273598381999, "contact_bce": 0.32029640674591064, "contact_force_loss": 0.03343072906136513, "terrain_level_mean": 3.107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9995300769805908, 0.9973694086074829, 2.997541666030884]} {"step": 32250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32250, "total_transitions": 132096000, "num_steps_per_env": 1, "wm_loss": 0.4777708649635315, "actor_loss": -8.812505722045898, "critic_loss": 0.019268495962023735, "reward": 0.07001589983701706, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2578336000442505, 0.16022901237010956, 0.26235565543174744], "policy_updates": 32150, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4851.7942781209995, "contact_bce": 0.32211822271347046, "contact_force_loss": 0.03392449766397476, "terrain_level_mean": 3.107177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.999739170074463, 0.9973694086074829, 2.997541666030884]} {"step": 32260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32260, "total_transitions": 132136960, "num_steps_per_env": 1, "wm_loss": 0.47040021419525146, "actor_loss": -8.737616539001465, "critic_loss": 0.027262574061751366, "reward": 0.06987906992435455, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2564452886581421, 0.15835650265216827, 0.26078367233276367], "policy_updates": 32160, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4855.309842293, "contact_bce": 0.31737563014030457, "contact_force_loss": 0.03302646055817604, "terrain_level_mean": 3.106689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.999739170074463, 0.997870683670044, 2.997541666030884]} {"step": 32270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32270, "total_transitions": 132177920, "num_steps_per_env": 1, "wm_loss": 0.490702360868454, "actor_loss": -8.78041934967041, "critic_loss": 0.020836828276515007, "reward": 0.07076621800661087, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25450995564460754, 0.15996205806732178, 0.25676795840263367], "policy_updates": 32170, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4858.838899034, "contact_bce": 0.3242366313934326, "contact_force_loss": 0.03373878821730614, "terrain_level_mean": 3.106689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.999739170074463, 0.997870683670044, 2.997541666030884]} {"step": 32280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32280, "total_transitions": 132218880, "num_steps_per_env": 1, "wm_loss": 0.45716315507888794, "actor_loss": -8.756181716918945, "critic_loss": 0.02397594414651394, "reward": 0.07064070552587509, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2539059817790985, 0.15981367230415344, 0.2568540871143341], "policy_updates": 32180, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4862.352900632, "contact_bce": 0.3150978982448578, "contact_force_loss": 0.03313979506492615, "terrain_level_mean": 3.106689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.999739170074463, 0.997870683670044, 2.997541666030884]} {"step": 32290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32290, "total_transitions": 132259840, "num_steps_per_env": 1, "wm_loss": 0.467180997133255, "actor_loss": -8.769896507263184, "critic_loss": 0.026985878124833107, "reward": 0.07083196192979813, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24892978370189667, 0.16035151481628418, 0.25937405228614807], "policy_updates": 32190, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4865.868359413, "contact_bce": 0.3153252601623535, "contact_force_loss": 0.03372840955853462, "terrain_level_mean": 3.107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.999739170074463, 0.997870683670044, 2.997541666030884]} {"step": 32300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32300, "total_transitions": 132300800, "num_steps_per_env": 1, "wm_loss": 0.5184940099716187, "actor_loss": -8.77857494354248, "critic_loss": 0.022296970710158348, "reward": 0.07087238878011703, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24714341759681702, 0.15712910890579224, 0.25651487708091736], "policy_updates": 32200, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4869.38928291, "contact_bce": 0.32221853733062744, "contact_force_loss": 0.03394021838903427, "terrain_level_mean": 3.107666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.999739170074463, 0.997870683670044, 2.997541666030884]} {"step": 32310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32310, "total_transitions": 132341760, "num_steps_per_env": 1, "wm_loss": 0.45521578192710876, "actor_loss": -8.722517967224121, "critic_loss": 0.04647165164351463, "reward": 0.0712524875998497, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24524131417274475, 0.1553993970155716, 0.254250705242157], "policy_updates": 32210, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4872.906213308999, "contact_bce": 0.3245299756526947, "contact_force_loss": 0.03298128768801689, "terrain_level_mean": 3.107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.999739170074463, 0.997870683670044, 2.997541666030884]} {"step": 32320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32320, "total_transitions": 132382720, "num_steps_per_env": 1, "wm_loss": 0.4764811396598816, "actor_loss": -8.749410629272461, "critic_loss": 0.03216671943664551, "reward": 0.07141382992267609, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24345073103904724, 0.15932577848434448, 0.2553575038909912], "policy_updates": 32220, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4876.417671782, "contact_bce": 0.3223174512386322, "contact_force_loss": 0.033040180802345276, "terrain_level_mean": 3.108154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9995300769805908, 0.997870683670044, 2.997541666030884]} {"step": 32330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32330, "total_transitions": 132423680, "num_steps_per_env": 1, "wm_loss": 0.4626349210739136, "actor_loss": -8.740158081054688, "critic_loss": 0.03402051329612732, "reward": 0.07100067287683487, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24552525579929352, 0.15957129001617432, 0.2584632635116577], "policy_updates": 32230, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4879.922527518, "contact_bce": 0.315535306930542, "contact_force_loss": 0.032746005803346634, "terrain_level_mean": 3.108642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9995300769805908, 0.997870683670044, 2.9980459213256836]} {"step": 32340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32340, "total_transitions": 132464640, "num_steps_per_env": 1, "wm_loss": 0.47359952330589294, "actor_loss": -8.755353927612305, "critic_loss": 0.020614204928278923, "reward": 0.07100287079811096, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2433728128671646, 0.15967348217964172, 0.2622852027416229], "policy_updates": 32240, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4883.426278374, "contact_bce": 0.3197309970855713, "contact_force_loss": 0.032668065279722214, "terrain_level_mean": 3.10791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9995300769805908, 0.997870683670044, 2.9980459213256836]} {"step": 32350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32350, "total_transitions": 132505600, "num_steps_per_env": 1, "wm_loss": 0.47756367921829224, "actor_loss": -8.741841316223145, "critic_loss": 0.035158801823854446, "reward": 0.07090803980827332, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24577875435352325, 0.1573668271303177, 0.2616633176803589], "policy_updates": 32250, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4886.937965642999, "contact_bce": 0.31925806403160095, "contact_force_loss": 0.03305589407682419, "terrain_level_mean": 3.107177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9995300769805908, 0.997870683670044, 2.9980459213256836]} {"step": 32360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32360, "total_transitions": 132546560, "num_steps_per_env": 1, "wm_loss": 0.4705972373485565, "actor_loss": -8.73985481262207, "critic_loss": 0.025282246991991997, "reward": 0.07105255126953125, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24811309576034546, 0.15762944519519806, 0.25532281398773193], "policy_updates": 32260, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4890.451573220999, "contact_bce": 0.31856754422187805, "contact_force_loss": 0.03311154246330261, "terrain_level_mean": 3.107177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9995300769805908, 0.9990408420562744, 2.9980459213256836]} {"step": 32370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32370, "total_transitions": 132587520, "num_steps_per_env": 1, "wm_loss": 0.5168601870536804, "actor_loss": -8.734058380126953, "critic_loss": 0.02647458389401436, "reward": 0.07075851410627365, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25008323788642883, 0.16085870563983917, 0.261187881231308], "policy_updates": 32270, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4893.958946926, "contact_bce": 0.32329466938972473, "contact_force_loss": 0.032844312489032745, "terrain_level_mean": 3.10693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9995300769805908, 0.9990408420562744, 2.9980459213256836]} {"step": 32380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32380, "total_transitions": 132628480, "num_steps_per_env": 1, "wm_loss": 0.46492624282836914, "actor_loss": -8.771389961242676, "critic_loss": 0.018859738484025, "reward": 0.07105358690023422, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25068792700767517, 0.157819464802742, 0.25838005542755127], "policy_updates": 32280, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4897.468631168, "contact_bce": 0.3205593228340149, "contact_force_loss": 0.03355737775564194, "terrain_level_mean": 3.107177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9995300769805908, 0.9997252225875854, 2.9980459213256836]} {"step": 32390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32390, "total_transitions": 132669440, "num_steps_per_env": 1, "wm_loss": 0.46885207295417786, "actor_loss": -8.759312629699707, "critic_loss": 0.034187253564596176, "reward": 0.07064918428659439, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24932438135147095, 0.15672427415847778, 0.2625667452812195], "policy_updates": 32290, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4900.9748255429995, "contact_bce": 0.31978967785835266, "contact_force_loss": 0.033427461981773376, "terrain_level_mean": 3.107177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9995300769805908, 0.999914288520813, 2.9980459213256836]} {"step": 32400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32400, "total_transitions": 132710400, "num_steps_per_env": 1, "wm_loss": 0.46621158719062805, "actor_loss": -8.810449600219727, "critic_loss": 0.021763144060969353, "reward": 0.07072099298238754, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25157630443573, 0.15987464785575867, 0.25882914662361145], "policy_updates": 32300, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4904.486397172, "contact_bce": 0.31508055329322815, "contact_force_loss": 0.033173758536577225, "terrain_level_mean": 3.108154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9995300769805908, 0.999914288520813, 2.9980459213256836]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_032400.mp4 {"step": 32410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32410, "total_transitions": 132751360, "num_steps_per_env": 1, "wm_loss": 0.48675286769866943, "actor_loss": -8.777546882629395, "critic_loss": 0.020839126780629158, "reward": 0.07075474411249161, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24871233105659485, 0.1626303493976593, 0.25688549876213074], "policy_updates": 32310, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4913.791930453, "contact_bce": 0.3205586373806, "contact_force_loss": 0.0332336351275444, "terrain_level_mean": 3.107666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9995300769805908, 0.999914288520813, 2.9980459213256836]} {"step": 32420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32420, "total_transitions": 132792320, "num_steps_per_env": 1, "wm_loss": 0.4607295095920563, "actor_loss": -8.745591163635254, "critic_loss": 0.023928944021463394, "reward": 0.0704219862818718, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2505688965320587, 0.16140207648277283, 0.2550937533378601], "policy_updates": 32320, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4917.292208037, "contact_bce": 0.3165389597415924, "contact_force_loss": 0.03296520560979843, "terrain_level_mean": 3.1064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9995300769805908, 0.999914288520813, 2.9980459213256836]} {"step": 32430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32430, "total_transitions": 132833280, "num_steps_per_env": 1, "wm_loss": 0.4450899660587311, "actor_loss": -8.741170883178711, "critic_loss": 0.029221324250102043, "reward": 0.07042108476161957, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2523399889469147, 0.1629267781972885, 0.2619647681713104], "policy_updates": 32330, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4920.798111513999, "contact_bce": 0.31449273228645325, "contact_force_loss": 0.0321604385972023, "terrain_level_mean": 3.106689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9995300769805908, 0.999914288520813, 2.9980459213256836]} {"step": 32440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32440, "total_transitions": 132874240, "num_steps_per_env": 1, "wm_loss": 0.5151773691177368, "actor_loss": -8.80098819732666, "critic_loss": 0.026427460834383965, "reward": 0.07034283131361008, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2519216239452362, 0.16405066847801208, 0.2623297870159149], "policy_updates": 32340, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4924.299367803999, "contact_bce": 0.3212159276008606, "contact_force_loss": 0.03275826573371887, "terrain_level_mean": 3.106201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9995300769805908, 0.999914288520813, 2.9980459213256836]} {"step": 32450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32450, "total_transitions": 132915200, "num_steps_per_env": 1, "wm_loss": 0.4769452214241028, "actor_loss": -8.776350975036621, "critic_loss": 0.026225829496979713, "reward": 0.07059891521930695, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24869754910469055, 0.16272829473018646, 0.2563517987728119], "policy_updates": 32350, "skipped_updates": 0, "invalid_env_resets": 35, "elapsed_s": 4927.805456587, "contact_bce": 0.32380688190460205, "contact_force_loss": 0.03381902351975441, "terrain_level_mean": 3.10595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9995300769805908, 0.9997252225875854, 2.9980459213256836]} RECOVERY reset 1 invalid environments; first IDs=[2322] {"step": 32460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32460, "total_transitions": 132956160, "num_steps_per_env": 1, "wm_loss": 0.4775744080543518, "actor_loss": -8.750274658203125, "critic_loss": 0.028343671932816505, "reward": 0.07089074701070786, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2432180494070053, 0.16176466643810272, 0.2564517557621002], "policy_updates": 32360, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4931.341532726, "contact_bce": 0.3200680613517761, "contact_force_loss": 0.03301633521914482, "terrain_level_mean": 3.10595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9995300769805908, 0.9997252225875854, 2.9980459213256836]} {"step": 32470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32470, "total_transitions": 132997120, "num_steps_per_env": 1, "wm_loss": 0.4585401117801666, "actor_loss": -8.7509765625, "critic_loss": 0.029307056218385696, "reward": 0.07075408846139908, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24381263554096222, 0.1591414213180542, 0.25760626792907715], "policy_updates": 32370, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4934.858172572, "contact_bce": 0.32152891159057617, "contact_force_loss": 0.03344932198524475, "terrain_level_mean": 3.107666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9995300769805908, 0.9997252225875854, 2.9980459213256836]} {"step": 32480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32480, "total_transitions": 133038080, "num_steps_per_env": 1, "wm_loss": 0.4703986346721649, "actor_loss": -8.763429641723633, "critic_loss": 0.030943667516112328, "reward": 0.0707252249121666, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24588918685913086, 0.15960851311683655, 0.2550291419029236], "policy_updates": 32380, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4938.375045055999, "contact_bce": 0.31860002875328064, "contact_force_loss": 0.03403381630778313, "terrain_level_mean": 3.107666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9995300769805908, 0.9997252225875854, 2.9980459213256836]} {"step": 32490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32490, "total_transitions": 133079040, "num_steps_per_env": 1, "wm_loss": 0.4799155592918396, "actor_loss": -8.756006240844727, "critic_loss": 0.02945469319820404, "reward": 0.07018270343542099, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24724239110946655, 0.16100028157234192, 0.25346148014068604], "policy_updates": 32390, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4941.899466575999, "contact_bce": 0.3229787349700928, "contact_force_loss": 0.03353140130639076, "terrain_level_mean": 3.108642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9995300769805908, 0.9997252225875854, 2.9980459213256836]} {"step": 32500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32500, "total_transitions": 133120000, "num_steps_per_env": 1, "wm_loss": 0.4396078586578369, "actor_loss": -8.72958755493164, "critic_loss": 0.027368692681193352, "reward": 0.07031779736280441, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25053146481513977, 0.1604921668767929, 0.25377652049064636], "policy_updates": 32400, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4945.423169891, "contact_bce": 0.31656625866889954, "contact_force_loss": 0.033170271664857864, "terrain_level_mean": 3.10986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.9980459213256836]} {"step": 32510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32510, "total_transitions": 133160960, "num_steps_per_env": 1, "wm_loss": 0.47512707114219666, "actor_loss": -8.786283493041992, "critic_loss": 0.02368616871535778, "reward": 0.07010110467672348, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25451788306236267, 0.16089582443237305, 0.25642794370651245], "policy_updates": 32410, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4948.956803890999, "contact_bce": 0.3210715651512146, "contact_force_loss": 0.03397459536790848, "terrain_level_mean": 3.109130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.9980459213256836]} {"step": 32520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32520, "total_transitions": 133201920, "num_steps_per_env": 1, "wm_loss": 0.47241660952568054, "actor_loss": -8.725748062133789, "critic_loss": 0.0261060893535614, "reward": 0.07065512984991074, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25215473771095276, 0.16045334935188293, 0.2556437849998474], "policy_updates": 32420, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4952.727660126, "contact_bce": 0.31989383697509766, "contact_force_loss": 0.03334841504693031, "terrain_level_mean": 3.109130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32530, "total_transitions": 133242880, "num_steps_per_env": 1, "wm_loss": 0.4895601272583008, "actor_loss": -8.736204147338867, "critic_loss": 0.029222864657640457, "reward": 0.07039260864257812, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25093188881874084, 0.15974734723567963, 0.2555069923400879], "policy_updates": 32430, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4956.241142921999, "contact_bce": 0.31965333223342896, "contact_force_loss": 0.03331517428159714, "terrain_level_mean": 3.109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32540, "total_transitions": 133283840, "num_steps_per_env": 1, "wm_loss": 0.46448296308517456, "actor_loss": -8.793601989746094, "critic_loss": 0.0182527843862772, "reward": 0.07075761258602142, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24676309525966644, 0.15924516320228577, 0.2514932453632355], "policy_updates": 32440, "skipped_updates": 0, "invalid_env_resets": 36, "elapsed_s": 4959.766862234999, "contact_bce": 0.32430312037467957, "contact_force_loss": 0.03265469893813133, "terrain_level_mean": 3.111083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} RECOVERY reset 1 invalid environments; first IDs=[1606] {"step": 32550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32550, "total_transitions": 133324800, "num_steps_per_env": 1, "wm_loss": 0.4647829234600067, "actor_loss": -8.773445129394531, "critic_loss": 0.023320382460951805, "reward": 0.0706370621919632, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24720388650894165, 0.15743695199489594, 0.25173506140708923], "policy_updates": 32450, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4963.307020144, "contact_bce": 0.3245876729488373, "contact_force_loss": 0.03291976824402809, "terrain_level_mean": 3.111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32560, "total_transitions": 133365760, "num_steps_per_env": 1, "wm_loss": 0.486551433801651, "actor_loss": -8.723588943481445, "critic_loss": 0.027648476883769035, "reward": 0.07082582265138626, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24648739397525787, 0.15816369652748108, 0.2511233389377594], "policy_updates": 32460, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4966.833717812, "contact_bce": 0.3163257837295532, "contact_force_loss": 0.032362714409828186, "terrain_level_mean": 3.112548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32570, "total_transitions": 133406720, "num_steps_per_env": 1, "wm_loss": 0.494402140378952, "actor_loss": -8.776135444641113, "critic_loss": 0.021694034337997437, "reward": 0.07108890265226364, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24576105177402496, 0.15716241300106049, 0.255044549703598], "policy_updates": 32470, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4970.360823184999, "contact_bce": 0.31786566972732544, "contact_force_loss": 0.033409081399440765, "terrain_level_mean": 3.112548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32580, "total_transitions": 133447680, "num_steps_per_env": 1, "wm_loss": 0.4843016266822815, "actor_loss": -8.804529190063477, "critic_loss": 0.024646161124110222, "reward": 0.07075449824333191, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24649357795715332, 0.15983138978481293, 0.2542489767074585], "policy_updates": 32480, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4973.882079968999, "contact_bce": 0.31859493255615234, "contact_force_loss": 0.03391575440764427, "terrain_level_mean": 3.11181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32590, "total_transitions": 133488640, "num_steps_per_env": 1, "wm_loss": 0.4668807089328766, "actor_loss": -8.782203674316406, "critic_loss": 0.02612636797130108, "reward": 0.0709400400519371, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24461491405963898, 0.15902619063854218, 0.2537899613380432], "policy_updates": 32490, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4977.399943134, "contact_bce": 0.322156697511673, "contact_force_loss": 0.033480171114206314, "terrain_level_mean": 3.113037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32600, "total_transitions": 133529600, "num_steps_per_env": 1, "wm_loss": 0.47257158160209656, "actor_loss": -8.735687255859375, "critic_loss": 0.02914137952029705, "reward": 0.07136180251836777, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24303755164146423, 0.15798453986644745, 0.2524094879627228], "policy_updates": 32500, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4980.927296358999, "contact_bce": 0.3158954977989197, "contact_force_loss": 0.033136121928691864, "terrain_level_mean": 3.11328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32610, "total_transitions": 133570560, "num_steps_per_env": 1, "wm_loss": 0.4609508514404297, "actor_loss": -8.79437255859375, "critic_loss": 0.020888281986117363, "reward": 0.07149623334407806, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24322065711021423, 0.1597805917263031, 0.2512569725513458], "policy_updates": 32510, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4984.446088498999, "contact_bce": 0.31905701756477356, "contact_force_loss": 0.03324822708964348, "terrain_level_mean": 3.11376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32620, "total_transitions": 133611520, "num_steps_per_env": 1, "wm_loss": 0.4593648612499237, "actor_loss": -8.698994636535645, "critic_loss": 0.029829490929841995, "reward": 0.07125518471002579, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2399023175239563, 0.16047586500644684, 0.2529705762863159], "policy_updates": 32520, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4987.964142424, "contact_bce": 0.31592851877212524, "contact_force_loss": 0.033064208924770355, "terrain_level_mean": 3.11376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32630, "total_transitions": 133652480, "num_steps_per_env": 1, "wm_loss": 0.49777552485466003, "actor_loss": -8.768674850463867, "critic_loss": 0.024118095636367798, "reward": 0.07096102833747864, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24261374771595, 0.16064821183681488, 0.2563939392566681], "policy_updates": 32530, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4991.47721546, "contact_bce": 0.3254474997520447, "contact_force_loss": 0.03365904465317726, "terrain_level_mean": 3.1142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32640, "total_transitions": 133693440, "num_steps_per_env": 1, "wm_loss": 0.44647714495658875, "actor_loss": -8.764598846435547, "critic_loss": 0.035186272114515305, "reward": 0.0709180012345314, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24273978173732758, 0.1617582142353058, 0.25271016359329224], "policy_updates": 32540, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4994.99160338, "contact_bce": 0.3224308490753174, "contact_force_loss": 0.0332040973007679, "terrain_level_mean": 3.11474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.996812582015991]} {"step": 32650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32650, "total_transitions": 133734400, "num_steps_per_env": 1, "wm_loss": 0.4891293942928314, "actor_loss": -8.75005054473877, "critic_loss": 0.02149203233420849, "reward": 0.07067286968231201, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24232691526412964, 0.16265740990638733, 0.25691479444503784], "policy_updates": 32550, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 4998.502906725, "contact_bce": 0.31962138414382935, "contact_force_loss": 0.03331250324845314, "terrain_level_mean": 3.115478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.997880697250366]} {"step": 32660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32660, "total_transitions": 133775360, "num_steps_per_env": 1, "wm_loss": 0.48812854290008545, "actor_loss": -8.749130249023438, "critic_loss": 0.02138420380651951, "reward": 0.07059692591428757, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24506765604019165, 0.16167064011096954, 0.2601264715194702], "policy_updates": 32560, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5002.025007339, "contact_bce": 0.3253321349620819, "contact_force_loss": 0.03287291154265404, "terrain_level_mean": 3.115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.997880697250366]} {"step": 32670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32670, "total_transitions": 133816320, "num_steps_per_env": 1, "wm_loss": 0.44387689232826233, "actor_loss": -8.789009094238281, "critic_loss": 0.03878205642104149, "reward": 0.07093870639801025, "falls": 4, "interval_steps": 10, "velocity_mae": [0.244271919131279, 0.15925218164920807, 0.257337361574173], "policy_updates": 32570, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5005.536718671, "contact_bce": 0.3209085464477539, "contact_force_loss": 0.03324752673506737, "terrain_level_mean": 3.115966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.997880697250366]} {"step": 32680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32680, "total_transitions": 133857280, "num_steps_per_env": 1, "wm_loss": 0.4786801040172577, "actor_loss": -8.717723846435547, "critic_loss": 0.028262028470635414, "reward": 0.07076459378004074, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24659225344657898, 0.15839192271232605, 0.2557680010795593], "policy_updates": 32580, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5009.057729439, "contact_bce": 0.31995004415512085, "contact_force_loss": 0.03368369862437248, "terrain_level_mean": 3.11572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.997880697250366]} {"step": 32690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32690, "total_transitions": 133898240, "num_steps_per_env": 1, "wm_loss": 0.48804256319999695, "actor_loss": -8.740978240966797, "critic_loss": 0.030487269163131714, "reward": 0.07087945938110352, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2505025863647461, 0.15760140120983124, 0.2506940960884094], "policy_updates": 32590, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5012.5723046309995, "contact_bce": 0.3216503858566284, "contact_force_loss": 0.03290582820773125, "terrain_level_mean": 3.116455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9988806247711182, 0.9997252225875854, 2.997880697250366]} {"step": 32700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32700, "total_transitions": 133939200, "num_steps_per_env": 1, "wm_loss": 0.4636775553226471, "actor_loss": -8.761343002319336, "critic_loss": 0.022122422233223915, "reward": 0.07101667672395706, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24839691817760468, 0.1575610488653183, 0.25508612394332886], "policy_updates": 32600, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5016.079485132999, "contact_bce": 0.3186670243740082, "contact_force_loss": 0.03352523222565651, "terrain_level_mean": 3.1171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9988059997558594, 0.9997252225875854, 2.997880697250366]} {"step": 32710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32710, "total_transitions": 133980160, "num_steps_per_env": 1, "wm_loss": 0.43126988410949707, "actor_loss": -8.712677955627441, "critic_loss": 0.03679591789841652, "reward": 0.07092531770467758, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24682128429412842, 0.15814031660556793, 0.2555667757987976], "policy_updates": 32610, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5019.591184616, "contact_bce": 0.3140537738800049, "contact_force_loss": 0.03228433057665825, "terrain_level_mean": 3.118408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32720, "total_transitions": 134021120, "num_steps_per_env": 1, "wm_loss": 0.47546151280403137, "actor_loss": -8.715536117553711, "critic_loss": 0.026410168036818504, "reward": 0.0707923173904419, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24949941039085388, 0.15733091533184052, 0.2525443136692047], "policy_updates": 32620, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5023.098985635999, "contact_bce": 0.31784841418266296, "contact_force_loss": 0.03264279291033745, "terrain_level_mean": 3.11865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32730, "total_transitions": 134062080, "num_steps_per_env": 1, "wm_loss": 0.4600426256656647, "actor_loss": -8.781831741333008, "critic_loss": 0.0301689263433218, "reward": 0.07097233086824417, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24870778620243073, 0.15790985524654388, 0.25343793630599976], "policy_updates": 32630, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5026.609308734, "contact_bce": 0.32094109058380127, "contact_force_loss": 0.03326898813247681, "terrain_level_mean": 3.1201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32740, "total_transitions": 134103040, "num_steps_per_env": 1, "wm_loss": 0.44236353039741516, "actor_loss": -8.741868019104004, "critic_loss": 0.024583274498581886, "reward": 0.07124684751033783, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24641287326812744, 0.1568922996520996, 0.2493949681520462], "policy_updates": 32640, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5030.1342573639995, "contact_bce": 0.31951040029525757, "contact_force_loss": 0.032633814960718155, "terrain_level_mean": 3.11962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32750, "total_transitions": 134144000, "num_steps_per_env": 1, "wm_loss": 0.47101354598999023, "actor_loss": -8.81021785736084, "critic_loss": 0.02771836519241333, "reward": 0.07083705067634583, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24587398767471313, 0.1541902869939804, 0.2557508945465088], "policy_updates": 32650, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5033.655150916999, "contact_bce": 0.3190179765224457, "contact_force_loss": 0.03337157517671585, "terrain_level_mean": 3.1201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32760, "total_transitions": 134184960, "num_steps_per_env": 1, "wm_loss": 0.45642179250717163, "actor_loss": -8.760412216186523, "critic_loss": 0.030415629968047142, "reward": 0.07067056000232697, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2418115735054016, 0.15601931512355804, 0.25353679060935974], "policy_updates": 32660, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5037.171155532999, "contact_bce": 0.3172105848789215, "contact_force_loss": 0.032797180116176605, "terrain_level_mean": 3.1220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32770, "total_transitions": 134225920, "num_steps_per_env": 1, "wm_loss": 0.45144325494766235, "actor_loss": -8.791766166687012, "critic_loss": 0.021482128649950027, "reward": 0.07076310366392136, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2435261607170105, 0.15525710582733154, 0.254968523979187], "policy_updates": 32670, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5040.6861868959995, "contact_bce": 0.32053011655807495, "contact_force_loss": 0.03300204128026962, "terrain_level_mean": 3.123291015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32780, "total_transitions": 134266880, "num_steps_per_env": 1, "wm_loss": 0.49251049757003784, "actor_loss": -8.744613647460938, "critic_loss": 0.02793181501328945, "reward": 0.07069885730743408, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2446952760219574, 0.1580774337053299, 0.25573912262916565], "policy_updates": 32680, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5044.200153033999, "contact_bce": 0.324607789516449, "contact_force_loss": 0.03446858376264572, "terrain_level_mean": 3.124755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330078125, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32790, "total_transitions": 134307840, "num_steps_per_env": 1, "wm_loss": 0.4790564775466919, "actor_loss": -8.753303527832031, "critic_loss": 0.027383306995034218, "reward": 0.07070816308259964, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24527117609977722, 0.15911416709423065, 0.25714758038520813], "policy_updates": 32690, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5047.711816204999, "contact_bce": 0.3195565938949585, "contact_force_loss": 0.033702727407217026, "terrain_level_mean": 3.125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32800, "total_transitions": 134348800, "num_steps_per_env": 1, "wm_loss": 0.4738544225692749, "actor_loss": -8.81009578704834, "critic_loss": 0.019356070086359978, "reward": 0.07104140520095825, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24482326209545135, 0.15835320949554443, 0.2533179819583893], "policy_updates": 32700, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5051.224163205, "contact_bce": 0.32290226221084595, "contact_force_loss": 0.0337708443403244, "terrain_level_mean": 3.125244140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32810, "total_transitions": 134389760, "num_steps_per_env": 1, "wm_loss": 0.4530969560146332, "actor_loss": -8.746814727783203, "critic_loss": 0.022245092317461967, "reward": 0.07087144255638123, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24685627222061157, 0.15781724452972412, 0.2535072863101959], "policy_updates": 32710, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5054.73773067, "contact_bce": 0.3221742808818817, "contact_force_loss": 0.0328584723174572, "terrain_level_mean": 3.12451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32820, "total_transitions": 134430720, "num_steps_per_env": 1, "wm_loss": 0.47895967960357666, "actor_loss": -8.730766296386719, "critic_loss": 0.02475697360932827, "reward": 0.07104680687189102, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24571461975574493, 0.15566249191761017, 0.2525312602519989], "policy_updates": 32720, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5058.258430809, "contact_bce": 0.32268714904785156, "contact_force_loss": 0.03350570797920227, "terrain_level_mean": 3.125244140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9988059997558594, 0.9997230768203735, 2.997880697250366]} {"step": 32830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32830, "total_transitions": 134471680, "num_steps_per_env": 1, "wm_loss": 0.44056832790374756, "actor_loss": -8.72799301147461, "critic_loss": 0.027983535081148148, "reward": 0.07111255079507828, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24276210367679596, 0.1574331820011139, 0.2524675130844116], "policy_updates": 32730, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5061.775895918, "contact_bce": 0.3239269554615021, "contact_force_loss": 0.03268669173121452, "terrain_level_mean": 3.125732421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} {"step": 32840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32840, "total_transitions": 134512640, "num_steps_per_env": 1, "wm_loss": 0.43355467915534973, "actor_loss": -8.757539749145508, "critic_loss": 0.025524070486426353, "reward": 0.07110387086868286, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24132493138313293, 0.1565597504377365, 0.25064778327941895], "policy_updates": 32740, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5065.280901579999, "contact_bce": 0.3196742534637451, "contact_force_loss": 0.033310458064079285, "terrain_level_mean": 3.12548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} {"step": 32850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32850, "total_transitions": 134553600, "num_steps_per_env": 1, "wm_loss": 0.4437689483165741, "actor_loss": -8.726938247680664, "critic_loss": 0.025764325633645058, "reward": 0.07126043736934662, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2446555644273758, 0.15425659716129303, 0.25095972418785095], "policy_updates": 32750, "skipped_updates": 0, "invalid_env_resets": 37, "elapsed_s": 5068.794392119999, "contact_bce": 0.3152037262916565, "contact_force_loss": 0.0322398915886879, "terrain_level_mean": 3.124755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} RECOVERY reset 1 invalid environments; first IDs=[1040] {"step": 32860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32860, "total_transitions": 134594560, "num_steps_per_env": 1, "wm_loss": 0.4705931544303894, "actor_loss": -8.731762886047363, "critic_loss": 0.027546986937522888, "reward": 0.07118101418018341, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24369622766971588, 0.15490181744098663, 0.25284525752067566], "policy_updates": 32760, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5072.318081673, "contact_bce": 0.3224511742591858, "contact_force_loss": 0.03274587541818619, "terrain_level_mean": 3.12548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} {"step": 32870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32870, "total_transitions": 134635520, "num_steps_per_env": 1, "wm_loss": 0.44609761238098145, "actor_loss": -8.731759071350098, "critic_loss": 0.024501128122210503, "reward": 0.07108958810567856, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24096913635730743, 0.15414659678936005, 0.25128382444381714], "policy_updates": 32770, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5075.837683588999, "contact_bce": 0.3144119679927826, "contact_force_loss": 0.03261135518550873, "terrain_level_mean": 3.12548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} {"step": 32880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32880, "total_transitions": 134676480, "num_steps_per_env": 1, "wm_loss": 0.47504568099975586, "actor_loss": -8.730053901672363, "critic_loss": 0.02630683220922947, "reward": 0.07172619551420212, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2395373284816742, 0.15512876212596893, 0.2506049573421478], "policy_updates": 32780, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5079.346820522999, "contact_bce": 0.31704163551330566, "contact_force_loss": 0.03328896313905716, "terrain_level_mean": 3.125732421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} {"step": 32890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32890, "total_transitions": 134717440, "num_steps_per_env": 1, "wm_loss": 0.4263950288295746, "actor_loss": -8.731426239013672, "critic_loss": 0.030435537919402122, "reward": 0.07148858159780502, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24076014757156372, 0.15836015343666077, 0.2500920295715332], "policy_updates": 32790, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5082.856796599, "contact_bce": 0.3177907168865204, "contact_force_loss": 0.03196090832352638, "terrain_level_mean": 3.126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} {"step": 32900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32900, "total_transitions": 134758400, "num_steps_per_env": 1, "wm_loss": 0.47961539030075073, "actor_loss": -8.758162498474121, "critic_loss": 0.03133713826537132, "reward": 0.07134144753217697, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24261198937892914, 0.15784665942192078, 0.24887299537658691], "policy_updates": 32800, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5086.36214142, "contact_bce": 0.3242686688899994, "contact_force_loss": 0.032965417951345444, "terrain_level_mean": 3.12744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.997880697250366]} {"step": 32910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32910, "total_transitions": 134799360, "num_steps_per_env": 1, "wm_loss": 0.46187323331832886, "actor_loss": -8.767536163330078, "critic_loss": 0.020730463787913322, "reward": 0.07160314172506332, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23817598819732666, 0.15462973713874817, 0.2507975697517395], "policy_updates": 32810, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5089.870336219999, "contact_bce": 0.320745587348938, "contact_force_loss": 0.03370950371026993, "terrain_level_mean": 3.128173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 32920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32920, "total_transitions": 134840320, "num_steps_per_env": 1, "wm_loss": 0.4873945415019989, "actor_loss": -8.78927230834961, "critic_loss": 0.0221323873847723, "reward": 0.07142747938632965, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24011686444282532, 0.15702393651008606, 0.2531055212020874], "policy_updates": 32820, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5093.399475859, "contact_bce": 0.32267507910728455, "contact_force_loss": 0.03391108289361, "terrain_level_mean": 3.128173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 32930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32930, "total_transitions": 134881280, "num_steps_per_env": 1, "wm_loss": 0.46411046385765076, "actor_loss": -8.721364974975586, "critic_loss": 0.025793934240937233, "reward": 0.07113564759492874, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24328580498695374, 0.15876176953315735, 0.25477874279022217], "policy_updates": 32830, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5096.909417795, "contact_bce": 0.32412126660346985, "contact_force_loss": 0.033786363899707794, "terrain_level_mean": 3.128173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 32940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32940, "total_transitions": 134922240, "num_steps_per_env": 1, "wm_loss": 0.43753907084465027, "actor_loss": -8.768644332885742, "critic_loss": 0.018033048138022423, "reward": 0.07100118696689606, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2444552481174469, 0.15519051253795624, 0.2563314735889435], "policy_updates": 32840, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5100.415974552, "contact_bce": 0.31503450870513916, "contact_force_loss": 0.03214237466454506, "terrain_level_mean": 3.127197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 32950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32950, "total_transitions": 134963200, "num_steps_per_env": 1, "wm_loss": 0.4457338750362396, "actor_loss": -8.79693603515625, "critic_loss": 0.025149276480078697, "reward": 0.0715252012014389, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24493923783302307, 0.15565988421440125, 0.2503371834754944], "policy_updates": 32850, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5103.923548952999, "contact_bce": 0.3211210072040558, "contact_force_loss": 0.03263454884290695, "terrain_level_mean": 3.1279296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331787109375, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 32960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32960, "total_transitions": 135004160, "num_steps_per_env": 1, "wm_loss": 0.4422007203102112, "actor_loss": -8.692533493041992, "critic_loss": 0.024233993142843246, "reward": 0.07156773656606674, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24164855480194092, 0.15600170195102692, 0.2495800256729126], "policy_updates": 32860, "skipped_updates": 0, "invalid_env_resets": 38, "elapsed_s": 5107.419463208, "contact_bce": 0.3157772123813629, "contact_force_loss": 0.032607752829790115, "terrain_level_mean": 3.12841796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} RECOVERY reset 1 invalid environments; first IDs=[1091] {"step": 32970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32970, "total_transitions": 135045120, "num_steps_per_env": 1, "wm_loss": 0.4648003876209259, "actor_loss": -8.692770957946777, "critic_loss": 0.04669502377510071, "reward": 0.07140650600194931, "falls": 9, "interval_steps": 10, "velocity_mae": [0.23927435278892517, 0.15281561017036438, 0.25287899374961853], "policy_updates": 32870, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5110.939531882, "contact_bce": 0.31894540786743164, "contact_force_loss": 0.032778795808553696, "terrain_level_mean": 3.126708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 32980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32980, "total_transitions": 135086080, "num_steps_per_env": 1, "wm_loss": 0.47260165214538574, "actor_loss": -8.80632209777832, "critic_loss": 0.025159094482660294, "reward": 0.07158961147069931, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24062460660934448, 0.15404966473579407, 0.2556856870651245], "policy_updates": 32880, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5114.467981993, "contact_bce": 0.3191787004470825, "contact_force_loss": 0.0328214131295681, "terrain_level_mean": 3.126708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 32990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 32990, "total_transitions": 135127040, "num_steps_per_env": 1, "wm_loss": 0.4881804585456848, "actor_loss": -8.780269622802734, "critic_loss": 0.029069123789668083, "reward": 0.07161147892475128, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24111329019069672, 0.156374990940094, 0.2565447986125946], "policy_updates": 32890, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5117.987565601999, "contact_bce": 0.3216847777366638, "contact_force_loss": 0.03281324356794357, "terrain_level_mean": 3.127197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9868879318237305]} {"step": 33000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33000, "total_transitions": 135168000, "num_steps_per_env": 1, "wm_loss": 0.4565645754337311, "actor_loss": -8.739163398742676, "critic_loss": 0.02600986696779728, "reward": 0.07142486423254013, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24062754213809967, 0.15627555549144745, 0.25592902302742004], "policy_updates": 32900, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5121.512500391999, "contact_bce": 0.31507501006126404, "contact_force_loss": 0.03204067796468735, "terrain_level_mean": 3.128662109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9988059997558594, 0.999733567237854, 2.9875242710113525]} {"step": 33010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33010, "total_transitions": 135208960, "num_steps_per_env": 1, "wm_loss": 0.4571056067943573, "actor_loss": -8.756168365478516, "critic_loss": 0.027583837509155273, "reward": 0.07071732729673386, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2441292703151703, 0.16016031801700592, 0.2560294270515442], "policy_updates": 32910, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5125.04749627, "contact_bce": 0.3222658634185791, "contact_force_loss": 0.03229964151978493, "terrain_level_mean": 3.130126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9985196590423584, 0.999733567237854, 2.9875242710113525]} {"step": 33020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33020, "total_transitions": 135249920, "num_steps_per_env": 1, "wm_loss": 0.44306400418281555, "actor_loss": -8.714397430419922, "critic_loss": 0.021697998046875, "reward": 0.07063701003789902, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2453567385673523, 0.15782424807548523, 0.25205811858177185], "policy_updates": 32920, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5128.550287726, "contact_bce": 0.31577473878860474, "contact_force_loss": 0.032130032777786255, "terrain_level_mean": 3.1298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9985196590423584, 0.999733567237854, 2.9875242710113525]} {"step": 33030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33030, "total_transitions": 135290880, "num_steps_per_env": 1, "wm_loss": 0.43343406915664673, "actor_loss": -8.746183395385742, "critic_loss": 0.024398868903517723, "reward": 0.07088784873485565, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2395647019147873, 0.15846040844917297, 0.2508834898471832], "policy_updates": 32930, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5132.307190568999, "contact_bce": 0.3198789656162262, "contact_force_loss": 0.03264573961496353, "terrain_level_mean": 3.12890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9985196590423584, 0.999733567237854, 2.9944067001342773]} {"step": 33040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33040, "total_transitions": 135331840, "num_steps_per_env": 1, "wm_loss": 0.48908284306526184, "actor_loss": -8.75516128540039, "critic_loss": 0.02921213023364544, "reward": 0.07079233229160309, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23997169733047485, 0.15643242001533508, 0.25359582901000977], "policy_updates": 32940, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5135.809174823, "contact_bce": 0.32183754444122314, "contact_force_loss": 0.03344133496284485, "terrain_level_mean": 3.1279296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9985196590423584, 0.999733567237854, 2.9944067001342773]} {"step": 33050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33050, "total_transitions": 135372800, "num_steps_per_env": 1, "wm_loss": 0.4551812708377838, "actor_loss": -8.775266647338867, "critic_loss": 0.022684305906295776, "reward": 0.07059095799922943, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24437455832958221, 0.1552373319864273, 0.2583640217781067], "policy_updates": 32950, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5139.305698151, "contact_bce": 0.31771716475486755, "contact_force_loss": 0.03263307735323906, "terrain_level_mean": 3.12890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9985196590423584, 0.999733567237854, 2.9944067001342773]} {"step": 33060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33060, "total_transitions": 135413760, "num_steps_per_env": 1, "wm_loss": 0.4480511546134949, "actor_loss": -8.747894287109375, "critic_loss": 0.02376534603536129, "reward": 0.07052013278007507, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24522455036640167, 0.15541616082191467, 0.25554904341697693], "policy_updates": 32960, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5142.800673357, "contact_bce": 0.325703889131546, "contact_force_loss": 0.03226710855960846, "terrain_level_mean": 3.127685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9985196590423584, 0.999733567237854, 2.9944067001342773]} {"step": 33070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33070, "total_transitions": 135454720, "num_steps_per_env": 1, "wm_loss": 0.4527892768383026, "actor_loss": -8.786178588867188, "critic_loss": 0.025564495474100113, "reward": 0.07081768661737442, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24286752939224243, 0.1553633213043213, 0.2528861463069916], "policy_updates": 32970, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5146.295228397, "contact_bce": 0.3111201524734497, "contact_force_loss": 0.03216933086514473, "terrain_level_mean": 3.12744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9980573654174805, 0.999733567237854, 2.9944067001342773]} {"step": 33080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33080, "total_transitions": 135495680, "num_steps_per_env": 1, "wm_loss": 0.43687599897384644, "actor_loss": -8.79556655883789, "critic_loss": 0.02782995067536831, "reward": 0.07069768011569977, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23894678056240082, 0.1537482738494873, 0.2504105865955353], "policy_updates": 32980, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5149.807594958999, "contact_bce": 0.3220513164997101, "contact_force_loss": 0.03310159593820572, "terrain_level_mean": 3.126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9980573654174805, 0.999733567237854, 2.9944067001342773]} {"step": 33090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33090, "total_transitions": 135536640, "num_steps_per_env": 1, "wm_loss": 0.4494648277759552, "actor_loss": -8.765315055847168, "critic_loss": 0.027040868997573853, "reward": 0.07102163136005402, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2379346787929535, 0.15510335564613342, 0.24991200864315033], "policy_updates": 32990, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5153.326269579, "contact_bce": 0.3160271644592285, "contact_force_loss": 0.03256352245807648, "terrain_level_mean": 3.1279296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9980573654174805, 0.999733567237854, 2.9944067001342773]} {"step": 33100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33100, "total_transitions": 135577600, "num_steps_per_env": 1, "wm_loss": 0.4766019582748413, "actor_loss": -8.806214332580566, "critic_loss": 0.01988687738776207, "reward": 0.07095549255609512, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23708532750606537, 0.15507125854492188, 0.2510738670825958], "policy_updates": 33000, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5156.842890027, "contact_bce": 0.32129934430122375, "contact_force_loss": 0.0337652862071991, "terrain_level_mean": 3.127197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9980573654174805, 0.9996623992919922, 2.9944067001342773]} {"step": 33110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33110, "total_transitions": 135618560, "num_steps_per_env": 1, "wm_loss": 0.49001607298851013, "actor_loss": -8.77719783782959, "critic_loss": 0.03226012736558914, "reward": 0.07107727229595184, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24092693626880646, 0.15606892108917236, 0.2506818175315857], "policy_updates": 33010, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5160.353959622, "contact_bce": 0.3214236795902252, "contact_force_loss": 0.03355163708329201, "terrain_level_mean": 3.126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9980573654174805, 0.9996623992919922, 2.9944067001342773]} {"step": 33120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33120, "total_transitions": 135659520, "num_steps_per_env": 1, "wm_loss": 0.44761449098587036, "actor_loss": -8.795360565185547, "critic_loss": 0.02520729973912239, "reward": 0.07201888412237167, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2348758727312088, 0.15542809665203094, 0.2502630352973938], "policy_updates": 33020, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5163.867722489999, "contact_bce": 0.3215203583240509, "contact_force_loss": 0.03366386517882347, "terrain_level_mean": 3.126708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9974308013916016, 0.9996623992919922, 2.9944067001342773]} {"step": 33130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33130, "total_transitions": 135700480, "num_steps_per_env": 1, "wm_loss": 0.44235655665397644, "actor_loss": -8.783580780029297, "critic_loss": 0.032335828989744186, "reward": 0.07149647921323776, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24196170270442963, 0.1568099409341812, 0.2545774579048157], "policy_updates": 33030, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5167.3804513079995, "contact_bce": 0.3197571933269501, "contact_force_loss": 0.032845690846443176, "terrain_level_mean": 3.127197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9974308013916016, 0.9996623992919922, 2.9944067001342773]} {"step": 33140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33140, "total_transitions": 135741440, "num_steps_per_env": 1, "wm_loss": 0.44538405537605286, "actor_loss": -8.753805160522461, "critic_loss": 0.026900703087449074, "reward": 0.07114187628030777, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2491690069437027, 0.15777769684791565, 0.25295764207839966], "policy_updates": 33040, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5170.894297465999, "contact_bce": 0.32262280583381653, "contact_force_loss": 0.03270158916711807, "terrain_level_mean": 3.129150390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9974308013916016, 0.9996623992919922, 2.9944067001342773]} {"step": 33150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33150, "total_transitions": 135782400, "num_steps_per_env": 1, "wm_loss": 0.47829681634902954, "actor_loss": -8.777700424194336, "critic_loss": 0.028664885088801384, "reward": 0.07152046263217926, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2490486055612564, 0.15589766204357147, 0.2485557347536087], "policy_updates": 33050, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5174.406977314, "contact_bce": 0.32235318422317505, "contact_force_loss": 0.03240945562720299, "terrain_level_mean": 3.13037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9974308013916016, 0.9996623992919922, 2.9944067001342773]} {"step": 33160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33160, "total_transitions": 135823360, "num_steps_per_env": 1, "wm_loss": 0.4478142559528351, "actor_loss": -8.733912467956543, "critic_loss": 0.025784391909837723, "reward": 0.0715276449918747, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24930869042873383, 0.15448351204395294, 0.24959000945091248], "policy_updates": 33060, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5177.91602756, "contact_bce": 0.3197997510433197, "contact_force_loss": 0.033433642238378525, "terrain_level_mean": 3.131103515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9974308013916016, 0.9996623992919922, 2.9987194538116455]} {"step": 33170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33170, "total_transitions": 135864320, "num_steps_per_env": 1, "wm_loss": 0.4417669475078583, "actor_loss": -8.799402236938477, "critic_loss": 0.021055806428194046, "reward": 0.07129865884780884, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24388465285301208, 0.15599453449249268, 0.25314730405807495], "policy_updates": 33070, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5181.427390094, "contact_bce": 0.32275253534317017, "contact_force_loss": 0.03266574814915657, "terrain_level_mean": 3.131103515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9974308013916016, 0.9996623992919922, 2.9987194538116455]} {"step": 33180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33180, "total_transitions": 135905280, "num_steps_per_env": 1, "wm_loss": 0.4631694555282593, "actor_loss": -8.802297592163086, "critic_loss": 0.0225569698959589, "reward": 0.07132814079523087, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2487906962633133, 0.15787604451179504, 0.254682719707489], "policy_updates": 33080, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5184.945985236, "contact_bce": 0.3230918347835541, "contact_force_loss": 0.033563267439603806, "terrain_level_mean": 3.130615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9974308013916016, 0.9997413158416748, 2.9987194538116455]} {"step": 33190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33190, "total_transitions": 135946240, "num_steps_per_env": 1, "wm_loss": 0.4363524913787842, "actor_loss": -8.766080856323242, "critic_loss": 0.028997844085097313, "reward": 0.07125290483236313, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2460937798023224, 0.1616593301296234, 0.25359806418418884], "policy_updates": 33090, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5188.4667840209995, "contact_bce": 0.3179070055484772, "contact_force_loss": 0.03181292861700058, "terrain_level_mean": 3.129150390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9974308013916016, 0.9997413158416748, 2.9987194538116455]} {"step": 33200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33200, "total_transitions": 135987200, "num_steps_per_env": 1, "wm_loss": 0.47433292865753174, "actor_loss": -8.817500114440918, "critic_loss": 0.025127381086349487, "reward": 0.07091943919658661, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24865716695785522, 0.15869371592998505, 0.25287312269210815], "policy_updates": 33100, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5191.982260569999, "contact_bce": 0.3182586133480072, "contact_force_loss": 0.0332430861890316, "terrain_level_mean": 3.12939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33210, "total_transitions": 136028160, "num_steps_per_env": 1, "wm_loss": 0.46064117550849915, "actor_loss": -8.757457733154297, "critic_loss": 0.02789144776761532, "reward": 0.07098130136728287, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24811670184135437, 0.1569654643535614, 0.25506430864334106], "policy_updates": 33110, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5195.499533186, "contact_bce": 0.32156476378440857, "contact_force_loss": 0.03261365368962288, "terrain_level_mean": 3.129638671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33220, "total_transitions": 136069120, "num_steps_per_env": 1, "wm_loss": 0.4525730013847351, "actor_loss": -8.803025245666504, "critic_loss": 0.028312642127275467, "reward": 0.07096850126981735, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2432582527399063, 0.15547864139080048, 0.2547675371170044], "policy_updates": 33120, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5199.008893077, "contact_bce": 0.31854546070098877, "contact_force_loss": 0.03310959413647652, "terrain_level_mean": 3.12939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33230, "total_transitions": 136110080, "num_steps_per_env": 1, "wm_loss": 0.524516224861145, "actor_loss": -8.761171340942383, "critic_loss": 0.030629774555563927, "reward": 0.0712318941950798, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23854444921016693, 0.15551163256168365, 0.24983838200569153], "policy_updates": 33130, "skipped_updates": 0, "invalid_env_resets": 39, "elapsed_s": 5202.524589117, "contact_bce": 0.324099600315094, "contact_force_loss": 0.03340710699558258, "terrain_level_mean": 3.13037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} RECOVERY reset 1 invalid environments; first IDs=[1891] {"step": 33240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33240, "total_transitions": 136151040, "num_steps_per_env": 1, "wm_loss": 0.44184809923171997, "actor_loss": -8.794437408447266, "critic_loss": 0.03356785327196121, "reward": 0.07175976037979126, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23552949726581573, 0.15446460247039795, 0.24678556621074677], "policy_updates": 33140, "skipped_updates": 0, "invalid_env_resets": 40, "elapsed_s": 5206.053561754, "contact_bce": 0.31900355219841003, "contact_force_loss": 0.032925549894571304, "terrain_level_mean": 3.130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} RECOVERY reset 1 invalid environments; first IDs=[828] {"step": 33250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33250, "total_transitions": 136192000, "num_steps_per_env": 1, "wm_loss": 0.4130110740661621, "actor_loss": -8.768213272094727, "critic_loss": 0.02239193581044674, "reward": 0.07190725952386856, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23535104095935822, 0.15178431570529938, 0.24794676899909973], "policy_updates": 33150, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5209.590089824999, "contact_bce": 0.3137982487678528, "contact_force_loss": 0.032159674912691116, "terrain_level_mean": 3.130126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33260, "total_transitions": 136232960, "num_steps_per_env": 1, "wm_loss": 0.43599197268486023, "actor_loss": -8.76634407043457, "critic_loss": 0.030898749828338623, "reward": 0.07201527804136276, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23363088071346283, 0.15139035880565643, 0.24496014416217804], "policy_updates": 33160, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5213.113786303, "contact_bce": 0.3208668828010559, "contact_force_loss": 0.03213956207036972, "terrain_level_mean": 3.130126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33270, "total_transitions": 136273920, "num_steps_per_env": 1, "wm_loss": 0.46591198444366455, "actor_loss": -8.7709379196167, "critic_loss": 0.022756870836019516, "reward": 0.07178782671689987, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2307516634464264, 0.1525970995426178, 0.24700725078582764], "policy_updates": 33170, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5216.628592128, "contact_bce": 0.3159961402416229, "contact_force_loss": 0.03233051672577858, "terrain_level_mean": 3.13037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33280, "total_transitions": 136314880, "num_steps_per_env": 1, "wm_loss": 0.46880313754081726, "actor_loss": -8.706642150878906, "critic_loss": 0.03800911456346512, "reward": 0.07168526947498322, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23444023728370667, 0.15172383189201355, 0.2476799488067627], "policy_updates": 33180, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5220.146269051999, "contact_bce": 0.3248559534549713, "contact_force_loss": 0.032785117626190186, "terrain_level_mean": 3.130615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33290, "total_transitions": 136355840, "num_steps_per_env": 1, "wm_loss": 0.46627140045166016, "actor_loss": -8.777058601379395, "critic_loss": 0.031047750264406204, "reward": 0.07180842012166977, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23512162268161774, 0.15139026939868927, 0.24975912272930145], "policy_updates": 33190, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5223.6595275459995, "contact_bce": 0.32008036971092224, "contact_force_loss": 0.03269662708044052, "terrain_level_mean": 3.13134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33300, "total_transitions": 136396800, "num_steps_per_env": 1, "wm_loss": 0.45831242203712463, "actor_loss": -8.80266284942627, "critic_loss": 0.023583298549056053, "reward": 0.07202616333961487, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23416514694690704, 0.15309149026870728, 0.24532780051231384], "policy_updates": 33200, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5227.170247614999, "contact_bce": 0.32332107424736023, "contact_force_loss": 0.03278845548629761, "terrain_level_mean": 3.1318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33310, "total_transitions": 136437760, "num_steps_per_env": 1, "wm_loss": 0.4562888443470001, "actor_loss": -8.790680885314941, "critic_loss": 0.02569056861102581, "reward": 0.07139377295970917, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23920877277851105, 0.15388214588165283, 0.24974757432937622], "policy_updates": 33210, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5230.691300414999, "contact_bce": 0.31598982214927673, "contact_force_loss": 0.032378409057855606, "terrain_level_mean": 3.133056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33320, "total_transitions": 136478720, "num_steps_per_env": 1, "wm_loss": 0.44537442922592163, "actor_loss": -8.706079483032227, "critic_loss": 0.031648989766836166, "reward": 0.07129973918199539, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23959609866142273, 0.15497536957263947, 0.2517358958721161], "policy_updates": 33220, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5234.205501224999, "contact_bce": 0.3143412470817566, "contact_force_loss": 0.032550133764743805, "terrain_level_mean": 3.13427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33330, "total_transitions": 136519680, "num_steps_per_env": 1, "wm_loss": 0.4659803807735443, "actor_loss": -8.799814224243164, "critic_loss": 0.022594043985009193, "reward": 0.07077474892139435, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23977382481098175, 0.15447363257408142, 0.25110673904418945], "policy_updates": 33230, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5237.71633484, "contact_bce": 0.3176676034927368, "contact_force_loss": 0.03228822723031044, "terrain_level_mean": 3.134033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33340, "total_transitions": 136560640, "num_steps_per_env": 1, "wm_loss": 0.46897220611572266, "actor_loss": -8.765148162841797, "critic_loss": 0.027376556769013405, "reward": 0.0712437778711319, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24184471368789673, 0.15281841158866882, 0.2472059279680252], "policy_updates": 33240, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5241.222566992999, "contact_bce": 0.3197714388370514, "contact_force_loss": 0.0324414037168026, "terrain_level_mean": 3.134033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33350, "total_transitions": 136601600, "num_steps_per_env": 1, "wm_loss": 0.4495324194431305, "actor_loss": -8.756146430969238, "critic_loss": 0.02860151045024395, "reward": 0.07105603814125061, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24133411049842834, 0.15237383544445038, 0.24959571659564972], "policy_updates": 33250, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5244.737922613, "contact_bce": 0.3181162476539612, "contact_force_loss": 0.032274480909109116, "terrain_level_mean": 3.135009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9992656707763672, 0.9997413158416748, 2.9987194538116455]} {"step": 33360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33360, "total_transitions": 136642560, "num_steps_per_env": 1, "wm_loss": 0.4443471431732178, "actor_loss": -8.834095001220703, "critic_loss": 0.029511962085962296, "reward": 0.07066237926483154, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2369842231273651, 0.1533835083246231, 0.25139644742012024], "policy_updates": 33260, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5248.2555489119995, "contact_bce": 0.32286232709884644, "contact_force_loss": 0.03264552354812622, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.996997356414795, 0.9997413158416748, 2.9987194538116455]} {"step": 33370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33370, "total_transitions": 136683520, "num_steps_per_env": 1, "wm_loss": 0.4429536461830139, "actor_loss": -8.771669387817383, "critic_loss": 0.026122553274035454, "reward": 0.07120823115110397, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23527809977531433, 0.1545831859111786, 0.24789254367351532], "policy_updates": 33270, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5251.771750929, "contact_bce": 0.31537356972694397, "contact_force_loss": 0.03170259669423103, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9972953796386719, 0.9997413158416748, 2.9987194538116455]} Warning: EPA horizon = 24 isn't large enough. Warning: EPA horizon = 24 isn't large enough. {"step": 33380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33380, "total_transitions": 136724480, "num_steps_per_env": 1, "wm_loss": 0.4627366364002228, "actor_loss": -8.791352272033691, "critic_loss": 0.030464906245470047, "reward": 0.07105465978384018, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23828855156898499, 0.1539968103170395, 0.2529023289680481], "policy_updates": 33280, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5255.286985383, "contact_bce": 0.3242783844470978, "contact_force_loss": 0.03314833715558052, "terrain_level_mean": 3.13671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9972953796386719, 0.9997413158416748, 2.9987194538116455]} {"step": 33390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33390, "total_transitions": 136765440, "num_steps_per_env": 1, "wm_loss": 0.46532055735588074, "actor_loss": -8.76729965209961, "critic_loss": 0.02429269626736641, "reward": 0.07099183648824692, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23955795168876648, 0.15180601179599762, 0.250061959028244], "policy_updates": 33290, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5258.805589087, "contact_bce": 0.31930577754974365, "contact_force_loss": 0.03260097652673721, "terrain_level_mean": 3.136962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9972953796386719, 0.9997413158416748, 2.9987194538116455]} {"step": 33400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33400, "total_transitions": 136806400, "num_steps_per_env": 1, "wm_loss": 0.4655265212059021, "actor_loss": -8.76416015625, "critic_loss": 0.022801855579018593, "reward": 0.0710781142115593, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23523961007595062, 0.15067988634109497, 0.24363553524017334], "policy_updates": 33300, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5262.332573813999, "contact_bce": 0.31582996249198914, "contact_force_loss": 0.03250335901975632, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9972953796386719, 0.9997413158416748, 2.9987194538116455]} {"step": 33410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33410, "total_transitions": 136847360, "num_steps_per_env": 1, "wm_loss": 0.4407206177711487, "actor_loss": -8.797399520874023, "critic_loss": 0.02716621570289135, "reward": 0.07103699445724487, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23832018673419952, 0.15338905155658722, 0.248375803232193], "policy_updates": 33310, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5265.8560458169995, "contact_bce": 0.31820839643478394, "contact_force_loss": 0.03231348469853401, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9989323616027832, 0.9997413158416748, 2.9987194538116455]} {"step": 33420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33420, "total_transitions": 136888320, "num_steps_per_env": 1, "wm_loss": 0.46288052201271057, "actor_loss": -8.767379760742188, "critic_loss": 0.025977766141295433, "reward": 0.07084538042545319, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23670394718647003, 0.15048815310001373, 0.24797958135604858], "policy_updates": 33320, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5269.361608806, "contact_bce": 0.32432952523231506, "contact_force_loss": 0.03290865942835808, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9987194538116455]} {"step": 33430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33430, "total_transitions": 136929280, "num_steps_per_env": 1, "wm_loss": 0.5032681822776794, "actor_loss": -8.783562660217285, "critic_loss": 0.022665096446871758, "reward": 0.07136797904968262, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23707988858222961, 0.15134862065315247, 0.24693958461284637], "policy_updates": 33330, "skipped_updates": 0, "invalid_env_resets": 41, "elapsed_s": 5272.880805504, "contact_bce": 0.3223860263824463, "contact_force_loss": 0.03332170844078064, "terrain_level_mean": 3.1357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9987194538116455]} RECOVERY reset 1 invalid environments; first IDs=[1310] {"step": 33440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33440, "total_transitions": 136970240, "num_steps_per_env": 1, "wm_loss": 0.46187669038772583, "actor_loss": -8.80548095703125, "critic_loss": 0.03163185715675354, "reward": 0.07128285616636276, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23720070719718933, 0.15378381311893463, 0.25167104601860046], "policy_updates": 33340, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5276.416150288999, "contact_bce": 0.31675222516059875, "contact_force_loss": 0.03336634859442711, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9987194538116455]} {"step": 33450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33450, "total_transitions": 137011200, "num_steps_per_env": 1, "wm_loss": 0.44300857186317444, "actor_loss": -8.763387680053711, "critic_loss": 0.027090800926089287, "reward": 0.0714116245508194, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2363203763961792, 0.15395396947860718, 0.2526988983154297], "policy_updates": 33350, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5279.939137834, "contact_bce": 0.31862860918045044, "contact_force_loss": 0.03233380988240242, "terrain_level_mean": 3.135498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33460, "total_transitions": 137052160, "num_steps_per_env": 1, "wm_loss": 0.4638786017894745, "actor_loss": -8.768560409545898, "critic_loss": 0.02718142606317997, "reward": 0.07108574360609055, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23862574994564056, 0.15204080939292908, 0.25468701124191284], "policy_updates": 33360, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5283.473118004999, "contact_bce": 0.3167305290699005, "contact_force_loss": 0.0319809727370739, "terrain_level_mean": 3.134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33470, "total_transitions": 137093120, "num_steps_per_env": 1, "wm_loss": 0.46234655380249023, "actor_loss": -8.788578033447266, "critic_loss": 0.0286265816539526, "reward": 0.07101985067129135, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24189504981040955, 0.1556631624698639, 0.2584051191806793], "policy_updates": 33370, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5287.003183694, "contact_bce": 0.31954681873321533, "contact_force_loss": 0.03316626697778702, "terrain_level_mean": 3.133056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33480, "total_transitions": 137134080, "num_steps_per_env": 1, "wm_loss": 0.43416088819503784, "actor_loss": -8.767730712890625, "critic_loss": 0.027342498302459717, "reward": 0.07095600664615631, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24812442064285278, 0.1564331352710724, 0.25192463397979736], "policy_updates": 33380, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5290.5282735149995, "contact_bce": 0.3237443268299103, "contact_force_loss": 0.03208164870738983, "terrain_level_mean": 3.1337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33490, "total_transitions": 137175040, "num_steps_per_env": 1, "wm_loss": 0.4621748924255371, "actor_loss": -8.721961975097656, "critic_loss": 0.026228904724121094, "reward": 0.07089666277170181, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2454676628112793, 0.15545260906219482, 0.2537747621536255], "policy_updates": 33390, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5294.056011693, "contact_bce": 0.3172142505645752, "contact_force_loss": 0.03219539672136307, "terrain_level_mean": 3.13427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33500, "total_transitions": 137216000, "num_steps_per_env": 1, "wm_loss": 0.42977043986320496, "actor_loss": -8.76388168334961, "critic_loss": 0.028545651584863663, "reward": 0.07086031883955002, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24330775439739227, 0.1525193601846695, 0.25415337085723877], "policy_updates": 33400, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5297.579029617, "contact_bce": 0.3178859353065491, "contact_force_loss": 0.032353974878787994, "terrain_level_mean": 3.134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33510, "total_transitions": 137256960, "num_steps_per_env": 1, "wm_loss": 0.4366845488548279, "actor_loss": -8.723440170288086, "critic_loss": 0.029855936765670776, "reward": 0.07109389454126358, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23999378085136414, 0.15278825163841248, 0.25037625432014465], "policy_updates": 33410, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5301.125153655999, "contact_bce": 0.3151665925979614, "contact_force_loss": 0.03220965713262558, "terrain_level_mean": 3.1357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33520, "total_transitions": 137297920, "num_steps_per_env": 1, "wm_loss": 0.4357873797416687, "actor_loss": -8.755290985107422, "critic_loss": 0.026680579409003258, "reward": 0.07093554735183716, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24182088673114777, 0.1575595587491989, 0.252843976020813], "policy_updates": 33420, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5304.64446386, "contact_bce": 0.31841620802879333, "contact_force_loss": 0.03244834020733833, "terrain_level_mean": 3.135498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33530, "total_transitions": 137338880, "num_steps_per_env": 1, "wm_loss": 0.4705854654312134, "actor_loss": -8.776344299316406, "critic_loss": 0.026277093216776848, "reward": 0.07070644944906235, "falls": 11, "interval_steps": 10, "velocity_mae": [0.24537049233913422, 0.1598489135503769, 0.25596773624420166], "policy_updates": 33430, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5308.405599981, "contact_bce": 0.3132621645927429, "contact_force_loss": 0.031730227172374725, "terrain_level_mean": 3.13427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33540, "total_transitions": 137379840, "num_steps_per_env": 1, "wm_loss": 0.43038100004196167, "actor_loss": -8.803695678710938, "critic_loss": 0.024107251316308975, "reward": 0.07064840942621231, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2469950169324875, 0.15709248185157776, 0.25515225529670715], "policy_updates": 33440, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5311.922238929999, "contact_bce": 0.31576773524284363, "contact_force_loss": 0.032064490020275116, "terrain_level_mean": 3.1337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33550, "total_transitions": 137420800, "num_steps_per_env": 1, "wm_loss": 0.43930965662002563, "actor_loss": -8.804683685302734, "critic_loss": 0.03786114975810051, "reward": 0.0704331174492836, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24268031120300293, 0.15843084454536438, 0.2564150393009186], "policy_updates": 33450, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5315.4444177489995, "contact_bce": 0.31506428122520447, "contact_force_loss": 0.03211403265595436, "terrain_level_mean": 3.134033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33560, "total_transitions": 137461760, "num_steps_per_env": 1, "wm_loss": 0.5137836933135986, "actor_loss": -8.748421669006348, "critic_loss": 0.03008246421813965, "reward": 0.07044323533773422, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2408880740404129, 0.15855543315410614, 0.25643935799598694], "policy_updates": 33460, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5318.966641278999, "contact_bce": 0.3185596168041229, "contact_force_loss": 0.032936520874500275, "terrain_level_mean": 3.1337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.9986252784729004]} {"step": 33570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33570, "total_transitions": 137502720, "num_steps_per_env": 1, "wm_loss": 0.47180214524269104, "actor_loss": -8.793399810791016, "critic_loss": 0.038253169506788254, "reward": 0.07102850824594498, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23771680891513824, 0.15724316239356995, 0.2515144348144531], "policy_updates": 33470, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5322.486541024, "contact_bce": 0.31592777371406555, "contact_force_loss": 0.03211893141269684, "terrain_level_mean": 3.134033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.996427536010742]} {"step": 33580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33580, "total_transitions": 137543680, "num_steps_per_env": 1, "wm_loss": 0.4239692687988281, "actor_loss": -8.821191787719727, "critic_loss": 0.02618568018078804, "reward": 0.07087181508541107, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24038301408290863, 0.15572340786457062, 0.25441983342170715], "policy_updates": 33480, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5325.9996771549995, "contact_bce": 0.31954264640808105, "contact_force_loss": 0.032212547957897186, "terrain_level_mean": 3.134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.996427536010742]} {"step": 33590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33590, "total_transitions": 137584640, "num_steps_per_env": 1, "wm_loss": 0.45354631543159485, "actor_loss": -8.768790245056152, "critic_loss": 0.030121034011244774, "reward": 0.07061027735471725, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24605312943458557, 0.15725478529930115, 0.25961562991142273], "policy_updates": 33490, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5329.512695658999, "contact_bce": 0.31418460607528687, "contact_force_loss": 0.03178061917424202, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.996427536010742]} {"step": 33600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33600, "total_transitions": 137625600, "num_steps_per_env": 1, "wm_loss": 0.4554341733455658, "actor_loss": -8.830896377563477, "critic_loss": 0.02680038847029209, "reward": 0.07075189799070358, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24216310679912567, 0.15899920463562012, 0.25675174593925476], "policy_updates": 33500, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5333.032195319, "contact_bce": 0.3204900622367859, "contact_force_loss": 0.032885339111089706, "terrain_level_mean": 3.1357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.996427536010742]} {"step": 33610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33610, "total_transitions": 137666560, "num_steps_per_env": 1, "wm_loss": 0.459477037191391, "actor_loss": -8.770482063293457, "critic_loss": 0.02921760082244873, "reward": 0.0708731859922409, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23992039263248444, 0.15549308061599731, 0.25203627347946167], "policy_updates": 33510, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5336.543372034999, "contact_bce": 0.3182995319366455, "contact_force_loss": 0.032371412962675095, "terrain_level_mean": 3.134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.996427536010742]} {"step": 33620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33620, "total_transitions": 137707520, "num_steps_per_env": 1, "wm_loss": 0.45136603713035583, "actor_loss": -8.797492980957031, "critic_loss": 0.02503761649131775, "reward": 0.07133311033248901, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2428666204214096, 0.1538231521844864, 0.25276312232017517], "policy_updates": 33520, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5340.062581323, "contact_bce": 0.3117591142654419, "contact_force_loss": 0.0319247804582119, "terrain_level_mean": 3.134521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.996427536010742]} {"step": 33630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33630, "total_transitions": 137748480, "num_steps_per_env": 1, "wm_loss": 0.4587225615978241, "actor_loss": -8.772151947021484, "critic_loss": 0.034552641212940216, "reward": 0.07143532484769821, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24273964762687683, 0.15394596755504608, 0.2561020851135254], "policy_updates": 33530, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5343.5817729069995, "contact_bce": 0.320607453584671, "contact_force_loss": 0.032971013337373734, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9989323616027832, 0.9999687075614929, 2.996427536010742]} {"step": 33640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33640, "total_transitions": 137789440, "num_steps_per_env": 1, "wm_loss": 0.4156491458415985, "actor_loss": -8.763336181640625, "critic_loss": 0.021666109561920166, "reward": 0.07104804366827011, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24596074223518372, 0.15724708139896393, 0.25500836968421936], "policy_updates": 33540, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5347.09247291, "contact_bce": 0.3149746060371399, "contact_force_loss": 0.03213338926434517, "terrain_level_mean": 3.136474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9989323616027832, 0.9994316697120667, 2.996427536010742]} {"step": 33650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33650, "total_transitions": 137830400, "num_steps_per_env": 1, "wm_loss": 0.457664430141449, "actor_loss": -8.787253379821777, "critic_loss": 0.020276332274079323, "reward": 0.07106908410787582, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2506553530693054, 0.15736567974090576, 0.252144992351532], "policy_updates": 33550, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5350.606742327999, "contact_bce": 0.3188638389110565, "contact_force_loss": 0.03288562595844269, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9989323616027832, 0.9994316697120667, 2.996427536010742]} {"step": 33660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33660, "total_transitions": 137871360, "num_steps_per_env": 1, "wm_loss": 0.4415349066257477, "actor_loss": -8.832763671875, "critic_loss": 0.024884242564439774, "reward": 0.0709289088845253, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24866871535778046, 0.1603730320930481, 0.2535070478916168], "policy_updates": 33560, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5354.119507332, "contact_bce": 0.3199281096458435, "contact_force_loss": 0.03288791701197624, "terrain_level_mean": 3.135498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9969314336776733, 0.9994316697120667, 2.996427536010742]} {"step": 33670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33670, "total_transitions": 137912320, "num_steps_per_env": 1, "wm_loss": 0.42973870038986206, "actor_loss": -8.773478507995605, "critic_loss": 0.024958260357379913, "reward": 0.07099974155426025, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24643798172473907, 0.15978851914405823, 0.25302690267562866], "policy_updates": 33570, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5357.632538616, "contact_bce": 0.3187512755393982, "contact_force_loss": 0.031220119446516037, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9969314336776733, 0.9994316697120667, 2.996427536010742]} {"step": 33680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33680, "total_transitions": 137953280, "num_steps_per_env": 1, "wm_loss": 0.4539301097393036, "actor_loss": -8.815061569213867, "critic_loss": 0.02657339908182621, "reward": 0.07098529487848282, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2465004026889801, 0.1580650806427002, 0.2559681534767151], "policy_updates": 33580, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5361.142807030999, "contact_bce": 0.31976792216300964, "contact_force_loss": 0.032734621316194534, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9969314336776733, 0.9994316697120667, 2.996427536010742]} {"step": 33690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33690, "total_transitions": 137994240, "num_steps_per_env": 1, "wm_loss": 0.4589318633079529, "actor_loss": -8.811399459838867, "critic_loss": 0.02185381017625332, "reward": 0.070907823741436, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25096479058265686, 0.15754543244838715, 0.2561046779155731], "policy_updates": 33590, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5364.649995678, "contact_bce": 0.31553205847740173, "contact_force_loss": 0.03239118680357933, "terrain_level_mean": 3.13671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9969314336776733, 0.9994316697120667, 2.997204303741455]} {"step": 33700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33700, "total_transitions": 138035200, "num_steps_per_env": 1, "wm_loss": 0.4265080392360687, "actor_loss": -8.78573989868164, "critic_loss": 0.021387262269854546, "reward": 0.07091201841831207, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2543770372867584, 0.1573970913887024, 0.25758931040763855], "policy_updates": 33600, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5368.163316812, "contact_bce": 0.3167797029018402, "contact_force_loss": 0.03216937929391861, "terrain_level_mean": 3.1357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9982235431671143, 0.9994316697120667, 2.997204303741455]} {"step": 33710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33710, "total_transitions": 138076160, "num_steps_per_env": 1, "wm_loss": 0.4676859974861145, "actor_loss": -8.758626937866211, "critic_loss": 0.03288817033171654, "reward": 0.07081807404756546, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2554456293582916, 0.1578863561153412, 0.2570251524448395], "policy_updates": 33610, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5371.676034403999, "contact_bce": 0.321441113948822, "contact_force_loss": 0.03196951374411583, "terrain_level_mean": 3.135498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9982235431671143, 0.9994316697120667, 2.997204303741455]} {"step": 33720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33720, "total_transitions": 138117120, "num_steps_per_env": 1, "wm_loss": 0.4252808094024658, "actor_loss": -8.807928085327148, "critic_loss": 0.02378200925886631, "reward": 0.07088439166545868, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25029802322387695, 0.16060826182365417, 0.25686803460121155], "policy_updates": 33620, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5375.183734288, "contact_bce": 0.31387513875961304, "contact_force_loss": 0.031874507665634155, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9982235431671143, 0.9982025623321533, 2.997204303741455]} {"step": 33730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33730, "total_transitions": 138158080, "num_steps_per_env": 1, "wm_loss": 0.4637008011341095, "actor_loss": -8.783937454223633, "critic_loss": 0.026439813897013664, "reward": 0.07095701992511749, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25151094794273376, 0.16092917323112488, 0.2561720311641693], "policy_updates": 33630, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5378.700241801, "contact_bce": 0.31705817580223083, "contact_force_loss": 0.03326337784528732, "terrain_level_mean": 3.13671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9982235431671143, 0.9982025623321533, 2.997204303741455]} {"step": 33740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33740, "total_transitions": 138199040, "num_steps_per_env": 1, "wm_loss": 0.44222894310951233, "actor_loss": -8.76352310180664, "critic_loss": 0.02830597199499607, "reward": 0.07098565250635147, "falls": 2, "interval_steps": 10, "velocity_mae": [0.248702272772789, 0.1604488641023636, 0.25581371784210205], "policy_updates": 33640, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5382.212942155999, "contact_bce": 0.3154732584953308, "contact_force_loss": 0.03222082927823067, "terrain_level_mean": 3.137939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9982235431671143, 0.9982025623321533, 2.997204303741455]} {"step": 33750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33750, "total_transitions": 138240000, "num_steps_per_env": 1, "wm_loss": 0.4349724352359772, "actor_loss": -8.778989791870117, "critic_loss": 0.026177672669291496, "reward": 0.07060135900974274, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25071293115615845, 0.16118928790092468, 0.2603098154067993], "policy_updates": 33650, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5385.741291439, "contact_bce": 0.31743931770324707, "contact_force_loss": 0.03228018060326576, "terrain_level_mean": 3.136962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9982235431671143, 0.9982025623321533, 2.997204303741455]} {"step": 33760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33760, "total_transitions": 138280960, "num_steps_per_env": 1, "wm_loss": 0.4579344391822815, "actor_loss": -8.780668258666992, "critic_loss": 0.022427113726735115, "reward": 0.07029888033866882, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2569611370563507, 0.16057519614696503, 0.2621297538280487], "policy_updates": 33660, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5389.257592907999, "contact_bce": 0.32072627544403076, "contact_force_loss": 0.03236822038888931, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9982235431671143, 0.9979923963546753, 2.997204303741455]} {"step": 33770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33770, "total_transitions": 138321920, "num_steps_per_env": 1, "wm_loss": 0.45244237780570984, "actor_loss": -8.808481216430664, "critic_loss": 0.02427619695663452, "reward": 0.07053565233945847, "falls": 9, "interval_steps": 10, "velocity_mae": [0.25404638051986694, 0.16048915684223175, 0.2601299285888672], "policy_updates": 33670, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5392.773367000999, "contact_bce": 0.3218003213405609, "contact_force_loss": 0.03221505507826805, "terrain_level_mean": 3.136474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9982235431671143, 0.9979923963546753, 2.997204303741455]} {"step": 33780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33780, "total_transitions": 138362880, "num_steps_per_env": 1, "wm_loss": 0.4522991478443146, "actor_loss": -8.762679100036621, "critic_loss": 0.025457516312599182, "reward": 0.0709356889128685, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2519092857837677, 0.16057652235031128, 0.2525496184825897], "policy_updates": 33680, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5396.273027272, "contact_bce": 0.3231870234012604, "contact_force_loss": 0.03300303965806961, "terrain_level_mean": 3.13720703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9982235431671143, 0.9979923963546753, 2.997204303741455]} {"step": 33790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33790, "total_transitions": 138403840, "num_steps_per_env": 1, "wm_loss": 0.4498072564601898, "actor_loss": -8.782892227172852, "critic_loss": 0.024361595511436462, "reward": 0.07052241265773773, "falls": 5, "interval_steps": 10, "velocity_mae": [0.253133088350296, 0.159324049949646, 0.25426116585731506], "policy_updates": 33690, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5399.791907383999, "contact_bce": 0.32126978039741516, "contact_force_loss": 0.032626841217279434, "terrain_level_mean": 3.137451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9944119453430176, 0.9979923963546753, 2.9974865913391113]} {"step": 33800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33800, "total_transitions": 138444800, "num_steps_per_env": 1, "wm_loss": 0.4356316328048706, "actor_loss": -8.750396728515625, "critic_loss": 0.027716388925909996, "reward": 0.07054691761732101, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24948011338710785, 0.15871122479438782, 0.25476330518722534], "policy_updates": 33700, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5403.311614106, "contact_bce": 0.32030418515205383, "contact_force_loss": 0.03306322917342186, "terrain_level_mean": 3.13818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9944119453430176, 0.9979923963546753, 2.9974865913391113]} {"step": 33810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33810, "total_transitions": 138485760, "num_steps_per_env": 1, "wm_loss": 0.4653284251689911, "actor_loss": -8.753029823303223, "critic_loss": 0.04911027476191521, "reward": 0.07036592811346054, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2466391921043396, 0.15886983275413513, 0.2559235394001007], "policy_updates": 33710, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5406.831231679, "contact_bce": 0.32365912199020386, "contact_force_loss": 0.033385470509529114, "terrain_level_mean": 3.138427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9944119453430176, 0.9979923963546753, 2.9974865913391113]} {"step": 33820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33820, "total_transitions": 138526720, "num_steps_per_env": 1, "wm_loss": 0.46123194694519043, "actor_loss": -8.790613174438477, "critic_loss": 0.02682647481560707, "reward": 0.0706666111946106, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24552953243255615, 0.15858137607574463, 0.25779038667678833], "policy_updates": 33720, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5410.349058534, "contact_bce": 0.3188009262084961, "contact_force_loss": 0.03378472477197647, "terrain_level_mean": 3.13818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9944119453430176, 0.9979923963546753, 2.9974865913391113]} {"step": 33830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33830, "total_transitions": 138567680, "num_steps_per_env": 1, "wm_loss": 0.45751312375068665, "actor_loss": -8.7857084274292, "critic_loss": 0.03170406073331833, "reward": 0.07093503326177597, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24974124133586884, 0.16145020723342896, 0.25565198063850403], "policy_updates": 33730, "skipped_updates": 0, "invalid_env_resets": 42, "elapsed_s": 5413.869925278999, "contact_bce": 0.31432804465293884, "contact_force_loss": 0.03220485523343086, "terrain_level_mean": 3.1376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9944119453430176, 0.9979923963546753, 2.9974865913391113]} RECOVERY reset 1 invalid environments; first IDs=[2833] {"step": 33840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33840, "total_transitions": 138608640, "num_steps_per_env": 1, "wm_loss": 0.42072656750679016, "actor_loss": -8.785594940185547, "critic_loss": 0.026169270277023315, "reward": 0.07091566175222397, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2469203770160675, 0.15854237973690033, 0.2538953721523285], "policy_updates": 33740, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5417.408344091999, "contact_bce": 0.3145092725753784, "contact_force_loss": 0.03138115629553795, "terrain_level_mean": 3.137451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9944119453430176, 0.9979923963546753, 2.9974865913391113]} {"step": 33850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33850, "total_transitions": 138649600, "num_steps_per_env": 1, "wm_loss": 0.41497474908828735, "actor_loss": -8.736383438110352, "critic_loss": 0.03777981549501419, "reward": 0.07141771912574768, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24335139989852905, 0.15765975415706635, 0.25455260276794434], "policy_updates": 33750, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5420.912687634, "contact_bce": 0.3158338963985443, "contact_force_loss": 0.03176817297935486, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9944119453430176, 0.9979923963546753, 2.9974865913391113]} {"step": 33860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33860, "total_transitions": 138690560, "num_steps_per_env": 1, "wm_loss": 0.4538729786872864, "actor_loss": -8.755990028381348, "critic_loss": 0.029740681871771812, "reward": 0.0713706910610199, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2482827752828598, 0.15986768901348114, 0.252206414937973], "policy_updates": 33760, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5424.423308648, "contact_bce": 0.32027867436408997, "contact_force_loss": 0.03300024941563606, "terrain_level_mean": 3.13671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9944119453430176, 0.9974524974822998, 2.9974865913391113]} {"step": 33870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33870, "total_transitions": 138731520, "num_steps_per_env": 1, "wm_loss": 0.44822707772254944, "actor_loss": -8.766485214233398, "critic_loss": 0.0242451261729002, "reward": 0.07142426073551178, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24489444494247437, 0.1578548103570938, 0.25388163328170776], "policy_updates": 33770, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5427.933508317, "contact_bce": 0.3120901584625244, "contact_force_loss": 0.03287864103913307, "terrain_level_mean": 3.136474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9944119453430176, 0.9995752573013306, 2.9974865913391113]} {"step": 33880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33880, "total_transitions": 138772480, "num_steps_per_env": 1, "wm_loss": 0.45135563611984253, "actor_loss": -8.718392372131348, "critic_loss": 0.029564371332526207, "reward": 0.0713648870587349, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24164481461048126, 0.16004478931427002, 0.25301578640937805], "policy_updates": 33780, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5431.451638568, "contact_bce": 0.31469976902008057, "contact_force_loss": 0.03227885067462921, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33890, "total_transitions": 138813440, "num_steps_per_env": 1, "wm_loss": 0.4841640591621399, "actor_loss": -8.785877227783203, "critic_loss": 0.02088315598666668, "reward": 0.07092594355344772, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2394602745771408, 0.16101180016994476, 0.2552744150161743], "policy_updates": 33790, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5434.971076968, "contact_bce": 0.32290011644363403, "contact_force_loss": 0.03365778923034668, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33900, "total_transitions": 138854400, "num_steps_per_env": 1, "wm_loss": 0.48049217462539673, "actor_loss": -8.732658386230469, "critic_loss": 0.0385352224111557, "reward": 0.07117721438407898, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23883050680160522, 0.15904270112514496, 0.25010886788368225], "policy_updates": 33800, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5438.486729327, "contact_bce": 0.3211773633956909, "contact_force_loss": 0.03354020416736603, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33910, "total_transitions": 138895360, "num_steps_per_env": 1, "wm_loss": 0.46772629022598267, "actor_loss": -8.762353897094727, "critic_loss": 0.02310081198811531, "reward": 0.07164803892374039, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23858186602592468, 0.15679018199443817, 0.24926146864891052], "policy_updates": 33810, "skipped_updates": 0, "invalid_env_resets": 43, "elapsed_s": 5442.008404239, "contact_bce": 0.31584981083869934, "contact_force_loss": 0.03323371335864067, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} RECOVERY reset 1 invalid environments; first IDs=[2202] {"step": 33920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33920, "total_transitions": 138936320, "num_steps_per_env": 1, "wm_loss": 0.44256946444511414, "actor_loss": -8.777830123901367, "critic_loss": 0.03052845597267151, "reward": 0.07118009775876999, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2408919334411621, 0.15675269067287445, 0.24968981742858887], "policy_updates": 33820, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5445.541168659, "contact_bce": 0.316547691822052, "contact_force_loss": 0.03248749300837517, "terrain_level_mean": 3.134033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333740234375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33930, "total_transitions": 138977280, "num_steps_per_env": 1, "wm_loss": 0.4391005039215088, "actor_loss": -8.779712677001953, "critic_loss": 0.024808842688798904, "reward": 0.07123129814863205, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24500787258148193, 0.157340869307518, 0.2501974403858185], "policy_updates": 33830, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5449.052910822, "contact_bce": 0.31793805956840515, "contact_force_loss": 0.032576609402894974, "terrain_level_mean": 3.13427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333740234375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33940, "total_transitions": 139018240, "num_steps_per_env": 1, "wm_loss": 0.4816375970840454, "actor_loss": -8.76707935333252, "critic_loss": 0.024314120411872864, "reward": 0.07113756239414215, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24446769058704376, 0.15868455171585083, 0.25141212344169617], "policy_updates": 33840, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5452.563454859999, "contact_bce": 0.32043182849884033, "contact_force_loss": 0.03227877616882324, "terrain_level_mean": 3.135009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33950, "total_transitions": 139059200, "num_steps_per_env": 1, "wm_loss": 0.46399882435798645, "actor_loss": -8.745721817016602, "critic_loss": 0.02748851291835308, "reward": 0.07088277488946915, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24437986314296722, 0.15950819849967957, 0.25389623641967773], "policy_updates": 33850, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5456.088335617999, "contact_bce": 0.3195700943470001, "contact_force_loss": 0.03300139307975769, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33960, "total_transitions": 139100160, "num_steps_per_env": 1, "wm_loss": 0.45014458894729614, "actor_loss": -8.720640182495117, "critic_loss": 0.04176187887787819, "reward": 0.07058341056108475, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2467842847108841, 0.1594378501176834, 0.25509804487228394], "policy_updates": 33860, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5459.608643297, "contact_bce": 0.31591179966926575, "contact_force_loss": 0.03320826217532158, "terrain_level_mean": 3.135498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33970, "total_transitions": 139141120, "num_steps_per_env": 1, "wm_loss": 0.46524763107299805, "actor_loss": -8.711909294128418, "critic_loss": 0.030577486380934715, "reward": 0.07097641378641129, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24419187009334564, 0.1571047306060791, 0.254960298538208], "policy_updates": 33870, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5463.130674624999, "contact_bce": 0.3166455924510956, "contact_force_loss": 0.0325409360229969, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33980, "total_transitions": 139182080, "num_steps_per_env": 1, "wm_loss": 0.4317091405391693, "actor_loss": -8.747533798217773, "critic_loss": 0.02413596771657467, "reward": 0.07088374346494675, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24530145525932312, 0.1553356647491455, 0.256307452917099], "policy_updates": 33880, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5466.649959368, "contact_bce": 0.31655243039131165, "contact_force_loss": 0.032676856964826584, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 33990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 33990, "total_transitions": 139223040, "num_steps_per_env": 1, "wm_loss": 0.4424305260181427, "actor_loss": -8.753243446350098, "critic_loss": 0.02810978889465332, "reward": 0.07083944976329803, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24294622242450714, 0.15559279918670654, 0.2538514733314514], "policy_updates": 33890, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5470.176067378, "contact_bce": 0.3187628984451294, "contact_force_loss": 0.03162415698170662, "terrain_level_mean": 3.13671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 34000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34000, "total_transitions": 139264000, "num_steps_per_env": 1, "wm_loss": 0.43078064918518066, "actor_loss": -8.75672721862793, "critic_loss": 0.031787771731615067, "reward": 0.0708487257361412, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23946301639080048, 0.1564389318227768, 0.256070077419281], "policy_updates": 33900, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5473.7017685559995, "contact_bce": 0.3191101551055908, "contact_force_loss": 0.03240592032670975, "terrain_level_mean": 3.13818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 34010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34010, "total_transitions": 139304960, "num_steps_per_env": 1, "wm_loss": 0.449054092168808, "actor_loss": -8.744658470153809, "critic_loss": 0.0238533616065979, "reward": 0.07098348438739777, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24098071455955505, 0.15566541254520416, 0.25473055243492126], "policy_updates": 33910, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5477.248129852999, "contact_bce": 0.31461015343666077, "contact_force_loss": 0.03209151700139046, "terrain_level_mean": 3.137939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 34020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34020, "total_transitions": 139345920, "num_steps_per_env": 1, "wm_loss": 0.4196625053882599, "actor_loss": -8.76610279083252, "critic_loss": 0.024325696751475334, "reward": 0.07121815532445908, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2401275932788849, 0.15637630224227905, 0.2527705132961273], "policy_updates": 33920, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5480.77273877, "contact_bce": 0.31685227155685425, "contact_force_loss": 0.03218922019004822, "terrain_level_mean": 3.138916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9994242191314697, 0.9995752573013306, 2.9974865913391113]} {"step": 34030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34030, "total_transitions": 139386880, "num_steps_per_env": 1, "wm_loss": 0.45023229718208313, "actor_loss": -8.713908195495605, "critic_loss": 0.041543539613485336, "reward": 0.07061666250228882, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24631080031394958, 0.1578020304441452, 0.25444892048835754], "policy_updates": 33930, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5484.544957735, "contact_bce": 0.31273171305656433, "contact_force_loss": 0.031933534890413284, "terrain_level_mean": 3.13818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9986324310302734, 0.9995752573013306, 2.9974865913391113]} {"step": 34040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34040, "total_transitions": 139427840, "num_steps_per_env": 1, "wm_loss": 0.45274409651756287, "actor_loss": -8.760049819946289, "critic_loss": 0.030137760564684868, "reward": 0.07037188857793808, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2499401569366455, 0.15734051167964935, 0.25345757603645325], "policy_updates": 33940, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5488.0592866, "contact_bce": 0.316720187664032, "contact_force_loss": 0.03253567963838577, "terrain_level_mean": 3.138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9986324310302734, 0.9995752573013306, 2.9974865913391113]} {"step": 34050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34050, "total_transitions": 139468800, "num_steps_per_env": 1, "wm_loss": 0.42773547768592834, "actor_loss": -8.768634796142578, "critic_loss": 0.018785756081342697, "reward": 0.07115571200847626, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24615749716758728, 0.1572784185409546, 0.2530181407928467], "policy_updates": 33950, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5491.570567827999, "contact_bce": 0.31462427973747253, "contact_force_loss": 0.03185896575450897, "terrain_level_mean": 3.138916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9986324310302734, 0.9995752573013306, 2.9974865913391113]} {"step": 34060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34060, "total_transitions": 139509760, "num_steps_per_env": 1, "wm_loss": 0.4560045897960663, "actor_loss": -8.774404525756836, "critic_loss": 0.02425478957593441, "reward": 0.07161720842123032, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24355953931808472, 0.1583249419927597, 0.2512257993221283], "policy_updates": 33960, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5495.0801983149995, "contact_bce": 0.32112371921539307, "contact_force_loss": 0.03304174542427063, "terrain_level_mean": 3.1376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9986324310302734, 0.9995752573013306, 2.9974865913391113]} {"step": 34070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34070, "total_transitions": 139550720, "num_steps_per_env": 1, "wm_loss": 0.48265302181243896, "actor_loss": -8.794856071472168, "critic_loss": 0.028235096484422684, "reward": 0.07137339562177658, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24465933442115784, 0.1566271334886551, 0.2557629644870758], "policy_updates": 33970, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5498.5890758059995, "contact_bce": 0.3211934566497803, "contact_force_loss": 0.03240245208144188, "terrain_level_mean": 3.137451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9986324310302734, 0.9995752573013306, 2.998732328414917]} {"step": 34080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34080, "total_transitions": 139591680, "num_steps_per_env": 1, "wm_loss": 0.43371397256851196, "actor_loss": -8.717528343200684, "critic_loss": 0.03240126371383667, "reward": 0.07155539840459824, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24441422522068024, 0.15694597363471985, 0.25178855657577515], "policy_updates": 33980, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5502.0990627989995, "contact_bce": 0.3191704750061035, "contact_force_loss": 0.03202175348997116, "terrain_level_mean": 3.13671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9986324310302734, 0.9995752573013306, 2.998732328414917]} {"step": 34090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34090, "total_transitions": 139632640, "num_steps_per_env": 1, "wm_loss": 0.44119226932525635, "actor_loss": -8.750761032104492, "critic_loss": 0.03514512628316879, "reward": 0.07157053798437119, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23842157423496246, 0.15584899485111237, 0.2489459365606308], "policy_updates": 33990, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5505.600381204999, "contact_bce": 0.32045647501945496, "contact_force_loss": 0.03272629529237747, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9975268840789795, 0.9995752573013306, 2.998732328414917]} {"step": 34100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34100, "total_transitions": 139673600, "num_steps_per_env": 1, "wm_loss": 0.447535902261734, "actor_loss": -8.789069175720215, "critic_loss": 0.029782986268401146, "reward": 0.07120289653539658, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24020107090473175, 0.15693211555480957, 0.2511308789253235], "policy_updates": 34000, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5509.105075589, "contact_bce": 0.31521672010421753, "contact_force_loss": 0.0315568670630455, "terrain_level_mean": 3.134033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9975268840789795, 0.9995752573013306, 2.998732328414917]} {"step": 34110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34110, "total_transitions": 139714560, "num_steps_per_env": 1, "wm_loss": 0.43790683150291443, "actor_loss": -8.705989837646484, "critic_loss": 0.02437750995159149, "reward": 0.07064493745565414, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24376365542411804, 0.159312441945076, 0.24892300367355347], "policy_updates": 34010, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5512.6203835, "contact_bce": 0.3154121935367584, "contact_force_loss": 0.03261486813426018, "terrain_level_mean": 3.13427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9975268840789795, 0.9995752573013306, 2.998732328414917]} {"step": 34120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34120, "total_transitions": 139755520, "num_steps_per_env": 1, "wm_loss": 0.44898274540901184, "actor_loss": -8.712738037109375, "critic_loss": 0.022160818800330162, "reward": 0.07093318551778793, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2431749403476715, 0.15891654789447784, 0.2502346932888031], "policy_updates": 34020, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5516.130805981999, "contact_bce": 0.32040366530418396, "contact_force_loss": 0.03298206627368927, "terrain_level_mean": 3.134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9975268840789795, 0.9995752573013306, 2.998732328414917]} {"step": 34130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34130, "total_transitions": 139796480, "num_steps_per_env": 1, "wm_loss": 0.4261060953140259, "actor_loss": -8.762115478515625, "critic_loss": 0.027557581663131714, "reward": 0.07109048217535019, "falls": 11, "interval_steps": 10, "velocity_mae": [0.24453380703926086, 0.15689383447170258, 0.2528878450393677], "policy_updates": 34030, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5519.653142182, "contact_bce": 0.31637516617774963, "contact_force_loss": 0.031881336122751236, "terrain_level_mean": 3.132568359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.998732328414917]} {"step": 34140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34140, "total_transitions": 139837440, "num_steps_per_env": 1, "wm_loss": 0.4228172302246094, "actor_loss": -8.751197814941406, "critic_loss": 0.027453992515802383, "reward": 0.07117883861064911, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24486498534679413, 0.15694645047187805, 0.2509874403476715], "policy_updates": 34040, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5523.162830308999, "contact_bce": 0.31368350982666016, "contact_force_loss": 0.03223831579089165, "terrain_level_mean": 3.134033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.998732328414917]} {"step": 34150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34150, "total_transitions": 139878400, "num_steps_per_env": 1, "wm_loss": 0.44653213024139404, "actor_loss": -8.74441909790039, "critic_loss": 0.02484857104718685, "reward": 0.07137610018253326, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2420935034751892, 0.15694384276866913, 0.24924278259277344], "policy_updates": 34050, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5526.676538654, "contact_bce": 0.31430450081825256, "contact_force_loss": 0.03187252953648567, "terrain_level_mean": 3.134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.998732328414917]} {"step": 34160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34160, "total_transitions": 139919360, "num_steps_per_env": 1, "wm_loss": 0.45856714248657227, "actor_loss": -8.750221252441406, "critic_loss": 0.022377043962478638, "reward": 0.07162930816411972, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24387246370315552, 0.15458014607429504, 0.2508116364479065], "policy_updates": 34060, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5530.195350597, "contact_bce": 0.3167519271373749, "contact_force_loss": 0.032951779663562775, "terrain_level_mean": 3.134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.998732328414917]} {"step": 34170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34170, "total_transitions": 139960320, "num_steps_per_env": 1, "wm_loss": 0.4714904725551605, "actor_loss": -8.745012283325195, "critic_loss": 0.020215153694152832, "reward": 0.07189656794071198, "falls": 2, "interval_steps": 10, "velocity_mae": [0.245584174990654, 0.1556035727262497, 0.2551572024822235], "policy_updates": 34070, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5533.7187005959995, "contact_bce": 0.317428320646286, "contact_force_loss": 0.03323754295706749, "terrain_level_mean": 3.135498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.998732328414917]} {"step": 34180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34180, "total_transitions": 140001280, "num_steps_per_env": 1, "wm_loss": 0.44187799096107483, "actor_loss": -8.75394058227539, "critic_loss": 0.02495194599032402, "reward": 0.07191705703735352, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2453497350215912, 0.1563127487897873, 0.2556926906108856], "policy_updates": 34080, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5537.240184231, "contact_bce": 0.3237437307834625, "contact_force_loss": 0.03283457085490227, "terrain_level_mean": 3.135009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.998732328414917]} {"step": 34190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34190, "total_transitions": 140042240, "num_steps_per_env": 1, "wm_loss": 0.4273006319999695, "actor_loss": -8.747110366821289, "critic_loss": 0.026544107124209404, "reward": 0.07189071178436279, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2442244291305542, 0.15563195943832397, 0.2514857053756714], "policy_updates": 34090, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5540.764197072, "contact_bce": 0.31781935691833496, "contact_force_loss": 0.032403312623500824, "terrain_level_mean": 3.135009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.9895966053009033]} {"step": 34200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34200, "total_transitions": 140083200, "num_steps_per_env": 1, "wm_loss": 0.4532385468482971, "actor_loss": -8.746782302856445, "critic_loss": 0.028163624927401543, "reward": 0.0721883773803711, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2460036277770996, 0.15378989279270172, 0.24982894957065582], "policy_updates": 34100, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5544.275599703, "contact_bce": 0.3203451335430145, "contact_force_loss": 0.03234034776687622, "terrain_level_mean": 3.13525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9975268840789795, 0.999221920967102, 2.995879650115967]} {"step": 34210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34210, "total_transitions": 140124160, "num_steps_per_env": 1, "wm_loss": 0.45951148867607117, "actor_loss": -8.765743255615234, "critic_loss": 0.02445446513593197, "reward": 0.07241085171699524, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2431473582983017, 0.14935404062271118, 0.24747134745121002], "policy_updates": 34110, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5547.782436011, "contact_bce": 0.3190441131591797, "contact_force_loss": 0.03296453133225441, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9975268840789795, 0.9983316659927368, 2.995879650115967]} {"step": 34220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34220, "total_transitions": 140165120, "num_steps_per_env": 1, "wm_loss": 0.443317711353302, "actor_loss": -8.701849937438965, "critic_loss": 0.02643345668911934, "reward": 0.07230717688798904, "falls": 3, "interval_steps": 10, "velocity_mae": [0.241839200258255, 0.1498645842075348, 0.24987122416496277], "policy_updates": 34120, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5551.299945164, "contact_bce": 0.31915387511253357, "contact_force_loss": 0.032492879778146744, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9975165128707886, 0.9983316659927368, 2.995879650115967]} {"step": 34230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34230, "total_transitions": 140206080, "num_steps_per_env": 1, "wm_loss": 0.4800827205181122, "actor_loss": -8.72369384765625, "critic_loss": 0.023895535618066788, "reward": 0.07255028188228607, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2395702600479126, 0.1507592350244522, 0.25052738189697266], "policy_updates": 34130, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5554.817005368, "contact_bce": 0.31274572014808655, "contact_force_loss": 0.0327400378882885, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9975165128707886, 0.9983316659927368, 2.995879650115967]} {"step": 34240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34240, "total_transitions": 140247040, "num_steps_per_env": 1, "wm_loss": 0.45051369071006775, "actor_loss": -8.747211456298828, "critic_loss": 0.019527679309248924, "reward": 0.07214684784412384, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2383725792169571, 0.15378159284591675, 0.25077947974205017], "policy_updates": 34140, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5558.334332613999, "contact_bce": 0.3214936852455139, "contact_force_loss": 0.03289466351270676, "terrain_level_mean": 3.135986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9975165128707886, 0.9983316659927368, 2.995879650115967]} {"step": 34250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34250, "total_transitions": 140288000, "num_steps_per_env": 1, "wm_loss": 0.44607600569725037, "actor_loss": -8.779533386230469, "critic_loss": 0.022637290880084038, "reward": 0.07197266817092896, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23867622017860413, 0.1546216905117035, 0.2522168755531311], "policy_updates": 34150, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5561.844621748, "contact_bce": 0.31653448939323425, "contact_force_loss": 0.03304089605808258, "terrain_level_mean": 3.13623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9975165128707886, 0.9983316659927368, 2.995879650115967]} {"step": 34260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34260, "total_transitions": 140328960, "num_steps_per_env": 1, "wm_loss": 0.44674134254455566, "actor_loss": -8.749141693115234, "critic_loss": 0.023670969530940056, "reward": 0.07210860401391983, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24090957641601562, 0.15362493693828583, 0.25050821900367737], "policy_updates": 34160, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5565.349918229999, "contact_bce": 0.31859520077705383, "contact_force_loss": 0.032849010080099106, "terrain_level_mean": 3.137451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9975165128707886, 0.9983316659927368, 2.995879650115967]} {"step": 34270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34270, "total_transitions": 140369920, "num_steps_per_env": 1, "wm_loss": 0.4417169988155365, "actor_loss": -8.73841667175293, "critic_loss": 0.03593156859278679, "reward": 0.07206838577985764, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24068717658519745, 0.15331684052944183, 0.2514724135398865], "policy_updates": 34170, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5568.865950329, "contact_bce": 0.31533780694007874, "contact_force_loss": 0.032650526612997055, "terrain_level_mean": 3.138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} {"step": 34280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34280, "total_transitions": 140410880, "num_steps_per_env": 1, "wm_loss": 0.41765719652175903, "actor_loss": -8.763311386108398, "critic_loss": 0.045064400881528854, "reward": 0.07195650786161423, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24405503273010254, 0.15575803816318512, 0.25247621536254883], "policy_updates": 34180, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5572.378418558, "contact_bce": 0.3178509473800659, "contact_force_loss": 0.032654549926519394, "terrain_level_mean": 3.139404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} {"step": 34290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34290, "total_transitions": 140451840, "num_steps_per_env": 1, "wm_loss": 0.45910921692848206, "actor_loss": -8.770291328430176, "critic_loss": 0.02323978953063488, "reward": 0.07193925231695175, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24874930083751678, 0.1546865701675415, 0.2509280741214752], "policy_updates": 34190, "skipped_updates": 0, "invalid_env_resets": 44, "elapsed_s": 5575.8886487849995, "contact_bce": 0.313544899225235, "contact_force_loss": 0.03234933316707611, "terrain_level_mean": 3.138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} RECOVERY reset 1 invalid environments; first IDs=[646] {"step": 34300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34300, "total_transitions": 140492800, "num_steps_per_env": 1, "wm_loss": 0.4596375524997711, "actor_loss": -8.763725280761719, "critic_loss": 0.024468321353197098, "reward": 0.07172031700611115, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24745917320251465, 0.15514251589775085, 0.2515025734901428], "policy_updates": 34200, "skipped_updates": 0, "invalid_env_resets": 45, "elapsed_s": 5579.410354975999, "contact_bce": 0.31009015440940857, "contact_force_loss": 0.032672490924596786, "terrain_level_mean": 3.138427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} {"step": 34310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34310, "total_transitions": 140533760, "num_steps_per_env": 1, "wm_loss": 0.4444546401500702, "actor_loss": -8.736929893493652, "critic_loss": 0.030260134488344193, "reward": 0.07178274542093277, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24265103042125702, 0.15415740013122559, 0.2484370321035385], "policy_updates": 34210, "skipped_updates": 0, "invalid_env_resets": 45, "elapsed_s": 5582.925923434999, "contact_bce": 0.31839796900749207, "contact_force_loss": 0.03261350840330124, "terrain_level_mean": 3.13818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} RECOVERY reset 1 invalid environments; first IDs=[532] {"step": 34320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34320, "total_transitions": 140574720, "num_steps_per_env": 1, "wm_loss": 0.46470722556114197, "actor_loss": -8.81442642211914, "critic_loss": 0.02476705051958561, "reward": 0.07207097858190536, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23928721249103546, 0.15222138166427612, 0.2512627840042114], "policy_updates": 34220, "skipped_updates": 0, "invalid_env_resets": 46, "elapsed_s": 5586.451222121, "contact_bce": 0.31993234157562256, "contact_force_loss": 0.03207603096961975, "terrain_level_mean": 3.138916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} {"step": 34330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34330, "total_transitions": 140615680, "num_steps_per_env": 1, "wm_loss": 0.40794244408607483, "actor_loss": -8.782130241394043, "critic_loss": 0.027678249403834343, "reward": 0.07184050977230072, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23845726251602173, 0.15306740999221802, 0.24944259226322174], "policy_updates": 34230, "skipped_updates": 0, "invalid_env_resets": 46, "elapsed_s": 5589.972310712, "contact_bce": 0.31472718715667725, "contact_force_loss": 0.03171593323349953, "terrain_level_mean": 3.139892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} {"step": 34340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34340, "total_transitions": 140656640, "num_steps_per_env": 1, "wm_loss": 0.461200088262558, "actor_loss": -8.796442031860352, "critic_loss": 0.025931382551789284, "reward": 0.07197362929582596, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23684468865394592, 0.15228314697742462, 0.24785757064819336], "policy_updates": 34240, "skipped_updates": 0, "invalid_env_resets": 46, "elapsed_s": 5593.4815536569995, "contact_bce": 0.3173668682575226, "contact_force_loss": 0.032632723450660706, "terrain_level_mean": 3.14013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} {"step": 34350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34350, "total_transitions": 140697600, "num_steps_per_env": 1, "wm_loss": 0.4501653015613556, "actor_loss": -8.752552032470703, "critic_loss": 0.02540629543364048, "reward": 0.07137518376111984, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24281008541584015, 0.15432974696159363, 0.2527543306350708], "policy_updates": 34250, "skipped_updates": 0, "invalid_env_resets": 46, "elapsed_s": 5596.9929282739995, "contact_bce": 0.3191368579864502, "contact_force_loss": 0.03287787362933159, "terrain_level_mean": 3.139892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9984357357025146, 0.9983316659927368, 2.995879650115967]} {"step": 34360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34360, "total_transitions": 140738560, "num_steps_per_env": 1, "wm_loss": 0.4423755705356598, "actor_loss": -8.730968475341797, "critic_loss": 0.018815984949469566, "reward": 0.07150710374116898, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2465895414352417, 0.15191935002803802, 0.25138020515441895], "policy_updates": 34260, "skipped_updates": 0, "invalid_env_resets": 46, "elapsed_s": 5600.5010149889995, "contact_bce": 0.3211311399936676, "contact_force_loss": 0.032379698008298874, "terrain_level_mean": 3.139404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.995879650115967]} {"step": 34370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34370, "total_transitions": 140779520, "num_steps_per_env": 1, "wm_loss": 0.4063153564929962, "actor_loss": -8.77304458618164, "critic_loss": 0.026535356417298317, "reward": 0.07148294150829315, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24362042546272278, 0.15195848047733307, 0.2519327700138092], "policy_updates": 34270, "skipped_updates": 0, "invalid_env_resets": 46, "elapsed_s": 5604.01166347, "contact_bce": 0.3149328827857971, "contact_force_loss": 0.03152075409889221, "terrain_level_mean": 3.139892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.995879650115967]} {"step": 34380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34380, "total_transitions": 140820480, "num_steps_per_env": 1, "wm_loss": 0.4248124957084656, "actor_loss": -8.796223640441895, "critic_loss": 0.021857960149645805, "reward": 0.07153701037168503, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24343155324459076, 0.15318217873573303, 0.2558601498603821], "policy_updates": 34280, "skipped_updates": 0, "invalid_env_resets": 46, "elapsed_s": 5607.5228690839995, "contact_bce": 0.3221544325351715, "contact_force_loss": 0.032525915652513504, "terrain_level_mean": 3.139892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.995879650115967]} RECOVERY reset 1 invalid environments; first IDs=[1666] {"step": 34390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34390, "total_transitions": 140861440, "num_steps_per_env": 1, "wm_loss": 0.4577273428440094, "actor_loss": -8.787801742553711, "critic_loss": 0.019488822668790817, "reward": 0.07133612036705017, "falls": 4, "interval_steps": 10, "velocity_mae": [0.245121031999588, 0.15338945388793945, 0.25418198108673096], "policy_updates": 34290, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5611.046654094, "contact_bce": 0.32313796877861023, "contact_force_loss": 0.033231399953365326, "terrain_level_mean": 3.140380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.995879650115967]} {"step": 34400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34400, "total_transitions": 140902400, "num_steps_per_env": 1, "wm_loss": 0.4295768439769745, "actor_loss": -8.745992660522461, "critic_loss": 0.023348400369286537, "reward": 0.07148849219083786, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2402935028076172, 0.15134157240390778, 0.25176018476486206], "policy_updates": 34300, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5614.557113440999, "contact_bce": 0.3161830008029938, "contact_force_loss": 0.03250977396965027, "terrain_level_mean": 3.141357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.995879650115967]} {"step": 34410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34410, "total_transitions": 140943360, "num_steps_per_env": 1, "wm_loss": 0.4504050016403198, "actor_loss": -8.792930603027344, "critic_loss": 0.020623866468667984, "reward": 0.07157518714666367, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2405109852552414, 0.15261486172676086, 0.2503844201564789], "policy_updates": 34310, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5618.0691241899995, "contact_bce": 0.32138416171073914, "contact_force_loss": 0.031979065388441086, "terrain_level_mean": 3.14111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34420, "total_transitions": 140984320, "num_steps_per_env": 1, "wm_loss": 0.43539777398109436, "actor_loss": -8.765636444091797, "critic_loss": 0.02498343028128147, "reward": 0.07193080335855484, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24129365384578705, 0.1527334302663803, 0.25229665637016296], "policy_updates": 34320, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5621.578001833, "contact_bce": 0.31246915459632874, "contact_force_loss": 0.031858429312705994, "terrain_level_mean": 3.14111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34430, "total_transitions": 141025280, "num_steps_per_env": 1, "wm_loss": 0.43792861700057983, "actor_loss": -8.74937629699707, "critic_loss": 0.0292894896119833, "reward": 0.07186127454042435, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24456192553043365, 0.15132687985897064, 0.25100433826446533], "policy_updates": 34330, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5625.088342931999, "contact_bce": 0.30977755784988403, "contact_force_loss": 0.03182706981897354, "terrain_level_mean": 3.1416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34440, "total_transitions": 141066240, "num_steps_per_env": 1, "wm_loss": 0.4498741328716278, "actor_loss": -8.753079414367676, "critic_loss": 0.02483041025698185, "reward": 0.07189183682203293, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24019646644592285, 0.15220576524734497, 0.2534503638744354], "policy_updates": 34340, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5628.594916796, "contact_bce": 0.31522712111473083, "contact_force_loss": 0.03176575154066086, "terrain_level_mean": 3.142822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34450, "total_transitions": 141107200, "num_steps_per_env": 1, "wm_loss": 0.4585615396499634, "actor_loss": -8.755356788635254, "critic_loss": 0.019325530156493187, "reward": 0.07163345068693161, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23724883794784546, 0.15346509218215942, 0.2555851340293884], "policy_updates": 34350, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5632.108465853, "contact_bce": 0.3255477547645569, "contact_force_loss": 0.033507052809000015, "terrain_level_mean": 3.143310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34460, "total_transitions": 141148160, "num_steps_per_env": 1, "wm_loss": 0.44603192806243896, "actor_loss": -8.725753784179688, "critic_loss": 0.02376590669155121, "reward": 0.0712742879986763, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2410346418619156, 0.1535663902759552, 0.25714439153671265], "policy_updates": 34360, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5635.6260361019995, "contact_bce": 0.318013459444046, "contact_force_loss": 0.03290078043937683, "terrain_level_mean": 3.143310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34470, "total_transitions": 141189120, "num_steps_per_env": 1, "wm_loss": 0.4398493468761444, "actor_loss": -8.735071182250977, "critic_loss": 0.03011409379541874, "reward": 0.07105173915624619, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24360665678977966, 0.15574677288532257, 0.2561511993408203], "policy_updates": 34370, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5639.144524636, "contact_bce": 0.3153613805770874, "contact_force_loss": 0.03204035013914108, "terrain_level_mean": 3.1435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34480, "total_transitions": 141230080, "num_steps_per_env": 1, "wm_loss": 0.431070476770401, "actor_loss": -8.819454193115234, "critic_loss": 0.021949170157313347, "reward": 0.07134732604026794, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24295848608016968, 0.15762333571910858, 0.25592079758644104], "policy_updates": 34380, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5642.642766151, "contact_bce": 0.32150402665138245, "contact_force_loss": 0.03182198107242584, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34490, "total_transitions": 141271040, "num_steps_per_env": 1, "wm_loss": 0.4282817542552948, "actor_loss": -8.762052536010742, "critic_loss": 0.02482251077890396, "reward": 0.0711645856499672, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24459756910800934, 0.15748858451843262, 0.25640782713890076], "policy_updates": 34390, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5646.13638732, "contact_bce": 0.31708312034606934, "contact_force_loss": 0.03207476809620857, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34500, "total_transitions": 141312000, "num_steps_per_env": 1, "wm_loss": 0.4395657777786255, "actor_loss": -8.781436920166016, "critic_loss": 0.030613631010055542, "reward": 0.07075848430395126, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24768556654453278, 0.15718171000480652, 0.25239208340644836], "policy_updates": 34400, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5649.634163166999, "contact_bce": 0.31623634696006775, "contact_force_loss": 0.03243543580174446, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34510, "total_transitions": 141352960, "num_steps_per_env": 1, "wm_loss": 0.44085928797721863, "actor_loss": -8.786953926086426, "critic_loss": 0.020898235961794853, "reward": 0.07064139097929001, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2502746284008026, 0.15735533833503723, 0.2565799951553345], "policy_updates": 34410, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5653.168574061, "contact_bce": 0.31708863377571106, "contact_force_loss": 0.03215015307068825, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} {"step": 34520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34520, "total_transitions": 141393920, "num_steps_per_env": 1, "wm_loss": 0.4174211919307709, "actor_loss": -8.805915832519531, "critic_loss": 0.0244143046438694, "reward": 0.07074201852083206, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2452901005744934, 0.15854643285274506, 0.25178879499435425], "policy_updates": 34420, "skipped_updates": 0, "invalid_env_resets": 47, "elapsed_s": 5656.682120175, "contact_bce": 0.3171667158603668, "contact_force_loss": 0.031617421656847, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9984357357025146, 0.9989240765571594, 2.9969136714935303]} RECOVERY reset 1 invalid environments; first IDs=[2109] {"step": 34530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34530, "total_transitions": 141434880, "num_steps_per_env": 1, "wm_loss": 0.43092799186706543, "actor_loss": -8.824026107788086, "critic_loss": 0.023577868938446045, "reward": 0.07061998546123505, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24302954971790314, 0.15969963371753693, 0.25497305393218994], "policy_updates": 34430, "skipped_updates": 0, "invalid_env_resets": 48, "elapsed_s": 5660.471183844999, "contact_bce": 0.31472674012184143, "contact_force_loss": 0.032555703073740005, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9990837574005127, 0.9989240765571594, 2.993821620941162]} RECOVERY reset 1 invalid environments; first IDs=[2148] {"step": 34540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34540, "total_transitions": 141475840, "num_steps_per_env": 1, "wm_loss": 0.4134044051170349, "actor_loss": -8.782007217407227, "critic_loss": 0.015897801145911217, "reward": 0.07050176709890366, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24318186938762665, 0.1610359102487564, 0.2530069351196289], "policy_updates": 34440, "skipped_updates": 0, "invalid_env_resets": 49, "elapsed_s": 5663.9969922949995, "contact_bce": 0.31835460662841797, "contact_force_loss": 0.0327490009367466, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9990837574005127, 0.9989240765571594, 2.993821620941162]} {"step": 34550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34550, "total_transitions": 141516800, "num_steps_per_env": 1, "wm_loss": 0.4532676339149475, "actor_loss": -8.7449951171875, "critic_loss": 0.02297988533973694, "reward": 0.07083452492952347, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24145475029945374, 0.16011042892932892, 0.2540832757949829], "policy_updates": 34450, "skipped_updates": 0, "invalid_env_resets": 49, "elapsed_s": 5667.513334763, "contact_bce": 0.3180912137031555, "contact_force_loss": 0.03302919119596481, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.993821620941162]} {"step": 34560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34560, "total_transitions": 141557760, "num_steps_per_env": 1, "wm_loss": 0.4367985725402832, "actor_loss": -8.832262992858887, "critic_loss": 0.02054721675813198, "reward": 0.07107336074113846, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24105875194072723, 0.15645158290863037, 0.25762850046157837], "policy_updates": 34460, "skipped_updates": 0, "invalid_env_resets": 49, "elapsed_s": 5671.028206096, "contact_bce": 0.3168804943561554, "contact_force_loss": 0.03232402727007866, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329833984375, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.993821620941162]} {"step": 34570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34570, "total_transitions": 141598720, "num_steps_per_env": 1, "wm_loss": 0.45786523818969727, "actor_loss": -8.80810260772705, "critic_loss": 0.021515363827347755, "reward": 0.07129782438278198, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24103733897209167, 0.1542729288339615, 0.2530568838119507], "policy_updates": 34470, "skipped_updates": 0, "invalid_env_resets": 49, "elapsed_s": 5674.5389273969995, "contact_bce": 0.31917449831962585, "contact_force_loss": 0.0320749431848526, "terrain_level_mean": 3.146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329833984375, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.993821620941162]} {"step": 34580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34580, "total_transitions": 141639680, "num_steps_per_env": 1, "wm_loss": 0.43600553274154663, "actor_loss": -8.799747467041016, "critic_loss": 0.028209758922457695, "reward": 0.07102799415588379, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24588249623775482, 0.15580683946609497, 0.25213220715522766], "policy_updates": 34480, "skipped_updates": 0, "invalid_env_resets": 49, "elapsed_s": 5678.050621929, "contact_bce": 0.3193543553352356, "contact_force_loss": 0.032954923808574677, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32666015625, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34590, "total_transitions": 141680640, "num_steps_per_env": 1, "wm_loss": 0.42585548758506775, "actor_loss": -8.75949478149414, "critic_loss": 0.01639666222035885, "reward": 0.07100188732147217, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23938609659671783, 0.15395091474056244, 0.24900275468826294], "policy_updates": 34490, "skipped_updates": 0, "invalid_env_resets": 49, "elapsed_s": 5681.564164246, "contact_bce": 0.31443920731544495, "contact_force_loss": 0.032601214945316315, "terrain_level_mean": 3.14501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.325439453125, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34600, "total_transitions": 141721600, "num_steps_per_env": 1, "wm_loss": 0.45700058341026306, "actor_loss": -8.798908233642578, "critic_loss": 0.024071043357253075, "reward": 0.07135334610939026, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2344246506690979, 0.14993226528167725, 0.24832604825496674], "policy_updates": 34500, "skipped_updates": 0, "invalid_env_resets": 49, "elapsed_s": 5685.073965676999, "contact_bce": 0.31981897354125977, "contact_force_loss": 0.03261488303542137, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3251953125, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} RECOVERY reset 1 invalid environments; first IDs=[2212] {"step": 34610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34610, "total_transitions": 141762560, "num_steps_per_env": 1, "wm_loss": 0.4011000692844391, "actor_loss": -8.746996879577637, "critic_loss": 0.018691908568143845, "reward": 0.07131665199995041, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23342929780483246, 0.15087495744228363, 0.251508504152298], "policy_updates": 34510, "skipped_updates": 0, "invalid_env_resets": 50, "elapsed_s": 5688.607925636, "contact_bce": 0.3136521279811859, "contact_force_loss": 0.03139539808034897, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3251953125, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34620, "total_transitions": 141803520, "num_steps_per_env": 1, "wm_loss": 0.43720534443855286, "actor_loss": -8.800006866455078, "critic_loss": 0.0214630588889122, "reward": 0.0718921422958374, "falls": 4, "interval_steps": 10, "velocity_mae": [0.22999629378318787, 0.151882603764534, 0.251957505941391], "policy_updates": 34520, "skipped_updates": 0, "invalid_env_resets": 50, "elapsed_s": 5692.127526296, "contact_bce": 0.3166908919811249, "contact_force_loss": 0.032517313957214355, "terrain_level_mean": 3.14501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.323974609375, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34630, "total_transitions": 141844480, "num_steps_per_env": 1, "wm_loss": 0.44789379835128784, "actor_loss": -8.801551818847656, "critic_loss": 0.028895659372210503, "reward": 0.07175671309232712, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23517662286758423, 0.14980670809745789, 0.25049588084220886], "policy_updates": 34530, "skipped_updates": 0, "invalid_env_resets": 50, "elapsed_s": 5695.63053829, "contact_bce": 0.3206685185432434, "contact_force_loss": 0.031941935420036316, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.323486328125, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} RECOVERY reset 1 invalid environments; first IDs=[1023] {"step": 34640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34640, "total_transitions": 141885440, "num_steps_per_env": 1, "wm_loss": 0.44558456540107727, "actor_loss": -8.79464054107666, "critic_loss": 0.022076860070228577, "reward": 0.07116346806287766, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23820248246192932, 0.15127766132354736, 0.2523552179336548], "policy_updates": 34540, "skipped_updates": 0, "invalid_env_resets": 51, "elapsed_s": 5699.152977013, "contact_bce": 0.3168463706970215, "contact_force_loss": 0.03208174929022789, "terrain_level_mean": 3.14404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32275390625, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34650, "total_transitions": 141926400, "num_steps_per_env": 1, "wm_loss": 0.4607870876789093, "actor_loss": -8.813725471496582, "critic_loss": 0.02197168581187725, "reward": 0.07089417427778244, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24209953844547272, 0.15528380870819092, 0.2528976798057556], "policy_updates": 34550, "skipped_updates": 0, "invalid_env_resets": 51, "elapsed_s": 5702.664344078999, "contact_bce": 0.31916484236717224, "contact_force_loss": 0.0320902094244957, "terrain_level_mean": 3.14404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.322509765625, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34660, "total_transitions": 141967360, "num_steps_per_env": 1, "wm_loss": 0.42572930455207825, "actor_loss": -8.817368507385254, "critic_loss": 0.023737674579024315, "reward": 0.07098805159330368, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23736152052879333, 0.152948796749115, 0.2546795606613159], "policy_updates": 34560, "skipped_updates": 0, "invalid_env_resets": 51, "elapsed_s": 5706.180878223, "contact_bce": 0.3179585933685303, "contact_force_loss": 0.03194377198815346, "terrain_level_mean": 3.143798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32080078125, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34670, "total_transitions": 142008320, "num_steps_per_env": 1, "wm_loss": 0.4651765823364258, "actor_loss": -8.761622428894043, "critic_loss": 0.026454513892531395, "reward": 0.07078468054533005, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2365942746400833, 0.15531565248966217, 0.2552984952926636], "policy_updates": 34570, "skipped_updates": 0, "invalid_env_resets": 51, "elapsed_s": 5709.703045847999, "contact_bce": 0.3247167468070984, "contact_force_loss": 0.031844597309827805, "terrain_level_mean": 3.1435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.322509765625, "command_abs_max": [1.9990837574005127, 0.9989972114562988, 2.997299909591675]} {"step": 34680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34680, "total_transitions": 142049280, "num_steps_per_env": 1, "wm_loss": 0.41702964901924133, "actor_loss": -8.812789916992188, "critic_loss": 0.021648278459906578, "reward": 0.07040125131607056, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24117989838123322, 0.15836916863918304, 0.2513183355331421], "policy_updates": 34580, "skipped_updates": 0, "invalid_env_resets": 51, "elapsed_s": 5713.204940926, "contact_bce": 0.3169058561325073, "contact_force_loss": 0.03126524016261101, "terrain_level_mean": 3.143310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.322509765625, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} {"step": 34690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34690, "total_transitions": 142090240, "num_steps_per_env": 1, "wm_loss": 0.45324641466140747, "actor_loss": -8.792060852050781, "critic_loss": 0.022758526727557182, "reward": 0.0702596977353096, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24063365161418915, 0.15781725943088531, 0.25599873065948486], "policy_updates": 34590, "skipped_updates": 0, "invalid_env_resets": 51, "elapsed_s": 5716.701255935, "contact_bce": 0.31705769896507263, "contact_force_loss": 0.03213626146316528, "terrain_level_mean": 3.1435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.324462890625, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} {"step": 34700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34700, "total_transitions": 142131200, "num_steps_per_env": 1, "wm_loss": 0.4254719316959381, "actor_loss": -8.792356491088867, "critic_loss": 0.022900624200701714, "reward": 0.07118476182222366, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23546038568019867, 0.15651315450668335, 0.25312572717666626], "policy_updates": 34600, "skipped_updates": 0, "invalid_env_resets": 51, "elapsed_s": 5720.206496168, "contact_bce": 0.31235775351524353, "contact_force_loss": 0.031749870628118515, "terrain_level_mean": 3.143310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328125, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} RECOVERY reset 1 invalid environments; first IDs=[751] {"step": 34710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34710, "total_transitions": 142172160, "num_steps_per_env": 1, "wm_loss": 0.43264779448509216, "actor_loss": -8.799424171447754, "critic_loss": 0.026784345507621765, "reward": 0.07125817239284515, "falls": 10, "interval_steps": 10, "velocity_mae": [0.23644521832466125, 0.15527896583080292, 0.25111812353134155], "policy_updates": 34610, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5723.724589418, "contact_bce": 0.3142085075378418, "contact_force_loss": 0.03166637197136879, "terrain_level_mean": 3.140869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327392578125, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} {"step": 34720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34720, "total_transitions": 142213120, "num_steps_per_env": 1, "wm_loss": 0.42324069142341614, "actor_loss": -8.796079635620117, "critic_loss": 0.02251669391989708, "reward": 0.07131212949752808, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23438332974910736, 0.1548680067062378, 0.2520824074745178], "policy_updates": 34620, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5727.238168215, "contact_bce": 0.31972914934158325, "contact_force_loss": 0.032368432730436325, "terrain_level_mean": 3.140869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326416015625, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} {"step": 34730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34730, "total_transitions": 142254080, "num_steps_per_env": 1, "wm_loss": 0.4474668502807617, "actor_loss": -8.756621360778809, "critic_loss": 0.024085888639092445, "reward": 0.07082951813936234, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23553667962551117, 0.15792416036128998, 0.25617456436157227], "policy_updates": 34630, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5730.745048487, "contact_bce": 0.31855079531669617, "contact_force_loss": 0.032384440302848816, "terrain_level_mean": 3.14013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326171875, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} {"step": 34740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34740, "total_transitions": 142295040, "num_steps_per_env": 1, "wm_loss": 0.4370748996734619, "actor_loss": -8.805190086364746, "critic_loss": 0.025116706266999245, "reward": 0.07139281928539276, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2381094992160797, 0.15670327842235565, 0.2505561411380768], "policy_updates": 34640, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5734.263188753, "contact_bce": 0.31651440262794495, "contact_force_loss": 0.03135974705219269, "terrain_level_mean": 3.140380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32666015625, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} {"step": 34750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34750, "total_transitions": 142336000, "num_steps_per_env": 1, "wm_loss": 0.4310592710971832, "actor_loss": -8.743692398071289, "critic_loss": 0.029633203521370888, "reward": 0.07115691900253296, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24469152092933655, 0.15259966254234314, 0.25245487689971924], "policy_updates": 34650, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5737.78382951, "contact_bce": 0.3162717819213867, "contact_force_loss": 0.032312795519828796, "terrain_level_mean": 3.140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3310546875, "command_abs_max": [1.9990837574005127, 0.9999018907546997, 2.997299909591675]} {"step": 34760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34760, "total_transitions": 142376960, "num_steps_per_env": 1, "wm_loss": 0.43970516324043274, "actor_loss": -8.721038818359375, "critic_loss": 0.02687698043882847, "reward": 0.0707068145275116, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24751625955104828, 0.15202169120311737, 0.2534514367580414], "policy_updates": 34660, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5741.304265952999, "contact_bce": 0.31355151534080505, "contact_force_loss": 0.03166026622056961, "terrain_level_mean": 3.140869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3291015625, "command_abs_max": [1.9981458187103271, 0.9999018907546997, 2.997299909591675]} {"step": 34770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34770, "total_transitions": 142417920, "num_steps_per_env": 1, "wm_loss": 0.4217950999736786, "actor_loss": -8.781044006347656, "critic_loss": 0.026545299217104912, "reward": 0.07122734934091568, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24084316194057465, 0.1525656133890152, 0.2498500943183899], "policy_updates": 34670, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5744.821670601999, "contact_bce": 0.30897408723831177, "contact_force_loss": 0.031121784821152687, "terrain_level_mean": 3.142822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9981458187103271, 0.9999018907546997, 2.997299909591675]} {"step": 34780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34780, "total_transitions": 142458880, "num_steps_per_env": 1, "wm_loss": 0.42664480209350586, "actor_loss": -8.765499114990234, "critic_loss": 0.028412282466888428, "reward": 0.07101764529943466, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2366941273212433, 0.1565418392419815, 0.2492179274559021], "policy_updates": 34680, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5748.340836429999, "contact_bce": 0.3161877989768982, "contact_force_loss": 0.031062453985214233, "terrain_level_mean": 3.142822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326904296875, "command_abs_max": [1.9981458187103271, 0.9999018907546997, 2.997299909591675]} {"step": 34790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34790, "total_transitions": 142499840, "num_steps_per_env": 1, "wm_loss": 0.4347831904888153, "actor_loss": -8.791255950927734, "critic_loss": 0.02885769121348858, "reward": 0.07140445709228516, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23699776828289032, 0.15568988025188446, 0.24654200673103333], "policy_updates": 34690, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5751.867898359999, "contact_bce": 0.31367018818855286, "contact_force_loss": 0.03197377175092697, "terrain_level_mean": 3.1435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327392578125, "command_abs_max": [1.9981458187103271, 0.9999018907546997, 2.997299909591675]} {"step": 34800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34800, "total_transitions": 142540800, "num_steps_per_env": 1, "wm_loss": 0.4104875922203064, "actor_loss": -8.770244598388672, "critic_loss": 0.023088764399290085, "reward": 0.0709574744105339, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23948878049850464, 0.15617166459560394, 0.24886848032474518], "policy_updates": 34700, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5755.38090262, "contact_bce": 0.3172643482685089, "contact_force_loss": 0.03202366456389427, "terrain_level_mean": 3.14501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32666015625, "command_abs_max": [1.9981458187103271, 0.9992895126342773, 2.997299909591675]} {"step": 34810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34810, "total_transitions": 142581760, "num_steps_per_env": 1, "wm_loss": 0.41291746497154236, "actor_loss": -8.744050979614258, "critic_loss": 0.02672608010470867, "reward": 0.07052186131477356, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2446625977754593, 0.15670445561408997, 0.25114721059799194], "policy_updates": 34710, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5758.890121095, "contact_bce": 0.3125486373901367, "contact_force_loss": 0.031077727675437927, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32763671875, "command_abs_max": [1.9981458187103271, 0.9992895126342773, 2.991151809692383]} {"step": 34820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34820, "total_transitions": 142622720, "num_steps_per_env": 1, "wm_loss": 0.42526745796203613, "actor_loss": -8.731998443603516, "critic_loss": 0.028371745720505714, "reward": 0.07039755582809448, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2443253993988037, 0.158320352435112, 0.25595763325691223], "policy_updates": 34720, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5762.397683040999, "contact_bce": 0.31510600447654724, "contact_force_loss": 0.03213586285710335, "terrain_level_mean": 3.14501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328369140625, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34830, "total_transitions": 142663680, "num_steps_per_env": 1, "wm_loss": 0.4607280194759369, "actor_loss": -8.736000061035156, "critic_loss": 0.023334553465247154, "reward": 0.07098973542451859, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24255499243736267, 0.15673305094242096, 0.252818763256073], "policy_updates": 34730, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5765.9090795229995, "contact_bce": 0.3209131360054016, "contact_force_loss": 0.032804667949676514, "terrain_level_mean": 3.14501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3271484375, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34840, "total_transitions": 142704640, "num_steps_per_env": 1, "wm_loss": 0.4619923233985901, "actor_loss": -8.810416221618652, "critic_loss": 0.02108270488679409, "reward": 0.07130613178014755, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23834924399852753, 0.1553671658039093, 0.24874615669250488], "policy_updates": 34740, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5769.425818404, "contact_bce": 0.31707674264907837, "contact_force_loss": 0.031932197511196136, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32666015625, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34850, "total_transitions": 142745600, "num_steps_per_env": 1, "wm_loss": 0.4359680116176605, "actor_loss": -8.851335525512695, "critic_loss": 0.017645901069045067, "reward": 0.07147859781980515, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23592542111873627, 0.15785633027553558, 0.25004813075065613], "policy_updates": 34750, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5772.9482671119995, "contact_bce": 0.3178703188896179, "contact_force_loss": 0.032121337950229645, "terrain_level_mean": 3.146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326416015625, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34860, "total_transitions": 142786560, "num_steps_per_env": 1, "wm_loss": 0.46039703488349915, "actor_loss": -8.784577369689941, "critic_loss": 0.02365565113723278, "reward": 0.07101644575595856, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23871451616287231, 0.1583837866783142, 0.25503239035606384], "policy_updates": 34760, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5776.472347117, "contact_bce": 0.31409749388694763, "contact_force_loss": 0.03182350471615791, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327392578125, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34870, "total_transitions": 142827520, "num_steps_per_env": 1, "wm_loss": 0.43639838695526123, "actor_loss": -8.811774253845215, "critic_loss": 0.026530742645263672, "reward": 0.0709250420331955, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24078653752803802, 0.15470412373542786, 0.25653156638145447], "policy_updates": 34770, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5779.995885650999, "contact_bce": 0.3156074285507202, "contact_force_loss": 0.032266467809677124, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3251953125, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34880, "total_transitions": 142868480, "num_steps_per_env": 1, "wm_loss": 0.4309665560722351, "actor_loss": -8.865777015686035, "critic_loss": 0.017052892595529556, "reward": 0.07004187256097794, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24654528498649597, 0.15634477138519287, 0.2574708163738251], "policy_updates": 34780, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5783.5125610919995, "contact_bce": 0.31475725769996643, "contact_force_loss": 0.032897524535655975, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32470703125, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34890, "total_transitions": 142909440, "num_steps_per_env": 1, "wm_loss": 0.4128319323062897, "actor_loss": -8.798318862915039, "critic_loss": 0.032459329813718796, "reward": 0.07050400972366333, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24786412715911865, 0.15429988503456116, 0.25550737977027893], "policy_updates": 34790, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5787.017917724999, "contact_bce": 0.3083615303039551, "contact_force_loss": 0.030911102890968323, "terrain_level_mean": 3.146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.323486328125, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34900, "total_transitions": 142950400, "num_steps_per_env": 1, "wm_loss": 0.42185625433921814, "actor_loss": -8.811973571777344, "critic_loss": 0.021606726571917534, "reward": 0.07076206058263779, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24647240340709686, 0.1569644957780838, 0.25460079312324524], "policy_updates": 34800, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5790.546313389, "contact_bce": 0.31412792205810547, "contact_force_loss": 0.03214491903781891, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32421875, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34910, "total_transitions": 142991360, "num_steps_per_env": 1, "wm_loss": 0.43560516834259033, "actor_loss": -8.79660415649414, "critic_loss": 0.026399046182632446, "reward": 0.07016600668430328, "falls": 6, "interval_steps": 10, "velocity_mae": [0.249550461769104, 0.15634538233280182, 0.25120383501052856], "policy_updates": 34810, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5794.0670099339995, "contact_bce": 0.3151649832725525, "contact_force_loss": 0.03220169618725777, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.321533203125, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34920, "total_transitions": 143032320, "num_steps_per_env": 1, "wm_loss": 0.45565366744995117, "actor_loss": -8.817392349243164, "critic_loss": 0.030530599877238274, "reward": 0.07046829909086227, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2511109411716461, 0.1556922048330307, 0.2486339807510376], "policy_updates": 34820, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5797.574468002, "contact_bce": 0.3179439902305603, "contact_force_loss": 0.03255768120288849, "terrain_level_mean": 3.146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326904296875, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34930, "total_transitions": 143073280, "num_steps_per_env": 1, "wm_loss": 0.4031612277030945, "actor_loss": -8.770915985107422, "critic_loss": 0.02392859011888504, "reward": 0.07108656316995621, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24722722172737122, 0.1559608280658722, 0.25228357315063477], "policy_updates": 34830, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5801.086450004, "contact_bce": 0.31035780906677246, "contact_force_loss": 0.031514156609773636, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327392578125, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34940, "total_transitions": 143114240, "num_steps_per_env": 1, "wm_loss": 0.41356268525123596, "actor_loss": -8.768485069274902, "critic_loss": 0.025050848722457886, "reward": 0.07082238048315048, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24730940163135529, 0.15588480234146118, 0.25401219725608826], "policy_updates": 34840, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5804.611283644, "contact_bce": 0.3132230341434479, "contact_force_loss": 0.0310695581138134, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328369140625, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34950, "total_transitions": 143155200, "num_steps_per_env": 1, "wm_loss": 0.4262406826019287, "actor_loss": -8.773355484008789, "critic_loss": 0.021702373400330544, "reward": 0.07108379900455475, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2456262707710266, 0.15434490144252777, 0.25124120712280273], "policy_updates": 34850, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5808.126207943, "contact_bce": 0.31019431352615356, "contact_force_loss": 0.03123052604496479, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330810546875, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34960, "total_transitions": 143196160, "num_steps_per_env": 1, "wm_loss": 0.4076930582523346, "actor_loss": -8.768753051757812, "critic_loss": 0.028416797518730164, "reward": 0.07076874375343323, "falls": 6, "interval_steps": 10, "velocity_mae": [0.246378555893898, 0.15413907170295715, 0.25468388199806213], "policy_updates": 34860, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5811.643534639, "contact_bce": 0.3142864406108856, "contact_force_loss": 0.03116012178361416, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34970, "total_transitions": 143237120, "num_steps_per_env": 1, "wm_loss": 0.46657806634902954, "actor_loss": -8.771038055419922, "critic_loss": 0.02300024963915348, "reward": 0.0711045190691948, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24170269072055817, 0.15566034615039825, 0.2543080747127533], "policy_updates": 34870, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5815.1707081469995, "contact_bce": 0.31923428177833557, "contact_force_loss": 0.032552994787693024, "terrain_level_mean": 3.1474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} {"step": 34980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34980, "total_transitions": 143278080, "num_steps_per_env": 1, "wm_loss": 0.43916985392570496, "actor_loss": -8.78232192993164, "critic_loss": 0.019856927916407585, "reward": 0.0710170641541481, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24148812890052795, 0.15809279680252075, 0.2518247067928314], "policy_updates": 34880, "skipped_updates": 0, "invalid_env_resets": 52, "elapsed_s": 5818.693828429, "contact_bce": 0.31472036242485046, "contact_force_loss": 0.031503722071647644, "terrain_level_mean": 3.1474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.991151809692383]} RECOVERY reset 1 invalid environments; first IDs=[1293] {"step": 34990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 34990, "total_transitions": 143319040, "num_steps_per_env": 1, "wm_loss": 0.4399408996105194, "actor_loss": -8.809123992919922, "critic_loss": 0.023167939856648445, "reward": 0.07104267179965973, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24571876227855682, 0.15504314005374908, 0.25484827160835266], "policy_updates": 34890, "skipped_updates": 0, "invalid_env_resets": 53, "elapsed_s": 5822.239529666999, "contact_bce": 0.3198324739933014, "contact_force_loss": 0.03241751715540886, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9991340637207031, 0.9992895126342773, 2.9926695823669434]} {"step": 35000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35000, "total_transitions": 143360000, "num_steps_per_env": 1, "wm_loss": 0.4209301173686981, "actor_loss": -8.753374099731445, "critic_loss": 0.029846876859664917, "reward": 0.0709177702665329, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24842573702335358, 0.1571027934551239, 0.2538245618343353], "policy_updates": 34900, "skipped_updates": 0, "invalid_env_resets": 53, "elapsed_s": 5825.7599504849995, "contact_bce": 0.3151870369911194, "contact_force_loss": 0.03169526532292366, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9991340637207031, 0.9988827109336853, 2.9926695823669434]} {"step": 35010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35010, "total_transitions": 143400960, "num_steps_per_env": 1, "wm_loss": 0.42140570282936096, "actor_loss": -8.827038764953613, "critic_loss": 0.035026587545871735, "reward": 0.07111284136772156, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24645553529262543, 0.15895217657089233, 0.2565097212791443], "policy_updates": 34910, "skipped_updates": 0, "invalid_env_resets": 53, "elapsed_s": 5829.295753234, "contact_bce": 0.31289222836494446, "contact_force_loss": 0.03177430480718613, "terrain_level_mean": 3.1484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9991340637207031, 0.9988827109336853, 2.9926695823669434]} {"step": 35020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35020, "total_transitions": 143441920, "num_steps_per_env": 1, "wm_loss": 0.42281103134155273, "actor_loss": -8.769763946533203, "critic_loss": 0.02432822249829769, "reward": 0.07118123024702072, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2429780513048172, 0.16135399043560028, 0.25449541211128235], "policy_updates": 34920, "skipped_updates": 0, "invalid_env_resets": 53, "elapsed_s": 5832.795879888, "contact_bce": 0.3174395263195038, "contact_force_loss": 0.032181307673454285, "terrain_level_mean": 3.1484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9991340637207031, 0.9988827109336853, 2.9926695823669434]} {"step": 35030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35030, "total_transitions": 143482880, "num_steps_per_env": 1, "wm_loss": 0.42416998744010925, "actor_loss": -8.787089347839355, "critic_loss": 0.03435736894607544, "reward": 0.07122088968753815, "falls": 12, "interval_steps": 10, "velocity_mae": [0.2401682585477829, 0.16019031405448914, 0.25389233231544495], "policy_updates": 34930, "skipped_updates": 0, "invalid_env_resets": 53, "elapsed_s": 5836.572027405, "contact_bce": 0.3131212592124939, "contact_force_loss": 0.031007234007120132, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9926695823669434]} {"step": 35040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35040, "total_transitions": 143523840, "num_steps_per_env": 1, "wm_loss": 0.43041664361953735, "actor_loss": -8.763126373291016, "critic_loss": 0.02822534739971161, "reward": 0.07128893584012985, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2385670244693756, 0.15727698802947998, 0.2534380257129669], "policy_updates": 34940, "skipped_updates": 0, "invalid_env_resets": 53, "elapsed_s": 5840.102471644999, "contact_bce": 0.31829169392585754, "contact_force_loss": 0.03204584866762161, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} RECOVERY reset 1 invalid environments; first IDs=[838] {"step": 35050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35050, "total_transitions": 143564800, "num_steps_per_env": 1, "wm_loss": 0.4530368149280548, "actor_loss": -8.790718078613281, "critic_loss": 0.028191452845931053, "reward": 0.07145025581121445, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23819050192832947, 0.15638865530490875, 0.2560276389122009], "policy_updates": 34950, "skipped_updates": 0, "invalid_env_resets": 54, "elapsed_s": 5843.640876349999, "contact_bce": 0.3174622356891632, "contact_force_loss": 0.032193005084991455, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35060, "total_transitions": 143605760, "num_steps_per_env": 1, "wm_loss": 0.4057184159755707, "actor_loss": -8.776805877685547, "critic_loss": 0.029753481969237328, "reward": 0.07148726284503937, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2442702054977417, 0.15394963324069977, 0.25601884722709656], "policy_updates": 34960, "skipped_updates": 0, "invalid_env_resets": 54, "elapsed_s": 5847.163657864, "contact_bce": 0.31429919600486755, "contact_force_loss": 0.031614888459444046, "terrain_level_mean": 3.148193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35070, "total_transitions": 143646720, "num_steps_per_env": 1, "wm_loss": 0.43856558203697205, "actor_loss": -8.725232124328613, "critic_loss": 0.031234610825777054, "reward": 0.07143349200487137, "falls": 11, "interval_steps": 10, "velocity_mae": [0.24468611180782318, 0.15603840351104736, 0.25083640217781067], "policy_updates": 34970, "skipped_updates": 0, "invalid_env_resets": 54, "elapsed_s": 5850.684987338999, "contact_bce": 0.310376912355423, "contact_force_loss": 0.03168768435716629, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35080, "total_transitions": 143687680, "num_steps_per_env": 1, "wm_loss": 0.43963587284088135, "actor_loss": -8.813899993896484, "critic_loss": 0.022453442215919495, "reward": 0.07175364345312119, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2432897388935089, 0.15598197281360626, 0.24693360924720764], "policy_updates": 34980, "skipped_updates": 0, "invalid_env_resets": 54, "elapsed_s": 5854.20561862, "contact_bce": 0.3177333474159241, "contact_force_loss": 0.031746506690979004, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} RECOVERY reset 1 invalid environments; first IDs=[1004] {"step": 35090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35090, "total_transitions": 143728640, "num_steps_per_env": 1, "wm_loss": 0.41724899411201477, "actor_loss": -8.766433715820312, "critic_loss": 0.03452206030488014, "reward": 0.0714230164885521, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23999661207199097, 0.15833525359630585, 0.2521023452281952], "policy_updates": 34990, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5857.729718901, "contact_bce": 0.31214696168899536, "contact_force_loss": 0.03157445043325424, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35100, "total_transitions": 143769600, "num_steps_per_env": 1, "wm_loss": 0.44603750109672546, "actor_loss": -8.765958786010742, "critic_loss": 0.027723688632249832, "reward": 0.0711018368601799, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24348482489585876, 0.15824341773986816, 0.25227823853492737], "policy_updates": 35000, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5861.2337149019995, "contact_bce": 0.3169389069080353, "contact_force_loss": 0.0324442982673645, "terrain_level_mean": 3.1474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_035100.mp4 {"step": 35110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35110, "total_transitions": 143810560, "num_steps_per_env": 1, "wm_loss": 0.453825443983078, "actor_loss": -8.779258728027344, "critic_loss": 0.029327070340514183, "reward": 0.0709124431014061, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24799005687236786, 0.15700998902320862, 0.2535083293914795], "policy_updates": 35010, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5870.576720532999, "contact_bce": 0.3189007341861725, "contact_force_loss": 0.032153815031051636, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35120, "total_transitions": 143851520, "num_steps_per_env": 1, "wm_loss": 0.42349910736083984, "actor_loss": -8.808266639709473, "critic_loss": 0.02438543178141117, "reward": 0.07100314646959305, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24567130208015442, 0.1585560292005539, 0.25267672538757324], "policy_updates": 35020, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5874.082335806999, "contact_bce": 0.3152136206626892, "contact_force_loss": 0.03232602775096893, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35130, "total_transitions": 143892480, "num_steps_per_env": 1, "wm_loss": 0.43429121375083923, "actor_loss": -8.693954467773438, "critic_loss": 0.0357038788497448, "reward": 0.07097586244344711, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24566949903964996, 0.15883950889110565, 0.2552836537361145], "policy_updates": 35030, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5877.584165087999, "contact_bce": 0.31724849343299866, "contact_force_loss": 0.03172517940402031, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35140, "total_transitions": 143933440, "num_steps_per_env": 1, "wm_loss": 0.4468405842781067, "actor_loss": -8.784542083740234, "critic_loss": 0.02680286578834057, "reward": 0.07119791954755783, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24695758521556854, 0.1577194482088089, 0.2549320161342621], "policy_updates": 35040, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5881.093599105, "contact_bce": 0.3113120198249817, "contact_force_loss": 0.032047152519226074, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355712890625, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9955201148986816]} {"step": 35150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35150, "total_transitions": 143974400, "num_steps_per_env": 1, "wm_loss": 0.4423944354057312, "actor_loss": -8.767513275146484, "critic_loss": 0.024010585620999336, "reward": 0.07165787369012833, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24217304587364197, 0.15779763460159302, 0.24837049841880798], "policy_updates": 35050, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5884.610520046, "contact_bce": 0.3116118609905243, "contact_force_loss": 0.032099612057209015, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9958667755126953]} {"step": 35160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35160, "total_transitions": 144015360, "num_steps_per_env": 1, "wm_loss": 0.43918904662132263, "actor_loss": -8.733054161071777, "critic_loss": 0.030162686482071877, "reward": 0.07199501246213913, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23574168980121613, 0.15608611702919006, 0.2512599527835846], "policy_updates": 35060, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5888.124468897, "contact_bce": 0.309800386428833, "contact_force_loss": 0.03154764696955681, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.9985475540161133, 0.9988827109336853, 2.9958667755126953]} {"step": 35170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35170, "total_transitions": 144056320, "num_steps_per_env": 1, "wm_loss": 0.4259406626224518, "actor_loss": -8.781241416931152, "critic_loss": 0.03647474944591522, "reward": 0.0721723735332489, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23482495546340942, 0.15633568167686462, 0.2507070302963257], "policy_updates": 35070, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5891.6387125579995, "contact_bce": 0.3150536119937897, "contact_force_loss": 0.03244083374738693, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9985475540161133, 0.9982502460479736, 2.9958667755126953]} {"step": 35180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35180, "total_transitions": 144097280, "num_steps_per_env": 1, "wm_loss": 0.4583752453327179, "actor_loss": -8.733335494995117, "critic_loss": 0.034153830260038376, "reward": 0.07196950912475586, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24392125010490417, 0.1573377102613449, 0.24968984723091125], "policy_updates": 35080, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5895.153910495, "contact_bce": 0.3170471489429474, "contact_force_loss": 0.032979920506477356, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9985475540161133, 0.9982502460479736, 2.9974400997161865]} {"step": 35190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35190, "total_transitions": 144138240, "num_steps_per_env": 1, "wm_loss": 0.41247043013572693, "actor_loss": -8.80478572845459, "critic_loss": 0.02062772773206234, "reward": 0.07126272469758987, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24568752944469452, 0.1587066650390625, 0.2538134455680847], "policy_updates": 35090, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5898.668840136, "contact_bce": 0.31223955750465393, "contact_force_loss": 0.03157394751906395, "terrain_level_mean": 3.148193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9985475540161133, 0.9982502460479736, 2.9974400997161865]} {"step": 35200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35200, "total_transitions": 144179200, "num_steps_per_env": 1, "wm_loss": 0.4384772479534149, "actor_loss": -8.827634811401367, "critic_loss": 0.02328249253332615, "reward": 0.07100564241409302, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24563440680503845, 0.15939714014530182, 0.25373002886772156], "policy_updates": 35100, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5902.171699199999, "contact_bce": 0.3168594241142273, "contact_force_loss": 0.032498858869075775, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35888671875, "command_abs_max": [1.9967498779296875, 0.9982502460479736, 2.999603033065796]} {"step": 35210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35210, "total_transitions": 144220160, "num_steps_per_env": 1, "wm_loss": 0.4107365608215332, "actor_loss": -8.750035285949707, "critic_loss": 0.02411547489464283, "reward": 0.07118639349937439, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24801968038082123, 0.1575033962726593, 0.25498664379119873], "policy_updates": 35110, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5905.668336541999, "contact_bce": 0.3092961609363556, "contact_force_loss": 0.03246388956904411, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359375, "command_abs_max": [1.9967498779296875, 0.9982502460479736, 2.999603033065796]} {"step": 35220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35220, "total_transitions": 144261120, "num_steps_per_env": 1, "wm_loss": 0.44662192463874817, "actor_loss": -8.755525588989258, "critic_loss": 0.03135812282562256, "reward": 0.07085824757814407, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2492906153202057, 0.15591445565223694, 0.25715503096580505], "policy_updates": 35120, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5909.171323377, "contact_bce": 0.31653785705566406, "contact_force_loss": 0.03255315497517586, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999265432357788, 0.9982502460479736, 2.999603033065796]} {"step": 35230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35230, "total_transitions": 144302080, "num_steps_per_env": 1, "wm_loss": 0.4472421109676361, "actor_loss": -8.695135116577148, "critic_loss": 0.042868390679359436, "reward": 0.07117824256420135, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24854347109794617, 0.15840354561805725, 0.25374507904052734], "policy_updates": 35130, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5912.674150596, "contact_bce": 0.3187310993671417, "contact_force_loss": 0.03269922733306885, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999265432357788, 0.9982502460479736, 2.999603033065796]} {"step": 35240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35240, "total_transitions": 144343040, "num_steps_per_env": 1, "wm_loss": 0.4468018412590027, "actor_loss": -8.711190223693848, "critic_loss": 0.02687370777130127, "reward": 0.07088780403137207, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2527310848236084, 0.16139817237854004, 0.25776663422584534], "policy_updates": 35140, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5916.178652349, "contact_bce": 0.31655341386795044, "contact_force_loss": 0.032448381185531616, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.999265432357788, 0.9982502460479736, 2.999603033065796]} {"step": 35250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35250, "total_transitions": 144384000, "num_steps_per_env": 1, "wm_loss": 0.4400803744792938, "actor_loss": -8.759265899658203, "critic_loss": 0.02416054904460907, "reward": 0.07091748714447021, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2529636323451996, 0.1595383882522583, 0.25659382343292236], "policy_updates": 35150, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5919.680527875, "contact_bce": 0.3126939535140991, "contact_force_loss": 0.03168532997369766, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.999265432357788, 0.9982502460479736, 2.999603033065796]} {"step": 35260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35260, "total_transitions": 144424960, "num_steps_per_env": 1, "wm_loss": 0.4130772352218628, "actor_loss": -8.763402938842773, "critic_loss": 0.025288313627243042, "reward": 0.07096701115369797, "falls": 9, "interval_steps": 10, "velocity_mae": [0.25193411111831665, 0.1622675359249115, 0.25459155440330505], "policy_updates": 35160, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5923.1854713739995, "contact_bce": 0.3117433786392212, "contact_force_loss": 0.031644392758607864, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35270, "total_transitions": 144465920, "num_steps_per_env": 1, "wm_loss": 0.44264253973960876, "actor_loss": -8.732409477233887, "critic_loss": 0.03268023580312729, "reward": 0.0707821175456047, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2529725730419159, 0.16295067965984344, 0.2550145983695984], "policy_updates": 35170, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5926.686332106, "contact_bce": 0.31571733951568604, "contact_force_loss": 0.03206109628081322, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35280, "total_transitions": 144506880, "num_steps_per_env": 1, "wm_loss": 0.43257009983062744, "actor_loss": -8.75413990020752, "critic_loss": 0.02596038579940796, "reward": 0.0710039734840393, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24587947130203247, 0.15990066528320312, 0.25439855456352234], "policy_updates": 35180, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5930.196255532999, "contact_bce": 0.3151848018169403, "contact_force_loss": 0.033076561987400055, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35290, "total_transitions": 144547840, "num_steps_per_env": 1, "wm_loss": 0.4271177351474762, "actor_loss": -8.752803802490234, "critic_loss": 0.030271774157881737, "reward": 0.07111161947250366, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24601124227046967, 0.15877044200897217, 0.2568279802799225], "policy_updates": 35190, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5933.711842002, "contact_bce": 0.3147220313549042, "contact_force_loss": 0.03214128315448761, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35300, "total_transitions": 144588800, "num_steps_per_env": 1, "wm_loss": 0.4472222328186035, "actor_loss": -8.76668930053711, "critic_loss": 0.03500867635011673, "reward": 0.0708213672041893, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2496676743030548, 0.15993663668632507, 0.2548825442790985], "policy_updates": 35200, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5937.215510704999, "contact_bce": 0.320592999458313, "contact_force_loss": 0.03254147991538048, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35310, "total_transitions": 144629760, "num_steps_per_env": 1, "wm_loss": 0.4446272552013397, "actor_loss": -8.756282806396484, "critic_loss": 0.03031339682638645, "reward": 0.07095911353826523, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24582476913928986, 0.15988346934318542, 0.25357648730278015], "policy_updates": 35210, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5940.73595915, "contact_bce": 0.32249173521995544, "contact_force_loss": 0.03278101235628128, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35320, "total_transitions": 144670720, "num_steps_per_env": 1, "wm_loss": 0.44212332367897034, "actor_loss": -8.712753295898438, "critic_loss": 0.02047835662961006, "reward": 0.07121257483959198, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24158774316310883, 0.1603253334760666, 0.2526721954345703], "policy_updates": 35220, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5944.2575118879995, "contact_bce": 0.3209654986858368, "contact_force_loss": 0.0326869897544384, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35330, "total_transitions": 144711680, "num_steps_per_env": 1, "wm_loss": 0.4554290473461151, "actor_loss": -8.798627853393555, "critic_loss": 0.018562540411949158, "reward": 0.07141629606485367, "falls": 11, "interval_steps": 10, "velocity_mae": [0.24118508398532867, 0.15753333270549774, 0.2508053779602051], "policy_updates": 35230, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5947.755800115, "contact_bce": 0.3118073344230652, "contact_force_loss": 0.033282823860645294, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35340, "total_transitions": 144752640, "num_steps_per_env": 1, "wm_loss": 0.4078158736228943, "actor_loss": -8.770160675048828, "critic_loss": 0.024053532630205154, "reward": 0.07129798084497452, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24591651558876038, 0.15638640522956848, 0.24946463108062744], "policy_updates": 35240, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5951.253641386, "contact_bce": 0.31525325775146484, "contact_force_loss": 0.03209765627980232, "terrain_level_mean": 3.14306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35350, "total_transitions": 144793600, "num_steps_per_env": 1, "wm_loss": 0.4532564580440521, "actor_loss": -8.755606651306152, "critic_loss": 0.02849811315536499, "reward": 0.0710383877158165, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24627454578876495, 0.155171737074852, 0.2557283043861389], "policy_updates": 35250, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5954.813970616, "contact_bce": 0.31608378887176514, "contact_force_loss": 0.03205202892422676, "terrain_level_mean": 3.143798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.999265432357788, 0.9985076189041138, 2.999603033065796]} {"step": 35360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35360, "total_transitions": 144834560, "num_steps_per_env": 1, "wm_loss": 0.43186694383621216, "actor_loss": -8.780204772949219, "critic_loss": 0.028336694464087486, "reward": 0.07092989981174469, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25002679228782654, 0.15636377036571503, 0.2607150673866272], "policy_updates": 35260, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5958.317243209, "contact_bce": 0.31801727414131165, "contact_force_loss": 0.03208126127719879, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35370, "total_transitions": 144875520, "num_steps_per_env": 1, "wm_loss": 0.43422824144363403, "actor_loss": -8.73725700378418, "critic_loss": 0.030647912994027138, "reward": 0.07103746384382248, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24828742444515228, 0.15606243908405304, 0.25643593072891235], "policy_updates": 35270, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5961.814421325999, "contact_bce": 0.3191054165363312, "contact_force_loss": 0.03276095166802406, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35380, "total_transitions": 144916480, "num_steps_per_env": 1, "wm_loss": 0.4269181787967682, "actor_loss": -8.795071601867676, "critic_loss": 0.026011202484369278, "reward": 0.07044936716556549, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2507001757621765, 0.15732763707637787, 0.25849464535713196], "policy_updates": 35280, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5965.318022775, "contact_bce": 0.3140047490596771, "contact_force_loss": 0.03258494660258293, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358642578125, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35390, "total_transitions": 144957440, "num_steps_per_env": 1, "wm_loss": 0.4377651512622833, "actor_loss": -8.737364768981934, "critic_loss": 0.025762660428881645, "reward": 0.07071232795715332, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2502235174179077, 0.15639105439186096, 0.26060792803764343], "policy_updates": 35290, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5968.826988836, "contact_bce": 0.31197673082351685, "contact_force_loss": 0.03222799673676491, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35400, "total_transitions": 144998400, "num_steps_per_env": 1, "wm_loss": 0.4502091109752655, "actor_loss": -8.724706649780273, "critic_loss": 0.03411991521716118, "reward": 0.07092007249593735, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24913887679576874, 0.15672975778579712, 0.25855833292007446], "policy_updates": 35300, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5972.339194513, "contact_bce": 0.314367413520813, "contact_force_loss": 0.03271979093551636, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35410, "total_transitions": 145039360, "num_steps_per_env": 1, "wm_loss": 0.46586987376213074, "actor_loss": -8.701163291931152, "critic_loss": 0.024171901866793633, "reward": 0.07072458416223526, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2499644011259079, 0.1581973433494568, 0.25527194142341614], "policy_updates": 35310, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5975.84326749, "contact_bce": 0.3166603744029999, "contact_force_loss": 0.03237883001565933, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35420, "total_transitions": 145080320, "num_steps_per_env": 1, "wm_loss": 0.45199280977249146, "actor_loss": -8.693219184875488, "critic_loss": 0.04228278622031212, "reward": 0.07094498723745346, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2529239058494568, 0.1582757830619812, 0.25655755400657654], "policy_updates": 35320, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5979.352444825, "contact_bce": 0.31106314063072205, "contact_force_loss": 0.032608792185783386, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35430, "total_transitions": 145121280, "num_steps_per_env": 1, "wm_loss": 0.44306841492652893, "actor_loss": -8.724966049194336, "critic_loss": 0.029134539887309074, "reward": 0.07097704708576202, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2514929175376892, 0.15850873291492462, 0.2577686607837677], "policy_updates": 35330, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5982.871263237999, "contact_bce": 0.3156624138355255, "contact_force_loss": 0.032050229609012604, "terrain_level_mean": 3.146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35440, "total_transitions": 145162240, "num_steps_per_env": 1, "wm_loss": 0.42299941182136536, "actor_loss": -8.7675142288208, "critic_loss": 0.02098430134356022, "reward": 0.07097480446100235, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25137004256248474, 0.16120290756225586, 0.2505982220172882], "policy_updates": 35340, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5986.377818207, "contact_bce": 0.3080102801322937, "contact_force_loss": 0.03173327445983887, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35450, "total_transitions": 145203200, "num_steps_per_env": 1, "wm_loss": 0.455520361661911, "actor_loss": -8.734304428100586, "critic_loss": 0.021695395931601524, "reward": 0.07070674747228622, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2532888650894165, 0.1601911336183548, 0.25280386209487915], "policy_updates": 35350, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5989.88701488, "contact_bce": 0.31864312291145325, "contact_force_loss": 0.03295944631099701, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35460, "total_transitions": 145244160, "num_steps_per_env": 1, "wm_loss": 0.4409398138523102, "actor_loss": -8.74072265625, "critic_loss": 0.023447610437870026, "reward": 0.07080359011888504, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2469944804906845, 0.1585891842842102, 0.2577429711818695], "policy_updates": 35360, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5993.396052841, "contact_bce": 0.31395789980888367, "contact_force_loss": 0.03232765570282936, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.999741792678833, 0.9985076189041138, 2.999603033065796]} {"step": 35470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35470, "total_transitions": 145285120, "num_steps_per_env": 1, "wm_loss": 0.43465280532836914, "actor_loss": -8.741697311401367, "critic_loss": 0.03067420795559883, "reward": 0.07108338922262192, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24376557767391205, 0.1584865152835846, 0.25562041997909546], "policy_updates": 35370, "skipped_updates": 0, "invalid_env_resets": 55, "elapsed_s": 5996.910993259, "contact_bce": 0.3143799901008606, "contact_force_loss": 0.032110102474689484, "terrain_level_mean": 3.14892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.999603033065796]} RECOVERY reset 1 invalid environments; first IDs=[1122] {"step": 35480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35480, "total_transitions": 145326080, "num_steps_per_env": 1, "wm_loss": 0.4460580348968506, "actor_loss": -8.711318969726562, "critic_loss": 0.03622984513640404, "reward": 0.0707385241985321, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2480037659406662, 0.16205176711082458, 0.2584998905658722], "policy_updates": 35380, "skipped_updates": 0, "invalid_env_resets": 56, "elapsed_s": 6000.444576162, "contact_bce": 0.31728580594062805, "contact_force_loss": 0.0318756066262722, "terrain_level_mean": 3.1484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.999603033065796]} {"step": 35490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35490, "total_transitions": 145367040, "num_steps_per_env": 1, "wm_loss": 0.43437647819519043, "actor_loss": -8.788541793823242, "critic_loss": 0.03071342408657074, "reward": 0.0711384266614914, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24406801164150238, 0.16136795282363892, 0.2571600079536438], "policy_updates": 35390, "skipped_updates": 0, "invalid_env_resets": 56, "elapsed_s": 6003.9636443829995, "contact_bce": 0.3115801215171814, "contact_force_loss": 0.03164103254675865, "terrain_level_mean": 3.148193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.999603033065796]} {"step": 35500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35500, "total_transitions": 145408000, "num_steps_per_env": 1, "wm_loss": 0.44920095801353455, "actor_loss": -8.72446060180664, "critic_loss": 0.031078893691301346, "reward": 0.0705779418349266, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2478443831205368, 0.15976934134960175, 0.2583797872066498], "policy_updates": 35400, "skipped_updates": 0, "invalid_env_resets": 56, "elapsed_s": 6007.484109501999, "contact_bce": 0.313526451587677, "contact_force_loss": 0.032089099287986755, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.999603033065796]} {"step": 35510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35510, "total_transitions": 145448960, "num_steps_per_env": 1, "wm_loss": 0.44198405742645264, "actor_loss": -8.739198684692383, "critic_loss": 0.02783930115401745, "reward": 0.07079456001520157, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24965454638004303, 0.15466530621051788, 0.2560420334339142], "policy_updates": 35410, "skipped_updates": 0, "invalid_env_resets": 56, "elapsed_s": 6011.028992666999, "contact_bce": 0.31307435035705566, "contact_force_loss": 0.031717728823423386, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.997452735900879]} {"step": 35520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35520, "total_transitions": 145489920, "num_steps_per_env": 1, "wm_loss": 0.4560960531234741, "actor_loss": -8.749505996704102, "critic_loss": 0.02762208692729473, "reward": 0.07108137756586075, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2474825531244278, 0.15579403936862946, 0.25257089734077454], "policy_updates": 35420, "skipped_updates": 0, "invalid_env_resets": 56, "elapsed_s": 6014.807375621, "contact_bce": 0.31338122487068176, "contact_force_loss": 0.03243013843894005, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.997452735900879]} {"step": 35530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35530, "total_transitions": 145530880, "num_steps_per_env": 1, "wm_loss": 0.4477114677429199, "actor_loss": -8.733362197875977, "critic_loss": 0.03459148108959198, "reward": 0.0707816630601883, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24958641827106476, 0.15733365714550018, 0.25734826922416687], "policy_updates": 35430, "skipped_updates": 0, "invalid_env_resets": 56, "elapsed_s": 6018.328060932, "contact_bce": 0.3118025064468384, "contact_force_loss": 0.03220619633793831, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.997452735900879]} {"step": 35540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35540, "total_transitions": 145571840, "num_steps_per_env": 1, "wm_loss": 0.4599073529243469, "actor_loss": -8.767688751220703, "critic_loss": 0.024443482980132103, "reward": 0.07113324850797653, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24976906180381775, 0.1567785143852234, 0.2559039294719696], "policy_updates": 35440, "skipped_updates": 0, "invalid_env_resets": 56, "elapsed_s": 6021.851190753, "contact_bce": 0.3126814067363739, "contact_force_loss": 0.03210919350385666, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.997452735900879]} RECOVERY reset 1 invalid environments; first IDs=[1568] {"step": 35550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35550, "total_transitions": 145612800, "num_steps_per_env": 1, "wm_loss": 0.4448089897632599, "actor_loss": -8.729072570800781, "critic_loss": 0.019459323957562447, "reward": 0.07067293673753738, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2514086663722992, 0.15871594846248627, 0.2566027045249939], "policy_updates": 35450, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6025.375963232999, "contact_bce": 0.323151171207428, "contact_force_loss": 0.03284125030040741, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.997452735900879]} {"step": 35560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35560, "total_transitions": 145653760, "num_steps_per_env": 1, "wm_loss": 0.42717379331588745, "actor_loss": -8.75071907043457, "critic_loss": 0.02569388784468174, "reward": 0.07031425088644028, "falls": 12, "interval_steps": 10, "velocity_mae": [0.2538529932498932, 0.15932874381542206, 0.2591629922389984], "policy_updates": 35460, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6028.883877251999, "contact_bce": 0.3122667670249939, "contact_force_loss": 0.03184396028518677, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9964669942855835, 0.9985076189041138, 2.997452735900879]} {"step": 35570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35570, "total_transitions": 145694720, "num_steps_per_env": 1, "wm_loss": 0.42277562618255615, "actor_loss": -8.756121635437012, "critic_loss": 0.0269462950527668, "reward": 0.07043341547250748, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25556680560112, 0.1598527580499649, 0.25678750872612], "policy_updates": 35470, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6032.390060809999, "contact_bce": 0.31330209970474243, "contact_force_loss": 0.03206900507211685, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9954891204833984, 0.9985076189041138, 2.997452735900879]} {"step": 35580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35580, "total_transitions": 145735680, "num_steps_per_env": 1, "wm_loss": 0.44789838790893555, "actor_loss": -8.715461730957031, "critic_loss": 0.026139015331864357, "reward": 0.07065461575984955, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24922004342079163, 0.1601094901561737, 0.25492534041404724], "policy_updates": 35480, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6035.893598537, "contact_bce": 0.3176553547382355, "contact_force_loss": 0.031679585576057434, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9954891204833984, 0.9985076189041138, 2.997452735900879]} {"step": 35590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35590, "total_transitions": 145776640, "num_steps_per_env": 1, "wm_loss": 0.45966607332229614, "actor_loss": -8.76297378540039, "critic_loss": 0.019169939681887627, "reward": 0.07088814675807953, "falls": 5, "interval_steps": 10, "velocity_mae": [0.249237522482872, 0.16036827862262726, 0.2562384307384491], "policy_updates": 35490, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6039.398915520999, "contact_bce": 0.321840763092041, "contact_force_loss": 0.033218443393707275, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9954891204833984, 0.9985076189041138, 2.997452735900879]} {"step": 35600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35600, "total_transitions": 145817600, "num_steps_per_env": 1, "wm_loss": 0.44072234630584717, "actor_loss": -8.735660552978516, "critic_loss": 0.03050053119659424, "reward": 0.07092278450727463, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25035059452056885, 0.15886259078979492, 0.2555910050868988], "policy_updates": 35500, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6042.9079325269995, "contact_bce": 0.31585580110549927, "contact_force_loss": 0.03249813988804817, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35610, "total_transitions": 145858560, "num_steps_per_env": 1, "wm_loss": 0.45342525839805603, "actor_loss": -8.728970527648926, "critic_loss": 0.025655070319771767, "reward": 0.07101638615131378, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24479587376117706, 0.15712691843509674, 0.25509485602378845], "policy_updates": 35510, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6046.411009363999, "contact_bce": 0.31515055894851685, "contact_force_loss": 0.033184099942445755, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35620, "total_transitions": 145899520, "num_steps_per_env": 1, "wm_loss": 0.4314478933811188, "actor_loss": -8.742142677307129, "critic_loss": 0.019968664273619652, "reward": 0.07077008485794067, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2509022057056427, 0.15848411619663239, 0.2576844096183777], "policy_updates": 35520, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6049.922128650999, "contact_bce": 0.31061989068984985, "contact_force_loss": 0.03240872547030449, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35630, "total_transitions": 145940480, "num_steps_per_env": 1, "wm_loss": 0.42863351106643677, "actor_loss": -8.75868034362793, "critic_loss": 0.03171258792281151, "reward": 0.07083950936794281, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24796712398529053, 0.15464596450328827, 0.2583617866039276], "policy_updates": 35530, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6053.427043138, "contact_bce": 0.31171223521232605, "contact_force_loss": 0.03204686567187309, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35640, "total_transitions": 145981440, "num_steps_per_env": 1, "wm_loss": 0.45462915301322937, "actor_loss": -8.769956588745117, "critic_loss": 0.026768803596496582, "reward": 0.07155144214630127, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24564456939697266, 0.15203210711479187, 0.2525528371334076], "policy_updates": 35540, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6056.922834288999, "contact_bce": 0.3134981393814087, "contact_force_loss": 0.03230158984661102, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35650, "total_transitions": 146022400, "num_steps_per_env": 1, "wm_loss": 0.43679937720298767, "actor_loss": -8.75411605834961, "critic_loss": 0.029145603999495506, "reward": 0.07184730470180511, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2463456392288208, 0.15168538689613342, 0.25217869877815247], "policy_updates": 35550, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6060.434149303, "contact_bce": 0.3114990293979645, "contact_force_loss": 0.03226252645254135, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35660, "total_transitions": 146063360, "num_steps_per_env": 1, "wm_loss": 0.43575912714004517, "actor_loss": -8.749406814575195, "critic_loss": 0.02953149937093258, "reward": 0.0712263360619545, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24653932452201843, 0.15225796401500702, 0.2553027868270874], "policy_updates": 35560, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6063.952035427, "contact_bce": 0.3209661841392517, "contact_force_loss": 0.032201800495386124, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35670, "total_transitions": 146104320, "num_steps_per_env": 1, "wm_loss": 0.4528522491455078, "actor_loss": -8.744420051574707, "critic_loss": 0.033811308443546295, "reward": 0.07071926444768906, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24806520342826843, 0.15694481134414673, 0.2584744095802307], "policy_updates": 35570, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6067.4718144769995, "contact_bce": 0.3163054287433624, "contact_force_loss": 0.03216265141963959, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35680, "total_transitions": 146145280, "num_steps_per_env": 1, "wm_loss": 0.48385608196258545, "actor_loss": -8.723609924316406, "critic_loss": 0.02198079228401184, "reward": 0.0707426592707634, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24483667314052582, 0.15712286531925201, 0.2564042806625366], "policy_updates": 35580, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6070.986953277, "contact_bce": 0.3193756639957428, "contact_force_loss": 0.03380274400115013, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.997452735900879]} {"step": 35690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35690, "total_transitions": 146186240, "num_steps_per_env": 1, "wm_loss": 0.4599319398403168, "actor_loss": -8.724430084228516, "critic_loss": 0.025657499209046364, "reward": 0.07034054398536682, "falls": 7, "interval_steps": 10, "velocity_mae": [0.245049849152565, 0.155387744307518, 0.2579309046268463], "policy_updates": 35590, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6074.497078228, "contact_bce": 0.31426241993904114, "contact_force_loss": 0.03257625177502632, "terrain_level_mean": 3.14599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.989854335784912]} {"step": 35700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35700, "total_transitions": 146227200, "num_steps_per_env": 1, "wm_loss": 0.45172223448753357, "actor_loss": -8.725629806518555, "critic_loss": 0.03227958083152771, "reward": 0.07037516683340073, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2481401115655899, 0.15515875816345215, 0.2558942437171936], "policy_updates": 35600, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6078.002147278, "contact_bce": 0.3161970376968384, "contact_force_loss": 0.03251238167285919, "terrain_level_mean": 3.144775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.989854335784912]} {"step": 35710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35710, "total_transitions": 146268160, "num_steps_per_env": 1, "wm_loss": 0.43708518147468567, "actor_loss": -8.681604385375977, "critic_loss": 0.0314435251057148, "reward": 0.07053636759519577, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24817825853824615, 0.15469522774219513, 0.2591695785522461], "policy_updates": 35610, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6081.5147368259995, "contact_bce": 0.3121321201324463, "contact_force_loss": 0.03205782547593117, "terrain_level_mean": 3.143798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9954891204833984, 0.998437225818634, 2.989854335784912]} {"step": 35720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35720, "total_transitions": 146309120, "num_steps_per_env": 1, "wm_loss": 0.46182653307914734, "actor_loss": -8.778594970703125, "critic_loss": 0.02340242639183998, "reward": 0.07076164335012436, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24317587912082672, 0.15366241335868835, 0.26102522015571594], "policy_updates": 35620, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6085.034342628999, "contact_bce": 0.317088782787323, "contact_force_loss": 0.03295909985899925, "terrain_level_mean": 3.142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9954891204833984, 0.9991834163665771, 2.989854335784912]} {"step": 35730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35730, "total_transitions": 146350080, "num_steps_per_env": 1, "wm_loss": 0.46858975291252136, "actor_loss": -8.761361122131348, "critic_loss": 0.02727838233113289, "reward": 0.07099854201078415, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24055778980255127, 0.15426598489284515, 0.2531381845474243], "policy_updates": 35630, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6088.550781225999, "contact_bce": 0.31645604968070984, "contact_force_loss": 0.03250381723046303, "terrain_level_mean": 3.141845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.989854335784912]} {"step": 35740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35740, "total_transitions": 146391040, "num_steps_per_env": 1, "wm_loss": 0.4984763562679291, "actor_loss": -8.71194076538086, "critic_loss": 0.02721598744392395, "reward": 0.0708613395690918, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24015483260154724, 0.15126095712184906, 0.2541872560977936], "policy_updates": 35640, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6092.061264837999, "contact_bce": 0.3144160509109497, "contact_force_loss": 0.03245853632688522, "terrain_level_mean": 3.140869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.989854335784912]} {"step": 35750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35750, "total_transitions": 146432000, "num_steps_per_env": 1, "wm_loss": 0.42908215522766113, "actor_loss": -8.729089736938477, "critic_loss": 0.02429724484682083, "reward": 0.07074890285730362, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24004478752613068, 0.15024304389953613, 0.2526666224002838], "policy_updates": 35650, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6095.5705696019995, "contact_bce": 0.31549614667892456, "contact_force_loss": 0.032291390001773834, "terrain_level_mean": 3.141845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.989854335784912]} {"step": 35760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35760, "total_transitions": 146472960, "num_steps_per_env": 1, "wm_loss": 0.4326479136943817, "actor_loss": -8.802757263183594, "critic_loss": 0.022359751164913177, "reward": 0.07024869322776794, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2466997355222702, 0.15138961374759674, 0.25285226106643677], "policy_updates": 35660, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6099.080153805, "contact_bce": 0.3118698298931122, "contact_force_loss": 0.03181667625904083, "terrain_level_mean": 3.142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.989854335784912]} {"step": 35770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35770, "total_transitions": 146513920, "num_steps_per_env": 1, "wm_loss": 0.4399360418319702, "actor_loss": -8.71844482421875, "critic_loss": 0.03512878343462944, "reward": 0.07054349035024643, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23933500051498413, 0.15291491150856018, 0.2522066831588745], "policy_updates": 35670, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6102.587973526, "contact_bce": 0.31450599431991577, "contact_force_loss": 0.03154690936207771, "terrain_level_mean": 3.142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.989854335784912]} {"step": 35780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35780, "total_transitions": 146554880, "num_steps_per_env": 1, "wm_loss": 0.486762672662735, "actor_loss": -8.729829788208008, "critic_loss": 0.027044687420129776, "reward": 0.07056788355112076, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2422725409269333, 0.15559197962284088, 0.2515621483325958], "policy_updates": 35680, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6106.095855809, "contact_bce": 0.31252503395080566, "contact_force_loss": 0.032451480627059937, "terrain_level_mean": 3.1416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.989854335784912]} {"step": 35790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35790, "total_transitions": 146595840, "num_steps_per_env": 1, "wm_loss": 0.43212950229644775, "actor_loss": -8.716448783874512, "critic_loss": 0.02431677281856537, "reward": 0.07064178586006165, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2423579841852188, 0.15176799893379211, 0.2500956952571869], "policy_updates": 35690, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6109.608899068, "contact_bce": 0.31621745228767395, "contact_force_loss": 0.03246702626347542, "terrain_level_mean": 3.1416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.989854335784912]} {"step": 35800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35800, "total_transitions": 146636800, "num_steps_per_env": 1, "wm_loss": 0.45964717864990234, "actor_loss": -8.697919845581055, "critic_loss": 0.029820546507835388, "reward": 0.07107535749673843, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24265220761299133, 0.1503451019525528, 0.24800921976566315], "policy_updates": 35700, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6113.136342309, "contact_bce": 0.31424298882484436, "contact_force_loss": 0.032062653452157974, "terrain_level_mean": 3.1416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.994401216506958]} {"step": 35810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35810, "total_transitions": 146677760, "num_steps_per_env": 1, "wm_loss": 0.49385589361190796, "actor_loss": -8.784994125366211, "critic_loss": 0.024914905428886414, "reward": 0.07099742442369461, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24418558180332184, 0.15127912163734436, 0.25281280279159546], "policy_updates": 35710, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6116.656197132, "contact_bce": 0.3187295198440552, "contact_force_loss": 0.03320227190852165, "terrain_level_mean": 3.140869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.994401216506958]} {"step": 35820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35820, "total_transitions": 146718720, "num_steps_per_env": 1, "wm_loss": 0.42076385021209717, "actor_loss": -8.779410362243652, "critic_loss": 0.03591769561171532, "reward": 0.0711163654923439, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24145174026489258, 0.15085472166538239, 0.2501724064350128], "policy_updates": 35720, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6120.175265342999, "contact_bce": 0.3114648163318634, "contact_force_loss": 0.03181971609592438, "terrain_level_mean": 3.139404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9973044395446777, 0.9991834163665771, 2.994401216506958]} {"step": 35830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35830, "total_transitions": 146759680, "num_steps_per_env": 1, "wm_loss": 0.4305587112903595, "actor_loss": -8.720884323120117, "critic_loss": 0.0311567485332489, "reward": 0.07153265923261642, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24091678857803345, 0.15066400170326233, 0.2504650950431824], "policy_updates": 35730, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6123.694085218, "contact_bce": 0.3147500157356262, "contact_force_loss": 0.03193969279527664, "terrain_level_mean": 3.140380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.994401216506958]} {"step": 35840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35840, "total_transitions": 146800640, "num_steps_per_env": 1, "wm_loss": 0.45282870531082153, "actor_loss": -8.734844207763672, "critic_loss": 0.02940991520881653, "reward": 0.07159944623708725, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24062223732471466, 0.14955806732177734, 0.2531147301197052], "policy_updates": 35740, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6127.219909414, "contact_bce": 0.31464457511901855, "contact_force_loss": 0.03247413411736488, "terrain_level_mean": 3.140869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.994401216506958]} {"step": 35850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35850, "total_transitions": 146841600, "num_steps_per_env": 1, "wm_loss": 0.4667171835899353, "actor_loss": -8.70069408416748, "critic_loss": 0.03504471853375435, "reward": 0.07131002098321915, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24102763831615448, 0.1515331119298935, 0.25514301657676697], "policy_updates": 35750, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6130.73471556, "contact_bce": 0.3087608814239502, "contact_force_loss": 0.03249061480164528, "terrain_level_mean": 3.140380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.986635684967041]} {"step": 35860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35860, "total_transitions": 146882560, "num_steps_per_env": 1, "wm_loss": 0.44917288422584534, "actor_loss": -8.77865982055664, "critic_loss": 0.018951967358589172, "reward": 0.07080429792404175, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24663181602954865, 0.15507780015468597, 0.2564639747142792], "policy_updates": 35760, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6134.239369721, "contact_bce": 0.316767156124115, "contact_force_loss": 0.032254476100206375, "terrain_level_mean": 3.1396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.986635684967041]} {"step": 35870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35870, "total_transitions": 146923520, "num_steps_per_env": 1, "wm_loss": 0.4124205410480499, "actor_loss": -8.796130180358887, "critic_loss": 0.01994984783232212, "reward": 0.0710829421877861, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2458188235759735, 0.15531766414642334, 0.2538852095603943], "policy_updates": 35770, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6137.761217718, "contact_bce": 0.3124164640903473, "contact_force_loss": 0.03191448375582695, "terrain_level_mean": 3.140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.986635684967041]} {"step": 35880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35880, "total_transitions": 146964480, "num_steps_per_env": 1, "wm_loss": 0.4467742443084717, "actor_loss": -8.723100662231445, "critic_loss": 0.021168002858757973, "reward": 0.07114332169294357, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2463989108800888, 0.1541575789451599, 0.25274813175201416], "policy_updates": 35780, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6141.282234781, "contact_bce": 0.3154788613319397, "contact_force_loss": 0.03307848796248436, "terrain_level_mean": 3.142333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.986635684967041]} {"step": 35890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35890, "total_transitions": 147005440, "num_steps_per_env": 1, "wm_loss": 0.45066529512405396, "actor_loss": -8.712263107299805, "critic_loss": 0.0286507960408926, "reward": 0.07098446786403656, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24589207768440247, 0.15602566301822662, 0.2527560591697693], "policy_updates": 35790, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6144.797203415999, "contact_bce": 0.31345221400260925, "contact_force_loss": 0.032416004687547684, "terrain_level_mean": 3.142822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.992487907409668]} {"step": 35900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35900, "total_transitions": 147046400, "num_steps_per_env": 1, "wm_loss": 0.4425278604030609, "actor_loss": -8.766134262084961, "critic_loss": 0.02296229638159275, "reward": 0.07068094611167908, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24830888211727142, 0.1592566967010498, 0.25763988494873047], "policy_updates": 35800, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6148.306444303, "contact_bce": 0.3159315586090088, "contact_force_loss": 0.032558709383010864, "terrain_level_mean": 3.142822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.992487907409668]} {"step": 35910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35910, "total_transitions": 147087360, "num_steps_per_env": 1, "wm_loss": 0.4592418670654297, "actor_loss": -8.744361877441406, "critic_loss": 0.026109347119927406, "reward": 0.07059406489133835, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24989917874336243, 0.15997107326984406, 0.2541063129901886], "policy_updates": 35810, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6151.822363374, "contact_bce": 0.31412529945373535, "contact_force_loss": 0.03223080188035965, "terrain_level_mean": 3.14208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.992487907409668]} {"step": 35920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35920, "total_transitions": 147128320, "num_steps_per_env": 1, "wm_loss": 0.45852401852607727, "actor_loss": -8.743890762329102, "critic_loss": 0.021190956234931946, "reward": 0.07093904167413712, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24791647493839264, 0.15792082250118256, 0.2540035545825958], "policy_updates": 35820, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6155.344598291, "contact_bce": 0.3193058371543884, "contact_force_loss": 0.033239368349313736, "terrain_level_mean": 3.14208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.992487907409668]} {"step": 35930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35930, "total_transitions": 147169280, "num_steps_per_env": 1, "wm_loss": 0.4216479957103729, "actor_loss": -8.77442455291748, "critic_loss": 0.020509636029601097, "reward": 0.07104574888944626, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24717392027378082, 0.1591169238090515, 0.2560673654079437], "policy_updates": 35830, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6158.873953537, "contact_bce": 0.3193841874599457, "contact_force_loss": 0.03232493996620178, "terrain_level_mean": 3.142822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.992487907409668]} {"step": 35940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35940, "total_transitions": 147210240, "num_steps_per_env": 1, "wm_loss": 0.4453144073486328, "actor_loss": -8.771041870117188, "critic_loss": 0.02785280905663967, "reward": 0.07128366082906723, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24621517956256866, 0.1600538045167923, 0.2549896240234375], "policy_updates": 35840, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6162.391809623, "contact_bce": 0.317598819732666, "contact_force_loss": 0.03234823793172836, "terrain_level_mean": 3.143310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.992487907409668]} {"step": 35950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35950, "total_transitions": 147251200, "num_steps_per_env": 1, "wm_loss": 0.43877002596855164, "actor_loss": -8.75915813446045, "critic_loss": 0.037937231361866, "reward": 0.07069691270589828, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2481277585029602, 0.16244135797023773, 0.25770917534828186], "policy_updates": 35850, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6165.908633213, "contact_bce": 0.31063568592071533, "contact_force_loss": 0.032628536224365234, "terrain_level_mean": 3.143310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.9980287551879883, 0.9991834163665771, 2.992487907409668]} {"step": 35960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35960, "total_transitions": 147292160, "num_steps_per_env": 1, "wm_loss": 0.45066016912460327, "actor_loss": -8.761770248413086, "critic_loss": 0.027124464511871338, "reward": 0.07046271860599518, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2492235153913498, 0.16419801115989685, 0.2556372880935669], "policy_updates": 35860, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6169.424071564999, "contact_bce": 0.31500813364982605, "contact_force_loss": 0.03313655033707619, "terrain_level_mean": 3.14306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358642578125, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.992487907409668]} {"step": 35970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35970, "total_transitions": 147333120, "num_steps_per_env": 1, "wm_loss": 0.42402738332748413, "actor_loss": -8.789815902709961, "critic_loss": 0.024115068838000298, "reward": 0.07046742737293243, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24826659262180328, 0.16127145290374756, 0.25756531953811646], "policy_updates": 35870, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6172.936945977, "contact_bce": 0.3131853938102722, "contact_force_loss": 0.03133595734834671, "terrain_level_mean": 3.141845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.360107421875, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.992487907409668]} {"step": 35980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35980, "total_transitions": 147374080, "num_steps_per_env": 1, "wm_loss": 0.45406022667884827, "actor_loss": -8.74349308013916, "critic_loss": 0.02659839391708374, "reward": 0.07090295106172562, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24727261066436768, 0.15912923216819763, 0.2543126344680786], "policy_updates": 35880, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6176.447852279, "contact_bce": 0.3135843873023987, "contact_force_loss": 0.03220445290207863, "terrain_level_mean": 3.14208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.364013671875, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.992487907409668]} {"step": 35990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 35990, "total_transitions": 147415040, "num_steps_per_env": 1, "wm_loss": 0.4388420283794403, "actor_loss": -8.758790969848633, "critic_loss": 0.02061363123357296, "reward": 0.07057195156812668, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24427302181720734, 0.15682151913642883, 0.25653722882270813], "policy_updates": 35890, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6179.9595626, "contact_bce": 0.3125540614128113, "contact_force_loss": 0.031763624399900436, "terrain_level_mean": 3.141845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.365478515625, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.992487907409668]} {"step": 36000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36000, "total_transitions": 147456000, "num_steps_per_env": 1, "wm_loss": 0.437099426984787, "actor_loss": -8.755943298339844, "critic_loss": 0.025868047028779984, "reward": 0.0710097923874855, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24363954365253448, 0.15796826779842377, 0.2557220160961151], "policy_updates": 35900, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6183.472556938999, "contact_bce": 0.31741946935653687, "contact_force_loss": 0.03212552145123482, "terrain_level_mean": 3.140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.368408203125, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.992487907409668]} {"step": 36010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36010, "total_transitions": 147496960, "num_steps_per_env": 1, "wm_loss": 0.46954405307769775, "actor_loss": -8.773576736450195, "critic_loss": 0.024825816974043846, "reward": 0.07143198698759079, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24321435391902924, 0.15931057929992676, 0.25293368101119995], "policy_updates": 35910, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6187.030178178999, "contact_bce": 0.31926649808883667, "contact_force_loss": 0.03395478054881096, "terrain_level_mean": 3.140380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36767578125, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.994213104248047]} {"step": 36020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36020, "total_transitions": 147537920, "num_steps_per_env": 1, "wm_loss": 0.4327463209629059, "actor_loss": -8.751612663269043, "critic_loss": 0.020907914265990257, "reward": 0.07112859934568405, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24758373200893402, 0.15849630534648895, 0.2565028965473175], "policy_updates": 35920, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6190.553398231999, "contact_bce": 0.31614556908607483, "contact_force_loss": 0.03233123943209648, "terrain_level_mean": 3.140869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3642578125, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.994213104248047]} {"step": 36030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36030, "total_transitions": 147578880, "num_steps_per_env": 1, "wm_loss": 0.45143643021583557, "actor_loss": -8.737716674804688, "critic_loss": 0.025043046101927757, "reward": 0.07161988317966461, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24788504838943481, 0.1554499864578247, 0.2526048719882965], "policy_updates": 35930, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6194.309358248, "contact_bce": 0.3093518316745758, "contact_force_loss": 0.032256390899419785, "terrain_level_mean": 3.14111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.364990234375, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.995377540588379]} {"step": 36040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36040, "total_transitions": 147619840, "num_steps_per_env": 1, "wm_loss": 0.44577595591545105, "actor_loss": -8.735408782958984, "critic_loss": 0.03173909708857536, "reward": 0.07148169726133347, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24611876904964447, 0.15675592422485352, 0.25363507866859436], "policy_updates": 35940, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6197.820397445999, "contact_bce": 0.3138503432273865, "contact_force_loss": 0.03213438391685486, "terrain_level_mean": 3.142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36328125, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.995377540588379]} {"step": 36050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36050, "total_transitions": 147660800, "num_steps_per_env": 1, "wm_loss": 0.431835800409317, "actor_loss": -8.760549545288086, "critic_loss": 0.02804132178425789, "reward": 0.07097554951906204, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2487192451953888, 0.1574825793504715, 0.25879329442977905], "policy_updates": 35950, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6201.336372076999, "contact_bce": 0.3163062036037445, "contact_force_loss": 0.03282161429524422, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361572265625, "command_abs_max": [1.9988614320755005, 0.9991834163665771, 2.995377540588379]} {"step": 36060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36060, "total_transitions": 147701760, "num_steps_per_env": 1, "wm_loss": 0.4221484661102295, "actor_loss": -8.71180534362793, "critic_loss": 0.023125508800148964, "reward": 0.07085532695055008, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24517986178398132, 0.15836918354034424, 0.2567731738090515], "policy_updates": 35960, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6204.832177861999, "contact_bce": 0.3138847351074219, "contact_force_loss": 0.03171613812446594, "terrain_level_mean": 3.144775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361083984375, "command_abs_max": [1.9978249073028564, 0.9991834163665771, 2.995377540588379]} {"step": 36070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36070, "total_transitions": 147742720, "num_steps_per_env": 1, "wm_loss": 0.4221456050872803, "actor_loss": -8.78196907043457, "critic_loss": 0.02381650172173977, "reward": 0.07128944247961044, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24708589911460876, 0.15935303270816803, 0.25464338064193726], "policy_updates": 35970, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6208.334332056, "contact_bce": 0.3168431520462036, "contact_force_loss": 0.032375678420066833, "terrain_level_mean": 3.14404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358642578125, "command_abs_max": [1.9978249073028564, 0.9991834163665771, 2.995377540588379]} {"step": 36080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36080, "total_transitions": 147783680, "num_steps_per_env": 1, "wm_loss": 0.46290722489356995, "actor_loss": -8.733053207397461, "critic_loss": 0.0231789443641901, "reward": 0.07161473482847214, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24639911949634552, 0.15800942480564117, 0.25569334626197815], "policy_updates": 35980, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6211.83230279, "contact_bce": 0.31420889496803284, "contact_force_loss": 0.03282272443175316, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9978249073028564, 0.9991834163665771, 2.995377540588379]} {"step": 36090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36090, "total_transitions": 147824640, "num_steps_per_env": 1, "wm_loss": 0.47007548809051514, "actor_loss": -8.751946449279785, "critic_loss": 0.019995754584670067, "reward": 0.0716601312160492, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24180251359939575, 0.1599312573671341, 0.2567967474460602], "policy_updates": 35990, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6215.331817316, "contact_bce": 0.31742754578590393, "contact_force_loss": 0.03247598558664322, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9978249073028564, 0.9991834163665771, 2.995377540588379]} {"step": 36100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36100, "total_transitions": 147865600, "num_steps_per_env": 1, "wm_loss": 0.4604753255844116, "actor_loss": -8.700927734375, "critic_loss": 0.03364340215921402, "reward": 0.0716136023402214, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2470698058605194, 0.15894465148448944, 0.2533034682273865], "policy_updates": 36000, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6218.831815514, "contact_bce": 0.3132425546646118, "contact_force_loss": 0.03167956694960594, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.9978249073028564, 0.9991834163665771, 2.995377540588379]} {"step": 36110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36110, "total_transitions": 147906560, "num_steps_per_env": 1, "wm_loss": 0.46460598707199097, "actor_loss": -8.752492904663086, "critic_loss": 0.030407512560486794, "reward": 0.07145526260137558, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2490203082561493, 0.15984772145748138, 0.2505738139152527], "policy_updates": 36010, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6222.353039459999, "contact_bce": 0.3203001618385315, "contact_force_loss": 0.032779280096292496, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9978249073028564, 0.9959897994995117, 2.995377540588379]} {"step": 36120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36120, "total_transitions": 147947520, "num_steps_per_env": 1, "wm_loss": 0.4507283568382263, "actor_loss": -8.717683792114258, "critic_loss": 0.031037181615829468, "reward": 0.07116437703371048, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24965159595012665, 0.15949413180351257, 0.25229552388191223], "policy_updates": 36020, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6225.874110817999, "contact_bce": 0.32192546129226685, "contact_force_loss": 0.032998912036418915, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9978249073028564, 0.9959897994995117, 2.999471426010132]} {"step": 36130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36130, "total_transitions": 147988480, "num_steps_per_env": 1, "wm_loss": 0.4420110881328583, "actor_loss": -8.706413269042969, "critic_loss": 0.031531866639852524, "reward": 0.07111312448978424, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2463228851556778, 0.15799754858016968, 0.25690171122550964], "policy_updates": 36030, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6229.392139805, "contact_bce": 0.3159690499305725, "contact_force_loss": 0.03283866122364998, "terrain_level_mean": 3.146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9978249073028564, 0.9959897994995117, 2.999471426010132]} {"step": 36140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36140, "total_transitions": 148029440, "num_steps_per_env": 1, "wm_loss": 0.4322308897972107, "actor_loss": -8.747812271118164, "critic_loss": 0.024970365688204765, "reward": 0.07133200764656067, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2396717667579651, 0.15693365037441254, 0.25393933057785034], "policy_updates": 36040, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6232.908252388999, "contact_bce": 0.3116489052772522, "contact_force_loss": 0.03262347728013992, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9978249073028564, 0.9959897994995117, 2.999471426010132]} {"step": 36150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36150, "total_transitions": 148070400, "num_steps_per_env": 1, "wm_loss": 0.43225497007369995, "actor_loss": -8.7425537109375, "critic_loss": 0.02529900148510933, "reward": 0.07161325216293335, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24399437010288239, 0.15766355395317078, 0.2515200674533844], "policy_updates": 36050, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6236.420908686, "contact_bce": 0.3180580139160156, "contact_force_loss": 0.03242132067680359, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9978249073028564, 0.9959897994995117, 2.999471426010132]} {"step": 36160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36160, "total_transitions": 148111360, "num_steps_per_env": 1, "wm_loss": 0.4483729600906372, "actor_loss": -8.72822380065918, "critic_loss": 0.025504428893327713, "reward": 0.07143858820199966, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24471232295036316, 0.16012679040431976, 0.25021499395370483], "policy_updates": 36060, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6239.931140645999, "contact_bce": 0.3103736937046051, "contact_force_loss": 0.03237798064947128, "terrain_level_mean": 3.1435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9978249073028564, 0.9959897994995117, 2.999471426010132]} {"step": 36170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36170, "total_transitions": 148152320, "num_steps_per_env": 1, "wm_loss": 0.42276060581207275, "actor_loss": -8.76399040222168, "critic_loss": 0.022559603676199913, "reward": 0.07117466628551483, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24641448259353638, 0.15929053723812103, 0.25385719537734985], "policy_updates": 36070, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6243.441582898, "contact_bce": 0.3165278136730194, "contact_force_loss": 0.03210240602493286, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9978249073028564, 0.9959897994995117, 2.999471426010132]} {"step": 36180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36180, "total_transitions": 148193280, "num_steps_per_env": 1, "wm_loss": 0.4715340733528137, "actor_loss": -8.76382064819336, "critic_loss": 0.026194190606474876, "reward": 0.07113124430179596, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24894066154956818, 0.16112887859344482, 0.25289732217788696], "policy_updates": 36080, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6246.962287824999, "contact_bce": 0.324493944644928, "contact_force_loss": 0.03348580375313759, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9978249073028564, 0.9938791394233704, 2.999471426010132]} {"step": 36190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36190, "total_transitions": 148234240, "num_steps_per_env": 1, "wm_loss": 0.4249498248100281, "actor_loss": -8.749470710754395, "critic_loss": 0.023545196279883385, "reward": 0.07126017659902573, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24597777426242828, 0.15647393465042114, 0.25477561354637146], "policy_updates": 36090, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6250.484232876, "contact_bce": 0.316756933927536, "contact_force_loss": 0.03194605931639671, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9978249073028564, 0.9938791394233704, 2.999471426010132]} {"step": 36200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36200, "total_transitions": 148275200, "num_steps_per_env": 1, "wm_loss": 0.4590415954589844, "actor_loss": -8.723234176635742, "critic_loss": 0.024438364431262016, "reward": 0.07103877514600754, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24995175004005432, 0.15647336840629578, 0.25516533851623535], "policy_updates": 36100, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6253.996645828, "contact_bce": 0.3141598105430603, "contact_force_loss": 0.0325394943356514, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9978249073028564, 0.9938791394233704, 2.999471426010132]} {"step": 36210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36210, "total_transitions": 148316160, "num_steps_per_env": 1, "wm_loss": 0.4617425203323364, "actor_loss": -8.741222381591797, "critic_loss": 0.03490814194083214, "reward": 0.0710175558924675, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24995405972003937, 0.1564386785030365, 0.25110891461372375], "policy_updates": 36110, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6257.505435294, "contact_bce": 0.31764712929725647, "contact_force_loss": 0.03301207721233368, "terrain_level_mean": 3.144775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9978249073028564, 0.9988263845443726, 2.999471426010132]} {"step": 36220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36220, "total_transitions": 148357120, "num_steps_per_env": 1, "wm_loss": 0.4261989891529083, "actor_loss": -8.759881019592285, "critic_loss": 0.026022419333457947, "reward": 0.07134970277547836, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24977757036685944, 0.1595020890235901, 0.25066787004470825], "policy_updates": 36120, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6261.017824469, "contact_bce": 0.316773384809494, "contact_force_loss": 0.03218325227499008, "terrain_level_mean": 3.14453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9978249073028564, 0.9988263845443726, 2.999471426010132]} {"step": 36230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36230, "total_transitions": 148398080, "num_steps_per_env": 1, "wm_loss": 0.5026921629905701, "actor_loss": -8.798919677734375, "critic_loss": 0.02681523561477661, "reward": 0.07117971032857895, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2488914579153061, 0.15844865143299103, 0.25311505794525146], "policy_updates": 36130, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6264.52466469, "contact_bce": 0.31968674063682556, "contact_force_loss": 0.03292347118258476, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9978249073028564, 0.9988263845443726, 2.999471426010132]} {"step": 36240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36240, "total_transitions": 148439040, "num_steps_per_env": 1, "wm_loss": 0.41039612889289856, "actor_loss": -8.823577880859375, "critic_loss": 0.015307351015508175, "reward": 0.07056837528944016, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24664324522018433, 0.15975819528102875, 0.2584993541240692], "policy_updates": 36140, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6268.040822299, "contact_bce": 0.3136156499385834, "contact_force_loss": 0.03172355517745018, "terrain_level_mean": 3.142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9964721202850342, 0.9988263845443726, 2.999471426010132]} {"step": 36250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36250, "total_transitions": 148480000, "num_steps_per_env": 1, "wm_loss": 0.4430297017097473, "actor_loss": -8.791446685791016, "critic_loss": 0.017380470409989357, "reward": 0.0703069269657135, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2449043095111847, 0.158242866396904, 0.25997495651245117], "policy_updates": 36150, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6271.551765882, "contact_bce": 0.3103419840335846, "contact_force_loss": 0.03204018250107765, "terrain_level_mean": 3.14306640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9964721202850342, 0.9988263845443726, 2.999471426010132]} {"step": 36260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36260, "total_transitions": 148520960, "num_steps_per_env": 1, "wm_loss": 0.42653143405914307, "actor_loss": -8.762968063354492, "critic_loss": 0.03853610157966614, "reward": 0.07089954614639282, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24566754698753357, 0.15735295414924622, 0.2579428255558014], "policy_updates": 36160, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6275.062158471999, "contact_bce": 0.30963510274887085, "contact_force_loss": 0.03183649107813835, "terrain_level_mean": 3.1435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36270, "total_transitions": 148561920, "num_steps_per_env": 1, "wm_loss": 0.4846886396408081, "actor_loss": -8.775381088256836, "critic_loss": 0.02591582015156746, "reward": 0.07120942324399948, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2430514395236969, 0.15690234303474426, 0.25314760208129883], "policy_updates": 36170, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6278.587908078, "contact_bce": 0.3204444348812103, "contact_force_loss": 0.03270043060183525, "terrain_level_mean": 3.143798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36280, "total_transitions": 148602880, "num_steps_per_env": 1, "wm_loss": 0.4691939949989319, "actor_loss": -8.741256713867188, "critic_loss": 0.022987715899944305, "reward": 0.07151635736227036, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23963594436645508, 0.15829315781593323, 0.25061360001564026], "policy_updates": 36180, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6282.100967884, "contact_bce": 0.3196554183959961, "contact_force_loss": 0.03299994394183159, "terrain_level_mean": 3.14404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36290, "total_transitions": 148643840, "num_steps_per_env": 1, "wm_loss": 0.41556891798973083, "actor_loss": -8.750288963317871, "critic_loss": 0.027260437607765198, "reward": 0.07133220881223679, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2395806461572647, 0.15816952288150787, 0.25411731004714966], "policy_updates": 36190, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6285.6121424289995, "contact_bce": 0.3173602819442749, "contact_force_loss": 0.03154166415333748, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36300, "total_transitions": 148684800, "num_steps_per_env": 1, "wm_loss": 0.4418548047542572, "actor_loss": -8.73066234588623, "critic_loss": 0.035104889422655106, "reward": 0.0707952007651329, "falls": 0, "interval_steps": 10, "velocity_mae": [0.23977743089199066, 0.15767614543437958, 0.25623446702957153], "policy_updates": 36200, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6289.121809712, "contact_bce": 0.3180561065673828, "contact_force_loss": 0.03233730047941208, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36310, "total_transitions": 148725760, "num_steps_per_env": 1, "wm_loss": 0.45581457018852234, "actor_loss": -8.752677917480469, "critic_loss": 0.022022239863872528, "reward": 0.07059996575117111, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24125953018665314, 0.1566220223903656, 0.25698617100715637], "policy_updates": 36210, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6292.643076077, "contact_bce": 0.31209006905555725, "contact_force_loss": 0.03281722962856293, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36320, "total_transitions": 148766720, "num_steps_per_env": 1, "wm_loss": 0.4555804133415222, "actor_loss": -8.78512191772461, "critic_loss": 0.01696488820016384, "reward": 0.07079961150884628, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23980607092380524, 0.15634670853614807, 0.2521365284919739], "policy_updates": 36220, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6296.154034186, "contact_bce": 0.3112860918045044, "contact_force_loss": 0.03264479711651802, "terrain_level_mean": 3.144775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36330, "total_transitions": 148807680, "num_steps_per_env": 1, "wm_loss": 0.44661158323287964, "actor_loss": -8.737678527832031, "critic_loss": 0.02049405872821808, "reward": 0.07037808746099472, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24477428197860718, 0.15937694907188416, 0.2545894384384155], "policy_updates": 36230, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6299.667209067, "contact_bce": 0.3209743797779083, "contact_force_loss": 0.032982923090457916, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36340, "total_transitions": 148848640, "num_steps_per_env": 1, "wm_loss": 0.44774019718170166, "actor_loss": -8.782971382141113, "critic_loss": 0.02290809527039528, "reward": 0.07053761929273605, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2448742687702179, 0.1579034924507141, 0.2588302791118622], "policy_updates": 36240, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6303.188484953999, "contact_bce": 0.31782928109169006, "contact_force_loss": 0.033069174736738205, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9964721202850342, 0.9998853206634521, 2.999471426010132]} {"step": 36350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36350, "total_transitions": 148889600, "num_steps_per_env": 1, "wm_loss": 0.4416607618331909, "actor_loss": -8.766231536865234, "critic_loss": 0.025904541835188866, "reward": 0.07025229930877686, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25053921341896057, 0.15727001428604126, 0.26083338260650635], "policy_updates": 36250, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6306.692689861, "contact_bce": 0.3194281756877899, "contact_force_loss": 0.03220108151435852, "terrain_level_mean": 3.14501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36360, "total_transitions": 148930560, "num_steps_per_env": 1, "wm_loss": 0.44151008129119873, "actor_loss": -8.774797439575195, "critic_loss": 0.02839541807770729, "reward": 0.0697907954454422, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24930348992347717, 0.15859292447566986, 0.26290348172187805], "policy_updates": 36260, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6310.205552804, "contact_bce": 0.3152201175689697, "contact_force_loss": 0.03225381299853325, "terrain_level_mean": 3.14501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36370, "total_transitions": 148971520, "num_steps_per_env": 1, "wm_loss": 0.4201396405696869, "actor_loss": -8.794341087341309, "critic_loss": 0.02178000472486019, "reward": 0.07002546638250351, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24979643523693085, 0.1579107791185379, 0.2597723603248596], "policy_updates": 36270, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6313.731088414999, "contact_bce": 0.3129829466342926, "contact_force_loss": 0.03183737397193909, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36380, "total_transitions": 149012480, "num_steps_per_env": 1, "wm_loss": 0.4369764029979706, "actor_loss": -8.762104988098145, "critic_loss": 0.023379893973469734, "reward": 0.07051211595535278, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2517136037349701, 0.15547850728034973, 0.2569950222969055], "policy_updates": 36280, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6317.250352120999, "contact_bce": 0.3172326683998108, "contact_force_loss": 0.032964758574962616, "terrain_level_mean": 3.144287109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36390, "total_transitions": 149053440, "num_steps_per_env": 1, "wm_loss": 0.4675233066082001, "actor_loss": -8.765295028686523, "critic_loss": 0.01867392472922802, "reward": 0.0702805146574974, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25358614325523376, 0.15743891894817352, 0.2567918598651886], "policy_updates": 36290, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6320.771755391, "contact_bce": 0.31843137741088867, "contact_force_loss": 0.03249846026301384, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36400, "total_transitions": 149094400, "num_steps_per_env": 1, "wm_loss": 0.4599387049674988, "actor_loss": -8.755413055419922, "critic_loss": 0.02163809724152088, "reward": 0.07094255834817886, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2509072422981262, 0.1569979190826416, 0.2533586621284485], "policy_updates": 36300, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6324.295207759999, "contact_bce": 0.3146388530731201, "contact_force_loss": 0.03227582201361656, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36410, "total_transitions": 149135360, "num_steps_per_env": 1, "wm_loss": 0.46673327684402466, "actor_loss": -8.695816040039062, "critic_loss": 0.030024021863937378, "reward": 0.07096753269433975, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24521830677986145, 0.15593375265598297, 0.2546970844268799], "policy_updates": 36310, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6327.824035299, "contact_bce": 0.32067328691482544, "contact_force_loss": 0.032557979226112366, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36420, "total_transitions": 149176320, "num_steps_per_env": 1, "wm_loss": 0.4587711989879608, "actor_loss": -8.787285804748535, "critic_loss": 0.026626795530319214, "reward": 0.07049473375082016, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24244219064712524, 0.15623484551906586, 0.2596542537212372], "policy_updates": 36320, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6331.348120052, "contact_bce": 0.3193228542804718, "contact_force_loss": 0.033087752759456635, "terrain_level_mean": 3.1455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36430, "total_transitions": 149217280, "num_steps_per_env": 1, "wm_loss": 0.4665742814540863, "actor_loss": -8.744279861450195, "critic_loss": 0.0216212160885334, "reward": 0.07071679085493088, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24499912559986115, 0.15860430896282196, 0.2563633620738983], "policy_updates": 36330, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6334.870312163, "contact_bce": 0.31815075874328613, "contact_force_loss": 0.03362898901104927, "terrain_level_mean": 3.144775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36440, "total_transitions": 149258240, "num_steps_per_env": 1, "wm_loss": 0.462374210357666, "actor_loss": -8.71017837524414, "critic_loss": 0.027660435065627098, "reward": 0.07085062563419342, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2433074414730072, 0.15545399487018585, 0.2556103765964508], "policy_updates": 36340, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6338.394628022, "contact_bce": 0.31569233536720276, "contact_force_loss": 0.03287585452198982, "terrain_level_mean": 3.145751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9968935251235962, 0.9998853206634521, 2.999471426010132]} {"step": 36450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36450, "total_transitions": 149299200, "num_steps_per_env": 1, "wm_loss": 0.486627995967865, "actor_loss": -8.744614601135254, "critic_loss": 0.022042596712708473, "reward": 0.07162918895483017, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24092303216457367, 0.15243135392665863, 0.2521617114543915], "policy_updates": 36350, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6341.914609400999, "contact_bce": 0.3183126151561737, "contact_force_loss": 0.03294951468706131, "terrain_level_mean": 3.145263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.996340274810791, 0.9998853206634521, 2.999471426010132]} {"step": 36460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36460, "total_transitions": 149340160, "num_steps_per_env": 1, "wm_loss": 0.4650821387767792, "actor_loss": -8.732815742492676, "critic_loss": 0.030614862218499184, "reward": 0.07182227820158005, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24038054049015045, 0.15198469161987305, 0.2512821555137634], "policy_updates": 36360, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6345.431066012, "contact_bce": 0.3172330856323242, "contact_force_loss": 0.03324100002646446, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.996340274810791, 0.9998853206634521, 2.999471426010132]} {"step": 36470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36470, "total_transitions": 149381120, "num_steps_per_env": 1, "wm_loss": 0.428252249956131, "actor_loss": -8.740639686584473, "critic_loss": 0.021659689024090767, "reward": 0.07154998183250427, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24078018963336945, 0.1529180258512497, 0.254409521818161], "policy_updates": 36370, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6348.956742578, "contact_bce": 0.3163699209690094, "contact_force_loss": 0.032226018607616425, "terrain_level_mean": 3.14697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.996340274810791, 0.9998853206634521, 2.999471426010132]} {"step": 36480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36480, "total_transitions": 149422080, "num_steps_per_env": 1, "wm_loss": 0.4485095143318176, "actor_loss": -8.752126693725586, "critic_loss": 0.02470039762556553, "reward": 0.07128434628248215, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24366196990013123, 0.1560966521501541, 0.26181358098983765], "policy_updates": 36380, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6352.480069619, "contact_bce": 0.3176448941230774, "contact_force_loss": 0.03268083184957504, "terrain_level_mean": 3.1474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.996340274810791, 0.9998853206634521, 2.9992752075195312]} {"step": 36490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36490, "total_transitions": 149463040, "num_steps_per_env": 1, "wm_loss": 0.447171688079834, "actor_loss": -8.728631019592285, "critic_loss": 0.03133552148938179, "reward": 0.07101594656705856, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24858704209327698, 0.15704049170017242, 0.2587119936943054], "policy_updates": 36390, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6356.002249157999, "contact_bce": 0.3206213116645813, "contact_force_loss": 0.03232951834797859, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.996340274810791, 0.9988263845443726, 2.9992752075195312]} {"step": 36500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36500, "total_transitions": 149504000, "num_steps_per_env": 1, "wm_loss": 0.44710230827331543, "actor_loss": -8.750064849853516, "critic_loss": 0.023661453276872635, "reward": 0.07125156372785568, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24723823368549347, 0.15492916107177734, 0.2573729157447815], "policy_updates": 36400, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6359.5095741469995, "contact_bce": 0.3190760612487793, "contact_force_loss": 0.03234844654798508, "terrain_level_mean": 3.1484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.996340274810791, 0.9988263845443726, 2.9992752075195312]} {"step": 36510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36510, "total_transitions": 149544960, "num_steps_per_env": 1, "wm_loss": 0.46012890338897705, "actor_loss": -8.729287147521973, "critic_loss": 0.026368433609604836, "reward": 0.07136877626180649, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24534523487091064, 0.15561997890472412, 0.25615835189819336], "policy_updates": 36410, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6363.046846513999, "contact_bce": 0.31863123178482056, "contact_force_loss": 0.033065322786569595, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.996340274810791, 0.9988263845443726, 2.9992752075195312]} {"step": 36520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36520, "total_transitions": 149585920, "num_steps_per_env": 1, "wm_loss": 0.44273942708969116, "actor_loss": -8.73903751373291, "critic_loss": 0.02063198946416378, "reward": 0.07161431014537811, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2407449185848236, 0.15625226497650146, 0.2574023902416229], "policy_updates": 36420, "skipped_updates": 0, "invalid_env_resets": 57, "elapsed_s": 6366.560415872999, "contact_bce": 0.319232702255249, "contact_force_loss": 0.032205622643232346, "terrain_level_mean": 3.148681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.996340274810791, 0.9988263845443726, 2.9992752075195312]} RECOVERY reset 1 invalid environments; first IDs=[2154] {"step": 36530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36530, "total_transitions": 149626880, "num_steps_per_env": 1, "wm_loss": 0.40771469473838806, "actor_loss": -8.752949714660645, "critic_loss": 0.02225944772362709, "reward": 0.071125328540802, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24201403558254242, 0.15915590524673462, 0.26143530011177063], "policy_updates": 36430, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6370.342850266, "contact_bce": 0.3161548376083374, "contact_force_loss": 0.032168157398700714, "terrain_level_mean": 3.1484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.996340274810791, 0.9988263845443726, 2.9951703548431396]} {"step": 36540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36540, "total_transitions": 149667840, "num_steps_per_env": 1, "wm_loss": 0.45615383982658386, "actor_loss": -8.75759506225586, "critic_loss": 0.028044620528817177, "reward": 0.07112108170986176, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24406573176383972, 0.1608136147260666, 0.2560441493988037], "policy_updates": 36440, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6373.872504866, "contact_bce": 0.31574052572250366, "contact_force_loss": 0.0318688340485096, "terrain_level_mean": 3.147705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9951703548431396]} {"step": 36550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36550, "total_transitions": 149708800, "num_steps_per_env": 1, "wm_loss": 0.45317351818084717, "actor_loss": -8.755450248718262, "critic_loss": 0.022952377796173096, "reward": 0.0712452083826065, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2477806955575943, 0.16131186485290527, 0.254839688539505], "policy_updates": 36450, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6377.3697843479995, "contact_bce": 0.31927555799484253, "contact_force_loss": 0.03333396092057228, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9954116344451904]} {"step": 36560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36560, "total_transitions": 149749760, "num_steps_per_env": 1, "wm_loss": 0.43492597341537476, "actor_loss": -8.729351043701172, "critic_loss": 0.023296859115362167, "reward": 0.07139692455530167, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24802212417125702, 0.15909306704998016, 0.2556481957435608], "policy_updates": 36460, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6380.869773275999, "contact_bce": 0.31853973865509033, "contact_force_loss": 0.03174947574734688, "terrain_level_mean": 3.146240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9954116344451904]} {"step": 36570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36570, "total_transitions": 149790720, "num_steps_per_env": 1, "wm_loss": 0.43237531185150146, "actor_loss": -8.720260620117188, "critic_loss": 0.03528715297579765, "reward": 0.07109371572732925, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25149258971214294, 0.1630788892507553, 0.254450261592865], "policy_updates": 36470, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6384.379636244999, "contact_bce": 0.31596213579177856, "contact_force_loss": 0.03202582150697708, "terrain_level_mean": 3.146728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.99771785736084]} {"step": 36580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36580, "total_transitions": 149831680, "num_steps_per_env": 1, "wm_loss": 0.461800217628479, "actor_loss": -8.73974323272705, "critic_loss": 0.03124450519680977, "reward": 0.07084030658006668, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25134798884391785, 0.1611267477273941, 0.26019152998924255], "policy_updates": 36480, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6387.895410448, "contact_bce": 0.32091087102890015, "contact_force_loss": 0.03289922699332237, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.99771785736084]} {"step": 36590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36590, "total_transitions": 149872640, "num_steps_per_env": 1, "wm_loss": 0.49784743785858154, "actor_loss": -8.763319969177246, "critic_loss": 0.022699488326907158, "reward": 0.0706813707947731, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25457096099853516, 0.15967443585395813, 0.26141440868377686], "policy_updates": 36490, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6391.4154340079995, "contact_bce": 0.31730976700782776, "contact_force_loss": 0.032753489911556244, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.99771785736084]} {"step": 36600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36600, "total_transitions": 149913600, "num_steps_per_env": 1, "wm_loss": 0.4415225386619568, "actor_loss": -8.732474327087402, "critic_loss": 0.025075063109397888, "reward": 0.070430688560009, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2583935856819153, 0.15891969203948975, 0.2558732330799103], "policy_updates": 36500, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6394.927086877, "contact_bce": 0.3193708062171936, "contact_force_loss": 0.0325237512588501, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.99771785736084]} {"step": 36610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36610, "total_transitions": 149954560, "num_steps_per_env": 1, "wm_loss": 0.4511030912399292, "actor_loss": -8.782602310180664, "critic_loss": 0.019566049799323082, "reward": 0.07008632272481918, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2587946057319641, 0.15921872854232788, 0.2565511465072632], "policy_updates": 36510, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6398.451127196, "contact_bce": 0.3072302043437958, "contact_force_loss": 0.03189896419644356, "terrain_level_mean": 3.147216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.99771785736084]} {"step": 36620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36620, "total_transitions": 149995520, "num_steps_per_env": 1, "wm_loss": 0.42807427048683167, "actor_loss": -8.729066848754883, "critic_loss": 0.027866629883646965, "reward": 0.07077445834875107, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2540898025035858, 0.15988455712795258, 0.2518647313117981], "policy_updates": 36520, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6401.964676406999, "contact_bce": 0.31123659014701843, "contact_force_loss": 0.03262000158429146, "terrain_level_mean": 3.14794921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9989352226257324]} {"step": 36630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36630, "total_transitions": 150036480, "num_steps_per_env": 1, "wm_loss": 0.42571696639060974, "actor_loss": -8.746337890625, "critic_loss": 0.022959396243095398, "reward": 0.07055887579917908, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2528432309627533, 0.1573522388935089, 0.25418299436569214], "policy_updates": 36530, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6405.483010358, "contact_bce": 0.31377944350242615, "contact_force_loss": 0.03256519138813019, "terrain_level_mean": 3.148681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9989352226257324]} {"step": 36640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36640, "total_transitions": 150077440, "num_steps_per_env": 1, "wm_loss": 0.4402497708797455, "actor_loss": -8.69842529296875, "critic_loss": 0.02911553718149662, "reward": 0.07078198343515396, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2503846287727356, 0.15595752000808716, 0.2564823031425476], "policy_updates": 36540, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6409.004647766999, "contact_bce": 0.3182775676250458, "contact_force_loss": 0.032594937831163406, "terrain_level_mean": 3.150146484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9989352226257324]} {"step": 36650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36650, "total_transitions": 150118400, "num_steps_per_env": 1, "wm_loss": 0.4613877534866333, "actor_loss": -8.770387649536133, "critic_loss": 0.024714192375540733, "reward": 0.07091157883405685, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24999427795410156, 0.15901173651218414, 0.2569286525249481], "policy_updates": 36550, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6412.529565772999, "contact_bce": 0.3227122724056244, "contact_force_loss": 0.03319729119539261, "terrain_level_mean": 3.1513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9989352226257324]} {"step": 36660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36660, "total_transitions": 150159360, "num_steps_per_env": 1, "wm_loss": 0.43240994215011597, "actor_loss": -8.746954917907715, "critic_loss": 0.022857164964079857, "reward": 0.07047182321548462, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25627556443214417, 0.15950517356395721, 0.2594112753868103], "policy_updates": 36560, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6416.048675579999, "contact_bce": 0.3143189251422882, "contact_force_loss": 0.032912708818912506, "terrain_level_mean": 3.1513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.996340274810791, 0.9992934465408325, 2.9989352226257324]} {"step": 36670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36670, "total_transitions": 150200320, "num_steps_per_env": 1, "wm_loss": 0.43605372309684753, "actor_loss": -8.767097473144531, "critic_loss": 0.02700943313539028, "reward": 0.07052174210548401, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25959327816963196, 0.1605583131313324, 0.26023921370506287], "policy_updates": 36570, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6419.569416988999, "contact_bce": 0.3144398331642151, "contact_force_loss": 0.0320524126291275, "terrain_level_mean": 3.15185546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.996340274810791, 0.9996211528778076, 2.9989352226257324]} {"step": 36680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36680, "total_transitions": 150241280, "num_steps_per_env": 1, "wm_loss": 0.4471946060657501, "actor_loss": -8.745689392089844, "critic_loss": 0.01647641696035862, "reward": 0.07105884701013565, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2547740340232849, 0.15667952597141266, 0.25584104657173157], "policy_updates": 36580, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6423.089116372, "contact_bce": 0.3139854967594147, "contact_force_loss": 0.032504498958587646, "terrain_level_mean": 3.15234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.996340274810791, 0.9996211528778076, 2.9989352226257324]} {"step": 36690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36690, "total_transitions": 150282240, "num_steps_per_env": 1, "wm_loss": 0.4440425932407379, "actor_loss": -8.767263412475586, "critic_loss": 0.022102201357483864, "reward": 0.0709368959069252, "falls": 1, "interval_steps": 10, "velocity_mae": [0.25147369503974915, 0.1593615561723709, 0.25795817375183105], "policy_updates": 36590, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6426.597486811999, "contact_bce": 0.31257811188697815, "contact_force_loss": 0.03236487880349159, "terrain_level_mean": 3.154052734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36700, "total_transitions": 150323200, "num_steps_per_env": 1, "wm_loss": 0.4821717143058777, "actor_loss": -8.741769790649414, "critic_loss": 0.02755906619131565, "reward": 0.070404551923275, "falls": 4, "interval_steps": 10, "velocity_mae": [0.250461608171463, 0.16228032112121582, 0.25606003403663635], "policy_updates": 36600, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6430.120441988, "contact_bce": 0.3227829933166504, "contact_force_loss": 0.03248405084013939, "terrain_level_mean": 3.15380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36710, "total_transitions": 150364160, "num_steps_per_env": 1, "wm_loss": 0.4512461721897125, "actor_loss": -8.8001070022583, "critic_loss": 0.021264618262648582, "reward": 0.07082891464233398, "falls": 5, "interval_steps": 10, "velocity_mae": [0.247873917222023, 0.15891921520233154, 0.25150808691978455], "policy_updates": 36610, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6433.636945136, "contact_bce": 0.31604981422424316, "contact_force_loss": 0.03314438834786415, "terrain_level_mean": 3.154541015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36720, "total_transitions": 150405120, "num_steps_per_env": 1, "wm_loss": 0.461211621761322, "actor_loss": -8.733360290527344, "critic_loss": 0.028122181072831154, "reward": 0.07069706916809082, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24972085654735565, 0.16016042232513428, 0.2517840564250946], "policy_updates": 36620, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6437.139408497999, "contact_bce": 0.3209287226200104, "contact_force_loss": 0.03248570114374161, "terrain_level_mean": 3.15478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36730, "total_transitions": 150446080, "num_steps_per_env": 1, "wm_loss": 0.47117719054222107, "actor_loss": -8.805275917053223, "critic_loss": 0.02336602844297886, "reward": 0.07089071720838547, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2482423484325409, 0.15797539055347443, 0.2514917850494385], "policy_updates": 36630, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6440.646236566, "contact_bce": 0.31793880462646484, "contact_force_loss": 0.03288719803094864, "terrain_level_mean": 3.155029296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36740, "total_transitions": 150487040, "num_steps_per_env": 1, "wm_loss": 0.4634413719177246, "actor_loss": -8.749271392822266, "critic_loss": 0.0329512357711792, "reward": 0.07121028751134872, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24426798522472382, 0.1583603471517563, 0.24975888431072235], "policy_updates": 36640, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6444.173045815, "contact_bce": 0.3155975341796875, "contact_force_loss": 0.033339183777570724, "terrain_level_mean": 3.156494140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36750, "total_transitions": 150528000, "num_steps_per_env": 1, "wm_loss": 0.4633154571056366, "actor_loss": -8.762154579162598, "critic_loss": 0.02307635359466076, "reward": 0.07111556828022003, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2437216341495514, 0.15619723498821259, 0.2519535422325134], "policy_updates": 36650, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6447.686709273999, "contact_bce": 0.3168814480304718, "contact_force_loss": 0.032812632620334625, "terrain_level_mean": 3.15673828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36760, "total_transitions": 150568960, "num_steps_per_env": 1, "wm_loss": 0.4608483910560608, "actor_loss": -8.766901016235352, "critic_loss": 0.022219302132725716, "reward": 0.07103317230939865, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24741049110889435, 0.15585856139659882, 0.2501833736896515], "policy_updates": 36660, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6451.202324893, "contact_bce": 0.31599587202072144, "contact_force_loss": 0.03280898183584213, "terrain_level_mean": 3.157470703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36770, "total_transitions": 150609920, "num_steps_per_env": 1, "wm_loss": 0.46588167548179626, "actor_loss": -8.761067390441895, "critic_loss": 0.018749265000224113, "reward": 0.07136284559965134, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24475035071372986, 0.15440291166305542, 0.2498057335615158], "policy_updates": 36670, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6454.713540362, "contact_bce": 0.32685354351997375, "contact_force_loss": 0.03363865986466408, "terrain_level_mean": 3.15869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36780, "total_transitions": 150650880, "num_steps_per_env": 1, "wm_loss": 0.47010737657546997, "actor_loss": -8.783687591552734, "critic_loss": 0.025590527802705765, "reward": 0.07143919169902802, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24273374676704407, 0.15677344799041748, 0.251557856798172], "policy_updates": 36680, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6458.22631553, "contact_bce": 0.3149048984050751, "contact_force_loss": 0.033158887177705765, "terrain_level_mean": 3.158935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36790, "total_transitions": 150691840, "num_steps_per_env": 1, "wm_loss": 0.4760906398296356, "actor_loss": -8.698182106018066, "critic_loss": 0.02653486095368862, "reward": 0.07143640518188477, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24455909430980682, 0.1569528579711914, 0.25001055002212524], "policy_updates": 36690, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6461.736144312999, "contact_bce": 0.31605371832847595, "contact_force_loss": 0.032812971621751785, "terrain_level_mean": 3.1591796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9916517734527588, 0.9996211528778076, 2.9989352226257324]} {"step": 36800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36800, "total_transitions": 150732800, "num_steps_per_env": 1, "wm_loss": 0.4456927180290222, "actor_loss": -8.791976928710938, "critic_loss": 0.02211890183389187, "reward": 0.07122092694044113, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24524584412574768, 0.15830419957637787, 0.2517261207103729], "policy_updates": 36700, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6465.245472082, "contact_bce": 0.3118192255496979, "contact_force_loss": 0.032328780740499496, "terrain_level_mean": 3.158935546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9916517734527588, 0.9998733997344971, 2.9989352226257324]} {"step": 36810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36810, "total_transitions": 150773760, "num_steps_per_env": 1, "wm_loss": 0.4476251006126404, "actor_loss": -8.776254653930664, "critic_loss": 0.0205371230840683, "reward": 0.07040882110595703, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24912624061107635, 0.1603209674358368, 0.25642773509025574], "policy_updates": 36710, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6468.756245604, "contact_bce": 0.3231425881385803, "contact_force_loss": 0.03255746141076088, "terrain_level_mean": 3.15869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9916517734527588, 0.9998733997344971, 2.9989352226257324]} {"step": 36820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36820, "total_transitions": 150814720, "num_steps_per_env": 1, "wm_loss": 0.4563332200050354, "actor_loss": -8.699601173400879, "critic_loss": 0.02303280495107174, "reward": 0.07035309821367264, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24584408104419708, 0.161232590675354, 0.2527201175689697], "policy_updates": 36720, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6472.2718464439995, "contact_bce": 0.31451186537742615, "contact_force_loss": 0.032528940588235855, "terrain_level_mean": 3.159423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9933576583862305, 0.9998733997344971, 2.9989352226257324]} {"step": 36830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36830, "total_transitions": 150855680, "num_steps_per_env": 1, "wm_loss": 0.4596380889415741, "actor_loss": -8.733047485351562, "critic_loss": 0.022141097113490105, "reward": 0.07091277837753296, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24251149594783783, 0.15887665748596191, 0.25137484073638916], "policy_updates": 36730, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6475.777995832999, "contact_bce": 0.3179420530796051, "contact_force_loss": 0.03274761512875557, "terrain_level_mean": 3.159423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9933576583862305, 0.9998733997344971, 2.9989352226257324]} {"step": 36840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36840, "total_transitions": 150896640, "num_steps_per_env": 1, "wm_loss": 0.41189172863960266, "actor_loss": -8.765439987182617, "critic_loss": 0.02851550094783306, "reward": 0.07088489830493927, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2450728863477707, 0.1575908213853836, 0.2551581561565399], "policy_updates": 36740, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6479.293372325, "contact_bce": 0.31421971321105957, "contact_force_loss": 0.032044652849435806, "terrain_level_mean": 3.160400390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9933576583862305, 0.9998733997344971, 2.9989352226257324]} {"step": 36850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36850, "total_transitions": 150937600, "num_steps_per_env": 1, "wm_loss": 0.4577297866344452, "actor_loss": -8.781702995300293, "critic_loss": 0.03070036880671978, "reward": 0.07069084793329239, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24727003276348114, 0.15883849561214447, 0.2541092038154602], "policy_updates": 36750, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6482.800096096, "contact_bce": 0.3189803659915924, "contact_force_loss": 0.031536709517240524, "terrain_level_mean": 3.159912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9933576583862305, 0.9998733997344971, 2.9975473880767822]} {"step": 36860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36860, "total_transitions": 150978560, "num_steps_per_env": 1, "wm_loss": 0.4711647629737854, "actor_loss": -8.720121383666992, "critic_loss": 0.0334564633667469, "reward": 0.07064075767993927, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2508879005908966, 0.15757156908512115, 0.2572079598903656], "policy_updates": 36760, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6486.306356391, "contact_bce": 0.31765180826187134, "contact_force_loss": 0.0331268347799778, "terrain_level_mean": 3.1611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9936103820800781, 0.9998733997344971, 2.9975473880767822]} {"step": 36870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36870, "total_transitions": 151019520, "num_steps_per_env": 1, "wm_loss": 0.44581836462020874, "actor_loss": -8.757574081420898, "critic_loss": 0.030629372224211693, "reward": 0.07019125670194626, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2522224485874176, 0.15904609858989716, 0.26227089762687683], "policy_updates": 36770, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6489.813030767999, "contact_bce": 0.3145795464515686, "contact_force_loss": 0.0328357107937336, "terrain_level_mean": 3.16162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355712890625, "command_abs_max": [1.9941325187683105, 0.9998733997344971, 2.9975473880767822]} {"step": 36880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36880, "total_transitions": 151060480, "num_steps_per_env": 1, "wm_loss": 0.43338119983673096, "actor_loss": -8.739730834960938, "critic_loss": 0.026346826925873756, "reward": 0.07018565386533737, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2524551749229431, 0.16249579191207886, 0.26148366928100586], "policy_updates": 36780, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6493.313929209, "contact_bce": 0.31171488761901855, "contact_force_loss": 0.03210828825831413, "terrain_level_mean": 3.16162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.9941325187683105, 0.9998733997344971, 2.9975473880767822]} {"step": 36890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36890, "total_transitions": 151101440, "num_steps_per_env": 1, "wm_loss": 0.45618075132369995, "actor_loss": -8.721044540405273, "critic_loss": 0.02447056956589222, "reward": 0.0704089030623436, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25415119528770447, 0.162421315908432, 0.261322021484375], "policy_updates": 36790, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6496.811723860999, "contact_bce": 0.32021263241767883, "contact_force_loss": 0.03246168792247772, "terrain_level_mean": 3.160888671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.9941325187683105, 0.9998733997344971, 2.9975473880767822]} {"step": 36900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36900, "total_transitions": 151142400, "num_steps_per_env": 1, "wm_loss": 0.46797728538513184, "actor_loss": -8.74483871459961, "critic_loss": 0.024827463552355766, "reward": 0.07013845443725586, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2528154253959656, 0.16089856624603271, 0.25963759422302246], "policy_updates": 36800, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6500.311866016999, "contact_bce": 0.32111886143684387, "contact_force_loss": 0.032987356185913086, "terrain_level_mean": 3.15966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3583984375, "command_abs_max": [1.9989585876464844, 0.9998733997344971, 2.9975473880767822]} {"step": 36910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36910, "total_transitions": 151183360, "num_steps_per_env": 1, "wm_loss": 0.45577168464660645, "actor_loss": -8.728617668151855, "critic_loss": 0.02551647089421749, "reward": 0.07050593942403793, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2518756091594696, 0.1608263999223709, 0.2584155201911926], "policy_updates": 36810, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6503.833103655999, "contact_bce": 0.31772714853286743, "contact_force_loss": 0.03256520628929138, "terrain_level_mean": 3.16015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9989585876464844, 0.9998733997344971, 2.9975473880767822]} {"step": 36920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36920, "total_transitions": 151224320, "num_steps_per_env": 1, "wm_loss": 0.45728227496147156, "actor_loss": -8.721738815307617, "critic_loss": 0.026557160541415215, "reward": 0.07084455341100693, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2534322142601013, 0.16214631497859955, 0.257068008184433], "policy_updates": 36820, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6507.335542559, "contact_bce": 0.3139803409576416, "contact_force_loss": 0.031432636082172394, "terrain_level_mean": 3.16064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9989585876464844, 0.9998733997344971, 2.9975473880767822]} {"step": 36930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36930, "total_transitions": 151265280, "num_steps_per_env": 1, "wm_loss": 0.4684258997440338, "actor_loss": -8.742288589477539, "critic_loss": 0.023119930177927017, "reward": 0.07061723619699478, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2517513632774353, 0.16117963194847107, 0.25630444288253784], "policy_updates": 36830, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6510.835369413, "contact_bce": 0.32059288024902344, "contact_force_loss": 0.03220146521925926, "terrain_level_mean": 3.160400390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3603515625, "command_abs_max": [1.9989585876464844, 0.9998733997344971, 2.9975473880767822]} {"step": 36940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36940, "total_transitions": 151306240, "num_steps_per_env": 1, "wm_loss": 0.4460940957069397, "actor_loss": -8.789852142333984, "critic_loss": 0.026194561272859573, "reward": 0.07082732021808624, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24979591369628906, 0.16111624240875244, 0.2604617476463318], "policy_updates": 36840, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6514.336598762, "contact_bce": 0.3203504681587219, "contact_force_loss": 0.03232986479997635, "terrain_level_mean": 3.15869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358642578125, "command_abs_max": [1.9989585876464844, 0.9998733997344971, 2.999157428741455]} {"step": 36950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36950, "total_transitions": 151347200, "num_steps_per_env": 1, "wm_loss": 0.4510806202888489, "actor_loss": -8.772568702697754, "critic_loss": 0.021847866475582123, "reward": 0.07117720693349838, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24443233013153076, 0.15749835968017578, 0.2603122591972351], "policy_updates": 36850, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6517.835007279, "contact_bce": 0.3158465623855591, "contact_force_loss": 0.03224159777164459, "terrain_level_mean": 3.157470703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9989585876464844, 0.9998733997344971, 2.999157428741455]} {"step": 36960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36960, "total_transitions": 151388160, "num_steps_per_env": 1, "wm_loss": 0.4552510976791382, "actor_loss": -8.78122615814209, "critic_loss": 0.022067980840802193, "reward": 0.07163321226835251, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24501381814479828, 0.1534660905599594, 0.25373905897140503], "policy_updates": 36860, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6521.330564018999, "contact_bce": 0.31878089904785156, "contact_force_loss": 0.032389573752880096, "terrain_level_mean": 3.158447265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9989585876464844, 0.9990882277488708, 2.999157428741455]} {"step": 36970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36970, "total_transitions": 151429120, "num_steps_per_env": 1, "wm_loss": 0.4473689794540405, "actor_loss": -8.742079734802246, "critic_loss": 0.022244591265916824, "reward": 0.07107692956924438, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24546529352664948, 0.15519578754901886, 0.25360217690467834], "policy_updates": 36870, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6524.828314122, "contact_bce": 0.3231049180030823, "contact_force_loss": 0.03363576531410217, "terrain_level_mean": 3.15869140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9989585876464844, 0.9990882277488708, 2.999157428741455]} {"step": 36980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36980, "total_transitions": 151470080, "num_steps_per_env": 1, "wm_loss": 0.4049755036830902, "actor_loss": -8.735123634338379, "critic_loss": 0.025752587243914604, "reward": 0.0709775984287262, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2460051029920578, 0.15450534224510193, 0.25702208280563354], "policy_updates": 36880, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6528.328694461, "contact_bce": 0.3101676404476166, "contact_force_loss": 0.03194129467010498, "terrain_level_mean": 3.159423828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.9989585876464844, 0.9990882277488708, 2.999157428741455]} {"step": 36990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 36990, "total_transitions": 151511040, "num_steps_per_env": 1, "wm_loss": 0.43043214082717896, "actor_loss": -8.645713806152344, "critic_loss": 0.025353794917464256, "reward": 0.07076718658208847, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25297820568084717, 0.15661512315273285, 0.26036393642425537], "policy_updates": 36890, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6531.841002722, "contact_bce": 0.3141697347164154, "contact_force_loss": 0.03227236494421959, "terrain_level_mean": 3.159912109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9989585876464844, 0.9990882277488708, 2.999157428741455]} {"step": 37000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37000, "total_transitions": 151552000, "num_steps_per_env": 1, "wm_loss": 0.45313647389411926, "actor_loss": -8.72891902923584, "critic_loss": 0.035107970237731934, "reward": 0.07104207575321198, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2528810501098633, 0.15751558542251587, 0.2554231882095337], "policy_updates": 36900, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6535.353832297, "contact_bce": 0.3174009919166565, "contact_force_loss": 0.03352285921573639, "terrain_level_mean": 3.1591796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9989585876464844, 0.9992738962173462, 2.999157428741455]} {"step": 37010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37010, "total_transitions": 151592960, "num_steps_per_env": 1, "wm_loss": 0.493668794631958, "actor_loss": -8.7616605758667, "critic_loss": 0.022373352199792862, "reward": 0.07127957791090012, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2517469823360443, 0.15692967176437378, 0.2591925859451294], "policy_updates": 36910, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6538.896358213, "contact_bce": 0.3145419955253601, "contact_force_loss": 0.03213118389248848, "terrain_level_mean": 3.16162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.9989585876464844, 0.9992738962173462, 2.999157428741455]} {"step": 37020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37020, "total_transitions": 151633920, "num_steps_per_env": 1, "wm_loss": 0.45010656118392944, "actor_loss": -8.77145767211914, "critic_loss": 0.03010421432554722, "reward": 0.07112450897693634, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2438362091779709, 0.1599324345588684, 0.26088088750839233], "policy_updates": 36920, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6542.413165121, "contact_bce": 0.31527283787727356, "contact_force_loss": 0.03195517137646675, "terrain_level_mean": 3.16162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35986328125, "command_abs_max": [1.9989585876464844, 0.9992738962173462, 2.999157428741455]} {"step": 37030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37030, "total_transitions": 151674880, "num_steps_per_env": 1, "wm_loss": 0.4486368000507355, "actor_loss": -8.735189437866211, "critic_loss": 0.024801155552268028, "reward": 0.0714091882109642, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2443881332874298, 0.16048750281333923, 0.2570968270301819], "policy_updates": 36930, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6546.182994109, "contact_bce": 0.31685400009155273, "contact_force_loss": 0.03266953304409981, "terrain_level_mean": 3.161376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.9989585876464844, 0.9992738962173462, 2.999157428741455]} {"step": 37040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37040, "total_transitions": 151715840, "num_steps_per_env": 1, "wm_loss": 0.49239403009414673, "actor_loss": -8.715914726257324, "critic_loss": 0.03447927162051201, "reward": 0.07099439948797226, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2503877580165863, 0.1616806536912918, 0.25797733664512634], "policy_updates": 36940, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6549.694613537999, "contact_bce": 0.3219870924949646, "contact_force_loss": 0.033106379210948944, "terrain_level_mean": 3.1611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9989585876464844, 0.9992738962173462, 2.999157428741455]} {"step": 37050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37050, "total_transitions": 151756800, "num_steps_per_env": 1, "wm_loss": 0.4623294770717621, "actor_loss": -8.713321685791016, "critic_loss": 0.031030410900712013, "reward": 0.0708189308643341, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2544581890106201, 0.16115142405033112, 0.2560066282749176], "policy_updates": 36950, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6553.210033529, "contact_bce": 0.31356826424598694, "contact_force_loss": 0.032534100115299225, "terrain_level_mean": 3.16064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9989585876464844, 0.9992738962173462, 2.999157428741455]} {"step": 37060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37060, "total_transitions": 151797760, "num_steps_per_env": 1, "wm_loss": 0.45073455572128296, "actor_loss": -8.740243911743164, "critic_loss": 0.02169114537537098, "reward": 0.07069344073534012, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24866265058517456, 0.16004109382629395, 0.2542036473751068], "policy_updates": 36960, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6556.722432338, "contact_bce": 0.3177105188369751, "contact_force_loss": 0.032710541039705276, "terrain_level_mean": 3.16015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37070, "total_transitions": 151838720, "num_steps_per_env": 1, "wm_loss": 0.4831858277320862, "actor_loss": -8.72445297241211, "critic_loss": 0.03056437335908413, "reward": 0.0710580125451088, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24291309714317322, 0.16015839576721191, 0.2517848610877991], "policy_updates": 36970, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6560.2386257319995, "contact_bce": 0.31272122263908386, "contact_force_loss": 0.03259853273630142, "terrain_level_mean": 3.16064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37080, "total_transitions": 151879680, "num_steps_per_env": 1, "wm_loss": 0.4518433213233948, "actor_loss": -8.727367401123047, "critic_loss": 0.027924919500947, "reward": 0.07105105370283127, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24379096925258636, 0.15979957580566406, 0.2531423270702362], "policy_updates": 36980, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6563.748264598, "contact_bce": 0.3151742219924927, "contact_force_loss": 0.033025819808244705, "terrain_level_mean": 3.160400390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37090, "total_transitions": 151920640, "num_steps_per_env": 1, "wm_loss": 0.45973846316337585, "actor_loss": -8.716063499450684, "critic_loss": 0.02295571006834507, "reward": 0.07109302282333374, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24521753191947937, 0.16025766730308533, 0.2517271637916565], "policy_updates": 36990, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6567.242204554999, "contact_bce": 0.3135078549385071, "contact_force_loss": 0.03323478624224663, "terrain_level_mean": 3.1611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37100, "total_transitions": 151961600, "num_steps_per_env": 1, "wm_loss": 0.4631950557231903, "actor_loss": -8.721345901489258, "critic_loss": 0.023927895352244377, "reward": 0.07062265276908875, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24921414256095886, 0.16270358860492706, 0.2548762261867523], "policy_updates": 37000, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6570.742656181, "contact_bce": 0.31623077392578125, "contact_force_loss": 0.03238921985030174, "terrain_level_mean": 3.162353515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37110, "total_transitions": 152002560, "num_steps_per_env": 1, "wm_loss": 0.4225565493106842, "actor_loss": -8.725439071655273, "critic_loss": 0.029907329007983208, "reward": 0.07090461999177933, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24550911784172058, 0.16402384638786316, 0.2544247508049011], "policy_updates": 37010, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6574.252372532999, "contact_bce": 0.31245869398117065, "contact_force_loss": 0.032665468752384186, "terrain_level_mean": 3.162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37120, "total_transitions": 152043520, "num_steps_per_env": 1, "wm_loss": 0.40965017676353455, "actor_loss": -8.70263385772705, "critic_loss": 0.0320114903151989, "reward": 0.07079573720693588, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24788308143615723, 0.16298285126686096, 0.2576255798339844], "policy_updates": 37020, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6577.749716075, "contact_bce": 0.31606563925743103, "contact_force_loss": 0.03172170743346214, "terrain_level_mean": 3.16259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37130, "total_transitions": 152084480, "num_steps_per_env": 1, "wm_loss": 0.4690137207508087, "actor_loss": -8.769662857055664, "critic_loss": 0.023633359000086784, "reward": 0.0709775909781456, "falls": 10, "interval_steps": 10, "velocity_mae": [0.25098708271980286, 0.1613749861717224, 0.2543693780899048], "policy_updates": 37030, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6581.2441452289995, "contact_bce": 0.3137655556201935, "contact_force_loss": 0.03280745819211006, "terrain_level_mean": 3.1611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37140, "total_transitions": 152125440, "num_steps_per_env": 1, "wm_loss": 0.4566539227962494, "actor_loss": -8.74039363861084, "critic_loss": 0.03019622527062893, "reward": 0.07124022394418716, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24964091181755066, 0.15988530218601227, 0.25346839427948], "policy_updates": 37040, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6584.741064625, "contact_bce": 0.3184655010700226, "contact_force_loss": 0.03236798197031021, "terrain_level_mean": 3.16064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37150, "total_transitions": 152166400, "num_steps_per_env": 1, "wm_loss": 0.4625140428543091, "actor_loss": -8.765172958374023, "critic_loss": 0.04008894041180611, "reward": 0.07120435684919357, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2510104179382324, 0.15901271998882294, 0.2530974745750427], "policy_updates": 37050, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6588.238304418999, "contact_bce": 0.3172587454319, "contact_force_loss": 0.033400725573301315, "terrain_level_mean": 3.160888671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.999157428741455]} {"step": 37160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37160, "total_transitions": 152207360, "num_steps_per_env": 1, "wm_loss": 0.4488770365715027, "actor_loss": -8.796344757080078, "critic_loss": 0.02519729547202587, "reward": 0.07100435346364975, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2496679127216339, 0.15891189873218536, 0.2579767405986786], "policy_updates": 37060, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6591.741682348, "contact_bce": 0.31176358461380005, "contact_force_loss": 0.032112639397382736, "terrain_level_mean": 3.161376953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.9975473880767822]} {"step": 37170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37170, "total_transitions": 152248320, "num_steps_per_env": 1, "wm_loss": 0.4338339567184448, "actor_loss": -8.698102951049805, "critic_loss": 0.0294334776699543, "reward": 0.07082396000623703, "falls": 2, "interval_steps": 10, "velocity_mae": [0.253717303276062, 0.1608068346977234, 0.25943663716316223], "policy_updates": 37070, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6595.239643153, "contact_bce": 0.3150855302810669, "contact_force_loss": 0.03233761712908745, "terrain_level_mean": 3.162353515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.9975473880767822]} {"step": 37180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37180, "total_transitions": 152289280, "num_steps_per_env": 1, "wm_loss": 0.4654648005962372, "actor_loss": -8.734511375427246, "critic_loss": 0.029633140191435814, "reward": 0.0708024725317955, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2514529824256897, 0.16014930605888367, 0.26121512055397034], "policy_updates": 37080, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6598.74024628, "contact_bce": 0.3159862160682678, "contact_force_loss": 0.03321428224444389, "terrain_level_mean": 3.1611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.9960222244262695]} {"step": 37190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37190, "total_transitions": 152330240, "num_steps_per_env": 1, "wm_loss": 0.44276002049446106, "actor_loss": -8.773969650268555, "critic_loss": 0.024457423016428947, "reward": 0.07105766981840134, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24752192199230194, 0.1613979935646057, 0.2594414949417114], "policy_updates": 37090, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6602.247545583, "contact_bce": 0.3140629827976227, "contact_force_loss": 0.03204191476106644, "terrain_level_mean": 3.162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.99946928024292, 0.9992738962173462, 2.9960222244262695]} {"step": 37200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37200, "total_transitions": 152371200, "num_steps_per_env": 1, "wm_loss": 0.4578890800476074, "actor_loss": -8.738998413085938, "critic_loss": 0.02547539211809635, "reward": 0.07073792070150375, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24807731807231903, 0.1637551337480545, 0.258924275636673], "policy_updates": 37100, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6605.762757220999, "contact_bce": 0.31277841329574585, "contact_force_loss": 0.03218623995780945, "terrain_level_mean": 3.1630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.99946928024292, 0.9990882277488708, 2.9960222244262695]} {"step": 37210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37210, "total_transitions": 152412160, "num_steps_per_env": 1, "wm_loss": 0.43704134225845337, "actor_loss": -8.746212005615234, "critic_loss": 0.026444843038916588, "reward": 0.07076140493154526, "falls": 11, "interval_steps": 10, "velocity_mae": [0.2498716115951538, 0.16078531742095947, 0.25575000047683716], "policy_updates": 37110, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6609.284070203, "contact_bce": 0.3156644105911255, "contact_force_loss": 0.03248339146375656, "terrain_level_mean": 3.162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.99946928024292, 0.99849534034729, 2.9960222244262695]} {"step": 37220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37220, "total_transitions": 152453120, "num_steps_per_env": 1, "wm_loss": 0.45940127968788147, "actor_loss": -8.732566833496094, "critic_loss": 0.03451303392648697, "reward": 0.07097947597503662, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24564138054847717, 0.15818841755390167, 0.25820261240005493], "policy_updates": 37120, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6612.800482916, "contact_bce": 0.31811684370040894, "contact_force_loss": 0.03448232635855675, "terrain_level_mean": 3.16259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.99946928024292, 0.99849534034729, 2.9960222244262695]} {"step": 37230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37230, "total_transitions": 152494080, "num_steps_per_env": 1, "wm_loss": 0.40788817405700684, "actor_loss": -8.754751205444336, "critic_loss": 0.03135829046368599, "reward": 0.07133075594902039, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24140247702598572, 0.15759778022766113, 0.2578791379928589], "policy_updates": 37130, "skipped_updates": 0, "invalid_env_resets": 58, "elapsed_s": 6616.315737934, "contact_bce": 0.31289762258529663, "contact_force_loss": 0.03228488191962242, "terrain_level_mean": 3.162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.99946928024292, 0.99849534034729, 2.9960222244262695]} RECOVERY reset 1 invalid environments; first IDs=[657] {"step": 37240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37240, "total_transitions": 152535040, "num_steps_per_env": 1, "wm_loss": 0.45615527033805847, "actor_loss": -8.746366500854492, "critic_loss": 0.028416967019438744, "reward": 0.07113932073116302, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24852123856544495, 0.1579241007566452, 0.2563023269176483], "policy_updates": 37140, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6619.843777958, "contact_bce": 0.31867483258247375, "contact_force_loss": 0.033063676208257675, "terrain_level_mean": 3.1630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.99946928024292, 0.99849534034729, 2.9960222244262695]} {"step": 37250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37250, "total_transitions": 152576000, "num_steps_per_env": 1, "wm_loss": 0.4791547656059265, "actor_loss": -8.749610900878906, "critic_loss": 0.022194495424628258, "reward": 0.07088121771812439, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24923215806484222, 0.16151779890060425, 0.25689825415611267], "policy_updates": 37150, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6623.366720821, "contact_bce": 0.3138892352581024, "contact_force_loss": 0.032651498913764954, "terrain_level_mean": 3.162841796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9980599880218506, 0.99849534034729, 2.9960222244262695]} {"step": 37260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37260, "total_transitions": 152616960, "num_steps_per_env": 1, "wm_loss": 0.43986746668815613, "actor_loss": -8.7222900390625, "critic_loss": 0.02784036472439766, "reward": 0.07095431536436081, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24699972569942474, 0.15974532067775726, 0.25397491455078125], "policy_updates": 37160, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6626.874226708999, "contact_bce": 0.3160547614097595, "contact_force_loss": 0.03317161649465561, "terrain_level_mean": 3.162353515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9957189559936523, 0.99849534034729, 2.9960222244262695]} {"step": 37270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37270, "total_transitions": 152657920, "num_steps_per_env": 1, "wm_loss": 0.4388103485107422, "actor_loss": -8.775897026062012, "critic_loss": 0.021633313968777657, "reward": 0.07124011963605881, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24556684494018555, 0.15983757376670837, 0.2520807683467865], "policy_updates": 37170, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6630.400392132, "contact_bce": 0.31248337030410767, "contact_force_loss": 0.03251614421606064, "terrain_level_mean": 3.162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9957189559936523, 0.99849534034729, 2.9960222244262695]} {"step": 37280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37280, "total_transitions": 152698880, "num_steps_per_env": 1, "wm_loss": 0.4545474946498871, "actor_loss": -8.727649688720703, "critic_loss": 0.03294868394732475, "reward": 0.07145316898822784, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24133330583572388, 0.15773867070674896, 0.2544580399990082], "policy_updates": 37180, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6633.9082148709995, "contact_bce": 0.3214457035064697, "contact_force_loss": 0.03312821686267853, "terrain_level_mean": 3.162841796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9970157146453857, 0.99849534034729, 2.9960222244262695]} {"step": 37290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37290, "total_transitions": 152739840, "num_steps_per_env": 1, "wm_loss": 0.46643683314323425, "actor_loss": -8.708744049072266, "critic_loss": 0.029599491506814957, "reward": 0.07173279672861099, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2417241483926773, 0.15953423082828522, 0.25217190384864807], "policy_updates": 37190, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6637.432406258999, "contact_bce": 0.3228861093521118, "contact_force_loss": 0.03327416256070137, "terrain_level_mean": 3.163330078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9970157146453857, 0.99849534034729, 2.9960222244262695]} {"step": 37300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37300, "total_transitions": 152780800, "num_steps_per_env": 1, "wm_loss": 0.4375876486301422, "actor_loss": -8.722413063049316, "critic_loss": 0.029760882258415222, "reward": 0.07169739902019501, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24455998837947845, 0.15919844806194305, 0.25519660115242004], "policy_updates": 37200, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6640.953991906, "contact_bce": 0.3199484050273895, "contact_force_loss": 0.03292308375239372, "terrain_level_mean": 3.163330078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9970157146453857, 0.99849534034729, 2.9960222244262695]} {"step": 37310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37310, "total_transitions": 152821760, "num_steps_per_env": 1, "wm_loss": 0.45616385340690613, "actor_loss": -8.712358474731445, "critic_loss": 0.027209773659706116, "reward": 0.07135609537363052, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24641738831996918, 0.15828001499176025, 0.2537548542022705], "policy_updates": 37210, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6644.468477519999, "contact_bce": 0.3186677396297455, "contact_force_loss": 0.03296339511871338, "terrain_level_mean": 3.162841796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9970157146453857, 0.99849534034729, 2.9964003562927246]} {"step": 37320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37320, "total_transitions": 152862720, "num_steps_per_env": 1, "wm_loss": 0.47312846779823303, "actor_loss": -8.743182182312012, "critic_loss": 0.02588818408548832, "reward": 0.07137725502252579, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2450881153345108, 0.1578759253025055, 0.25570985674858093], "policy_updates": 37220, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6647.978787364, "contact_bce": 0.3201523423194885, "contact_force_loss": 0.0326518788933754, "terrain_level_mean": 3.163818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9970157146453857, 0.9989224672317505, 2.9964003562927246]} {"step": 37330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37330, "total_transitions": 152903680, "num_steps_per_env": 1, "wm_loss": 0.45219844579696655, "actor_loss": -8.727415084838867, "critic_loss": 0.03180504962801933, "reward": 0.07155024260282516, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24702376127243042, 0.15835346281528473, 0.25272077322006226], "policy_updates": 37230, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6651.496653093, "contact_bce": 0.3160451352596283, "contact_force_loss": 0.03269660472869873, "terrain_level_mean": 3.16455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9970157146453857, 0.9989224672317505, 2.9964003562927246]} {"step": 37340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37340, "total_transitions": 152944640, "num_steps_per_env": 1, "wm_loss": 0.41937607526779175, "actor_loss": -8.674481391906738, "critic_loss": 0.032685551792383194, "reward": 0.07151187211275101, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24559439718723297, 0.15768401324748993, 0.25319018959999084], "policy_updates": 37240, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6655.005941486, "contact_bce": 0.3138183057308197, "contact_force_loss": 0.03237386792898178, "terrain_level_mean": 3.1630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9970157146453857, 0.9989224672317505, 2.9964003562927246]} {"step": 37350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37350, "total_transitions": 152985600, "num_steps_per_env": 1, "wm_loss": 0.44431987404823303, "actor_loss": -8.679830551147461, "critic_loss": 0.03520866110920906, "reward": 0.070985808968544, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24721162021160126, 0.15925033390522003, 0.2548493444919586], "policy_updates": 37250, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6658.5174968189995, "contact_bce": 0.31750670075416565, "contact_force_loss": 0.0326419435441494, "terrain_level_mean": 3.1650390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9957189559936523, 0.9989224672317505, 2.9964003562927246]} {"step": 37360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37360, "total_transitions": 153026560, "num_steps_per_env": 1, "wm_loss": 0.4209296405315399, "actor_loss": -8.702086448669434, "critic_loss": 0.021689703688025475, "reward": 0.07076167315244675, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2525022029876709, 0.15882538259029388, 0.2542087137699127], "policy_updates": 37260, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6662.038993546999, "contact_bce": 0.317006379365921, "contact_force_loss": 0.03243513032793999, "terrain_level_mean": 3.1650390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9959100484848022, 0.9989224672317505, 2.9964003562927246]} {"step": 37370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37370, "total_transitions": 153067520, "num_steps_per_env": 1, "wm_loss": 0.48445406556129456, "actor_loss": -8.69020938873291, "critic_loss": 0.023272434249520302, "reward": 0.07058785110712051, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2494412213563919, 0.15661965310573578, 0.25503894686698914], "policy_updates": 37270, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6665.561729641, "contact_bce": 0.32011163234710693, "contact_force_loss": 0.03404122591018677, "terrain_level_mean": 3.16552734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9959100484848022, 0.9989224672317505, 2.9964003562927246]} {"step": 37380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37380, "total_transitions": 153108480, "num_steps_per_env": 1, "wm_loss": 0.46247702836990356, "actor_loss": -8.673212051391602, "critic_loss": 0.030263710767030716, "reward": 0.07074656337499619, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24451075494289398, 0.15790380537509918, 0.25705549120903015], "policy_updates": 37280, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6669.089990191999, "contact_bce": 0.3086075186729431, "contact_force_loss": 0.03256558999419212, "terrain_level_mean": 3.1669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.9959100484848022, 0.9989224672317505, 2.9964003562927246]} {"step": 37390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37390, "total_transitions": 153149440, "num_steps_per_env": 1, "wm_loss": 0.42346176505088806, "actor_loss": -8.757096290588379, "critic_loss": 0.025260401889681816, "reward": 0.07035909593105316, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24296602606773376, 0.15772561728954315, 0.2557450532913208], "policy_updates": 37290, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6672.610007550999, "contact_bce": 0.3173029124736786, "contact_force_loss": 0.03258027136325836, "terrain_level_mean": 3.16796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9960685968399048, 0.9989224672317505, 2.9964003562927246]} {"step": 37400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37400, "total_transitions": 153190400, "num_steps_per_env": 1, "wm_loss": 0.4545363485813141, "actor_loss": -8.765961647033691, "critic_loss": 0.01923440769314766, "reward": 0.07048358023166656, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24412094056606293, 0.15675179660320282, 0.2560417056083679], "policy_updates": 37300, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6676.129803252, "contact_bce": 0.31687891483306885, "contact_force_loss": 0.032511040568351746, "terrain_level_mean": 3.16796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9960685968399048, 0.9989224672317505, 2.9964003562927246]} {"step": 37410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37410, "total_transitions": 153231360, "num_steps_per_env": 1, "wm_loss": 0.43266788125038147, "actor_loss": -8.69998836517334, "critic_loss": 0.02520771324634552, "reward": 0.07039161771535873, "falls": 3, "interval_steps": 10, "velocity_mae": [0.247639000415802, 0.15836483240127563, 0.25404098629951477], "policy_updates": 37310, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6679.6604591039995, "contact_bce": 0.31204164028167725, "contact_force_loss": 0.032617297023534775, "terrain_level_mean": 3.168212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9978406429290771, 0.9989224672317505, 2.9964003562927246]} {"step": 37420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37420, "total_transitions": 153272320, "num_steps_per_env": 1, "wm_loss": 0.46505290269851685, "actor_loss": -8.760701179504395, "critic_loss": 0.025737065821886063, "reward": 0.0704098716378212, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24561281502246857, 0.16013787686824799, 0.25182265043258667], "policy_updates": 37320, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6683.178553686999, "contact_bce": 0.31719234585762024, "contact_force_loss": 0.033298615366220474, "terrain_level_mean": 3.167236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.9978406429290771, 0.9989224672317505, 2.9964003562927246]} {"step": 37430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37430, "total_transitions": 153313280, "num_steps_per_env": 1, "wm_loss": 0.4249393045902252, "actor_loss": -8.714695930480957, "critic_loss": 0.026731867343187332, "reward": 0.07014813274145126, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24630962312221527, 0.15945491194725037, 0.25431618094444275], "policy_updates": 37330, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6686.691764272, "contact_bce": 0.3155914545059204, "contact_force_loss": 0.03142118081450462, "terrain_level_mean": 3.16552734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9978406429290771, 0.9989224672317505, 2.9964003562927246]} {"step": 37440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37440, "total_transitions": 153354240, "num_steps_per_env": 1, "wm_loss": 0.4195535182952881, "actor_loss": -8.729663848876953, "critic_loss": 0.028169184923171997, "reward": 0.07077061384916306, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24386104941368103, 0.15783505141735077, 0.25414881110191345], "policy_updates": 37340, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6690.216141723, "contact_bce": 0.31402209401130676, "contact_force_loss": 0.03229455649852753, "terrain_level_mean": 3.16650390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.360107421875, "command_abs_max": [1.9978406429290771, 0.9989224672317505, 2.9964003562927246]} {"step": 37450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37450, "total_transitions": 153395200, "num_steps_per_env": 1, "wm_loss": 0.4397205114364624, "actor_loss": -8.709213256835938, "critic_loss": 0.028025437146425247, "reward": 0.07077611237764359, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24383297562599182, 0.15825381875038147, 0.2554577589035034], "policy_updates": 37350, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6693.738552452, "contact_bce": 0.3185460567474365, "contact_force_loss": 0.032803092151880264, "terrain_level_mean": 3.1669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361083984375, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37460, "total_transitions": 153436160, "num_steps_per_env": 1, "wm_loss": 0.43834033608436584, "actor_loss": -8.766426086425781, "critic_loss": 0.03247823193669319, "reward": 0.07076001912355423, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24572376906871796, 0.15615512430667877, 0.25203725695610046], "policy_updates": 37360, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6697.262690945, "contact_bce": 0.3120780885219574, "contact_force_loss": 0.03286745026707649, "terrain_level_mean": 3.1669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359130859375, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37470, "total_transitions": 153477120, "num_steps_per_env": 1, "wm_loss": 0.4488804340362549, "actor_loss": -8.695741653442383, "critic_loss": 0.024576997384428978, "reward": 0.07089904695749283, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24804869294166565, 0.15396073460578918, 0.25301527976989746], "policy_updates": 37370, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6700.785442384, "contact_bce": 0.3200800120830536, "contact_force_loss": 0.03285424783825874, "terrain_level_mean": 3.166259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36181640625, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37480, "total_transitions": 153518080, "num_steps_per_env": 1, "wm_loss": 0.41993460059165955, "actor_loss": -8.696268081665039, "critic_loss": 0.025976264849305153, "reward": 0.07080339640378952, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24874334037303925, 0.15510165691375732, 0.2527540624141693], "policy_updates": 37380, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6704.306147505999, "contact_bce": 0.3183883726596832, "contact_force_loss": 0.03170126676559448, "terrain_level_mean": 3.166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.360595703125, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37490, "total_transitions": 153559040, "num_steps_per_env": 1, "wm_loss": 0.4357597529888153, "actor_loss": -8.704344749450684, "critic_loss": 0.02516125701367855, "reward": 0.07089044898748398, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2483971118927002, 0.15725478529930115, 0.25509965419769287], "policy_updates": 37390, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6707.833509618, "contact_bce": 0.31317219138145447, "contact_force_loss": 0.03170989826321602, "terrain_level_mean": 3.16552734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37500, "total_transitions": 153600000, "num_steps_per_env": 1, "wm_loss": 0.42818009853363037, "actor_loss": -8.677550315856934, "critic_loss": 0.03352430462837219, "reward": 0.07070233672857285, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25159040093421936, 0.15837669372558594, 0.25330716371536255], "policy_updates": 37400, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6711.359224696, "contact_bce": 0.31531423330307007, "contact_force_loss": 0.03188226744532585, "terrain_level_mean": 3.165283203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3583984375, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37510, "total_transitions": 153640960, "num_steps_per_env": 1, "wm_loss": 0.4265112578868866, "actor_loss": -8.754679679870605, "critic_loss": 0.023105155676603317, "reward": 0.07083497941493988, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24878838658332825, 0.15749488770961761, 0.25529229640960693], "policy_updates": 37410, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6714.897692607, "contact_bce": 0.31144341826438904, "contact_force_loss": 0.03124537132680416, "terrain_level_mean": 3.1650390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35888671875, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37520, "total_transitions": 153681920, "num_steps_per_env": 1, "wm_loss": 0.4457433521747589, "actor_loss": -8.72293758392334, "critic_loss": 0.022330092266201973, "reward": 0.07130756229162216, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2436191588640213, 0.15720032155513763, 0.25456729531288147], "policy_updates": 37420, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6718.409849647, "contact_bce": 0.3184479773044586, "contact_force_loss": 0.03290371596813202, "terrain_level_mean": 3.16552734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358642578125, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37530, "total_transitions": 153722880, "num_steps_per_env": 1, "wm_loss": 0.425932914018631, "actor_loss": -8.727851867675781, "critic_loss": 0.03054131381213665, "reward": 0.07136806100606918, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2409525215625763, 0.1599634438753128, 0.253180593252182], "policy_updates": 37430, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6722.1847365779995, "contact_bce": 0.312978595495224, "contact_force_loss": 0.031771764159202576, "terrain_level_mean": 3.16650390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3583984375, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37540, "total_transitions": 153763840, "num_steps_per_env": 1, "wm_loss": 0.436323881149292, "actor_loss": -8.736059188842773, "critic_loss": 0.020201554521918297, "reward": 0.0705333948135376, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24102330207824707, 0.16230346262454987, 0.2549951374530792], "policy_updates": 37440, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6725.708230931, "contact_bce": 0.3172779977321625, "contact_force_loss": 0.03260395675897598, "terrain_level_mean": 3.166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37550, "total_transitions": 153804800, "num_steps_per_env": 1, "wm_loss": 0.4468306005001068, "actor_loss": -8.701887130737305, "critic_loss": 0.01969183422625065, "reward": 0.07035179436206818, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2440081089735031, 0.16186805069446564, 0.25835877656936646], "policy_updates": 37450, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6729.223859924, "contact_bce": 0.3158271610736847, "contact_force_loss": 0.03283769637346268, "terrain_level_mean": 3.165283203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37560, "total_transitions": 153845760, "num_steps_per_env": 1, "wm_loss": 0.4525682330131531, "actor_loss": -8.79664134979248, "critic_loss": 0.019263049587607384, "reward": 0.07028830796480179, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24971003830432892, 0.16311432421207428, 0.2589583694934845], "policy_updates": 37460, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6732.735330412, "contact_bce": 0.31985488533973694, "contact_force_loss": 0.032119929790496826, "terrain_level_mean": 3.166748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37570, "total_transitions": 153886720, "num_steps_per_env": 1, "wm_loss": 0.45028960704803467, "actor_loss": -8.733026504516602, "critic_loss": 0.028848934918642044, "reward": 0.07065249979496002, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25033143162727356, 0.1591280996799469, 0.25773945450782776], "policy_updates": 37470, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6736.246961332, "contact_bce": 0.3155064284801483, "contact_force_loss": 0.032891228795051575, "terrain_level_mean": 3.166748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37580, "total_transitions": 153927680, "num_steps_per_env": 1, "wm_loss": 0.43804624676704407, "actor_loss": -8.768214225769043, "critic_loss": 0.02476688288152218, "reward": 0.07034318894147873, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2487296313047409, 0.15638424456119537, 0.25705718994140625], "policy_updates": 37480, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6739.761850377, "contact_bce": 0.3117518723011017, "contact_force_loss": 0.0326700322329998, "terrain_level_mean": 3.165771484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37590, "total_transitions": 153968640, "num_steps_per_env": 1, "wm_loss": 0.4367271661758423, "actor_loss": -8.733210563659668, "critic_loss": 0.033777978271245956, "reward": 0.0702577605843544, "falls": 14, "interval_steps": 10, "velocity_mae": [0.247579425573349, 0.15458983182907104, 0.2552328407764435], "policy_updates": 37490, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6743.2835962419995, "contact_bce": 0.3164069354534149, "contact_force_loss": 0.032308049499988556, "terrain_level_mean": 3.16357421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37600, "total_transitions": 154009600, "num_steps_per_env": 1, "wm_loss": 0.45394811034202576, "actor_loss": -8.7353515625, "critic_loss": 0.026120508089661598, "reward": 0.07063032686710358, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24816244840621948, 0.15479393303394318, 0.2535925805568695], "policy_updates": 37500, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6746.807057444, "contact_bce": 0.315639466047287, "contact_force_loss": 0.03309215232729912, "terrain_level_mean": 3.163818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37610, "total_transitions": 154050560, "num_steps_per_env": 1, "wm_loss": 0.43572863936424255, "actor_loss": -8.705672264099121, "critic_loss": 0.029863698408007622, "reward": 0.07055752724409103, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24642515182495117, 0.15673162043094635, 0.25553637742996216], "policy_updates": 37510, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6750.329292197, "contact_bce": 0.3183498680591583, "contact_force_loss": 0.032815851271152496, "terrain_level_mean": 3.163818359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37620, "total_transitions": 154091520, "num_steps_per_env": 1, "wm_loss": 0.46519607305526733, "actor_loss": -8.735313415527344, "critic_loss": 0.023552371188998222, "reward": 0.07118548452854156, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24139495193958282, 0.15589497983455658, 0.25662416219711304], "policy_updates": 37520, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6753.853471279, "contact_bce": 0.3151805102825165, "contact_force_loss": 0.0327107198536396, "terrain_level_mean": 3.166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37630, "total_transitions": 154132480, "num_steps_per_env": 1, "wm_loss": 0.4670826494693756, "actor_loss": -8.706388473510742, "critic_loss": 0.03887512534856796, "reward": 0.07067661732435226, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2441539466381073, 0.15830589830875397, 0.253985196352005], "policy_updates": 37530, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6757.374726984, "contact_bce": 0.31596216559410095, "contact_force_loss": 0.03365187346935272, "terrain_level_mean": 3.16455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9978406429290771, 0.9990699291229248, 2.9964003562927246]} {"step": 37640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37640, "total_transitions": 154173440, "num_steps_per_env": 1, "wm_loss": 0.4549396336078644, "actor_loss": -8.725994110107422, "critic_loss": 0.04028354212641716, "reward": 0.07047796994447708, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24499951303005219, 0.15838739275932312, 0.25543785095214844], "policy_updates": 37540, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6760.896446281, "contact_bce": 0.31990811228752136, "contact_force_loss": 0.03305218741297722, "terrain_level_mean": 3.165283203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9977445602416992, 0.9990699291229248, 2.9964003562927246]} {"step": 37650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37650, "total_transitions": 154214400, "num_steps_per_env": 1, "wm_loss": 0.4340716302394867, "actor_loss": -8.69598388671875, "critic_loss": 0.029843492433428764, "reward": 0.07089149206876755, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24677206575870514, 0.15586522221565247, 0.25259163975715637], "policy_updates": 37550, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6764.414949812, "contact_bce": 0.3221469819545746, "contact_force_loss": 0.03327689692378044, "terrain_level_mean": 3.165771484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9977445602416992, 0.9990699291229248, 2.9964003562927246]} {"step": 37660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37660, "total_transitions": 154255360, "num_steps_per_env": 1, "wm_loss": 0.443643182516098, "actor_loss": -8.706550598144531, "critic_loss": 0.026942962780594826, "reward": 0.07070634514093399, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24641276895999908, 0.15704675018787384, 0.25634950399398804], "policy_updates": 37560, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6767.932817432, "contact_bce": 0.3157360255718231, "contact_force_loss": 0.0315154530107975, "terrain_level_mean": 3.166748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9977445602416992, 0.9990699291229248, 2.9964003562927246]} {"step": 37670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37670, "total_transitions": 154296320, "num_steps_per_env": 1, "wm_loss": 0.442945659160614, "actor_loss": -8.717510223388672, "critic_loss": 0.03107368014752865, "reward": 0.07102801650762558, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2451716959476471, 0.15600283443927765, 0.2559392750263214], "policy_updates": 37570, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6771.453362980999, "contact_bce": 0.31680089235305786, "contact_force_loss": 0.032129935920238495, "terrain_level_mean": 3.16748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9977445602416992, 0.9990699291229248, 2.9964003562927246]} {"step": 37680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37680, "total_transitions": 154337280, "num_steps_per_env": 1, "wm_loss": 0.4428882598876953, "actor_loss": -8.791959762573242, "critic_loss": 0.03259040042757988, "reward": 0.07070707529783249, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2509368062019348, 0.1583358198404312, 0.26256194710731506], "policy_updates": 37580, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6774.969454149, "contact_bce": 0.3141435384750366, "contact_force_loss": 0.03205728903412819, "terrain_level_mean": 3.16796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9977445602416992, 0.9990699291229248, 2.9964003562927246]} {"step": 37690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37690, "total_transitions": 154378240, "num_steps_per_env": 1, "wm_loss": 0.44601747393608093, "actor_loss": -8.750547409057617, "critic_loss": 0.0212082639336586, "reward": 0.06975756585597992, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2532699406147003, 0.16361190378665924, 0.26372402906417847], "policy_updates": 37590, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6778.483246979, "contact_bce": 0.3155075013637543, "contact_force_loss": 0.032651763409376144, "terrain_level_mean": 3.16748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9977445602416992, 0.9990699291229248, 2.9964003562927246]} {"step": 37700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37700, "total_transitions": 154419200, "num_steps_per_env": 1, "wm_loss": 0.45058274269104004, "actor_loss": -8.697675704956055, "critic_loss": 0.02989916503429413, "reward": 0.07017061114311218, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2533901333808899, 0.16261808574199677, 0.25775018334388733], "policy_updates": 37600, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6782.00262057, "contact_bce": 0.316961407661438, "contact_force_loss": 0.03155212476849556, "terrain_level_mean": 3.16748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9977445602416992, 0.9990699291229248, 2.9964003562927246]} {"step": 37710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37710, "total_transitions": 154460160, "num_steps_per_env": 1, "wm_loss": 0.4301135241985321, "actor_loss": -8.774446487426758, "critic_loss": 0.023415565490722656, "reward": 0.07029649615287781, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2501492500305176, 0.16440576314926147, 0.2571309208869934], "policy_updates": 37610, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6785.516364933, "contact_bce": 0.3143797516822815, "contact_force_loss": 0.03212360292673111, "terrain_level_mean": 3.167724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9977445602416992, 0.9985527396202087, 2.993171453475952]} {"step": 37720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37720, "total_transitions": 154501120, "num_steps_per_env": 1, "wm_loss": 0.4526864290237427, "actor_loss": -8.742156982421875, "critic_loss": 0.01969202049076557, "reward": 0.07061786204576492, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2481255829334259, 0.16333314776420593, 0.25580236315727234], "policy_updates": 37620, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6789.040852085, "contact_bce": 0.3211812674999237, "contact_force_loss": 0.032644715160131454, "terrain_level_mean": 3.16748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9977445602416992, 0.9951755404472351, 2.993171453475952]} {"step": 37730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37730, "total_transitions": 154542080, "num_steps_per_env": 1, "wm_loss": 0.4522189795970917, "actor_loss": -8.695899963378906, "critic_loss": 0.026750648394227028, "reward": 0.07082327455282211, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24760191142559052, 0.16005271673202515, 0.2616746127605438], "policy_updates": 37630, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6792.558530585, "contact_bce": 0.3161814212799072, "contact_force_loss": 0.03300774469971657, "terrain_level_mean": 3.168212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9983807802200317, 0.9951755404472351, 2.995980978012085]} {"step": 37740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37740, "total_transitions": 154583040, "num_steps_per_env": 1, "wm_loss": 0.45715489983558655, "actor_loss": -8.75830364227295, "critic_loss": 0.02973235212266445, "reward": 0.0705588161945343, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2531505227088928, 0.16011177003383636, 0.2580547034740448], "policy_updates": 37640, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6796.0748355119995, "contact_bce": 0.31465452909469604, "contact_force_loss": 0.033144086599349976, "terrain_level_mean": 3.169189453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9983807802200317, 0.9951755404472351, 2.995980978012085]} {"step": 37750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37750, "total_transitions": 154624000, "num_steps_per_env": 1, "wm_loss": 0.4337075650691986, "actor_loss": -8.738885879516602, "critic_loss": 0.027484415099024773, "reward": 0.07030615955591202, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25055938959121704, 0.15731768310070038, 0.254172146320343], "policy_updates": 37650, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6799.591687286, "contact_bce": 0.31628942489624023, "contact_force_loss": 0.03309525549411774, "terrain_level_mean": 3.16796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9983807802200317, 0.9951755404472351, 2.995980978012085]} {"step": 37760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37760, "total_transitions": 154664960, "num_steps_per_env": 1, "wm_loss": 0.4292834997177124, "actor_loss": -8.738714218139648, "critic_loss": 0.02962823025882244, "reward": 0.07035110145807266, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24860939383506775, 0.16085179150104523, 0.25488194823265076], "policy_updates": 37660, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6803.107956217999, "contact_bce": 0.31762176752090454, "contact_force_loss": 0.031890615820884705, "terrain_level_mean": 3.168701171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9983807802200317, 0.9951755404472351, 2.995980978012085]} {"step": 37770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37770, "total_transitions": 154705920, "num_steps_per_env": 1, "wm_loss": 0.4516834318637848, "actor_loss": -8.74789810180664, "critic_loss": 0.027155468240380287, "reward": 0.0702437311410904, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24331985414028168, 0.16196753084659576, 0.25842225551605225], "policy_updates": 37670, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6806.620232917, "contact_bce": 0.3183910846710205, "contact_force_loss": 0.03289792314171791, "terrain_level_mean": 3.167724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9983807802200317, 0.9959813356399536, 2.995980978012085]} {"step": 37780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37780, "total_transitions": 154746880, "num_steps_per_env": 1, "wm_loss": 0.5093590021133423, "actor_loss": -8.760350227355957, "critic_loss": 0.020308610051870346, "reward": 0.0705803856253624, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24177461862564087, 0.161982461810112, 0.2572536766529083], "policy_updates": 37680, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6810.134874846, "contact_bce": 0.3130494952201843, "contact_force_loss": 0.032344698905944824, "terrain_level_mean": 3.167724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9977445602416992, 0.9951755404472351, 2.995980978012085]} {"step": 37790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37790, "total_transitions": 154787840, "num_steps_per_env": 1, "wm_loss": 0.43867748975753784, "actor_loss": -8.767353057861328, "critic_loss": 0.022127510979771614, "reward": 0.0704696923494339, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2430545687675476, 0.16099296510219574, 0.25678935647010803], "policy_updates": 37690, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6813.665709108, "contact_bce": 0.31470683217048645, "contact_force_loss": 0.033016759902238846, "terrain_level_mean": 3.168212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9977445602416992, 0.9985311031341553, 2.995980978012085]} {"step": 37800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37800, "total_transitions": 154828800, "num_steps_per_env": 1, "wm_loss": 0.4402683973312378, "actor_loss": -8.724776268005371, "critic_loss": 0.025998203083872795, "reward": 0.07094498723745346, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24081109464168549, 0.161915123462677, 0.2507506012916565], "policy_updates": 37700, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6817.182499285999, "contact_bce": 0.3162197172641754, "contact_force_loss": 0.0328107550740242, "terrain_level_mean": 3.167724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9977445602416992, 0.9985311031341553, 2.995980978012085]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_037800.mp4 {"step": 37810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37810, "total_transitions": 154869760, "num_steps_per_env": 1, "wm_loss": 0.4507620632648468, "actor_loss": -8.753467559814453, "critic_loss": 0.026494408026337624, "reward": 0.07040505111217499, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2431001365184784, 0.1625271439552307, 0.25587978959083557], "policy_updates": 37710, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6826.5016596, "contact_bce": 0.3134492337703705, "contact_force_loss": 0.03216907009482384, "terrain_level_mean": 3.16748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9977445602416992, 0.9985311031341553, 2.995980978012085]} {"step": 37820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37820, "total_transitions": 154910720, "num_steps_per_env": 1, "wm_loss": 0.4407414495944977, "actor_loss": -8.770503997802734, "critic_loss": 0.027573127299547195, "reward": 0.07061147689819336, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24719391763210297, 0.1660766899585724, 0.25748512148857117], "policy_updates": 37720, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6830.001809611999, "contact_bce": 0.3150421679019928, "contact_force_loss": 0.0328652523458004, "terrain_level_mean": 3.167724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9971346855163574, 0.9985311031341553, 2.995980978012085]} {"step": 37830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37830, "total_transitions": 154951680, "num_steps_per_env": 1, "wm_loss": 0.43741756677627563, "actor_loss": -8.722912788391113, "critic_loss": 0.029658442363142967, "reward": 0.07027014344930649, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24869951605796814, 0.16396558284759521, 0.2555231750011444], "policy_updates": 37730, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6833.519388117, "contact_bce": 0.3151913285255432, "contact_force_loss": 0.03267369419336319, "terrain_level_mean": 3.1689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9971346855163574, 0.9985311031341553, 2.995980978012085]} {"step": 37840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37840, "total_transitions": 154992640, "num_steps_per_env": 1, "wm_loss": 0.44770100712776184, "actor_loss": -8.731473922729492, "critic_loss": 0.021343082189559937, "reward": 0.07041620463132858, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2471035271883011, 0.15840686857700348, 0.2541060745716095], "policy_updates": 37740, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6837.016152034999, "contact_bce": 0.31551989912986755, "contact_force_loss": 0.03254113718867302, "terrain_level_mean": 3.169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9972726106643677, 0.9985311031341553, 2.995980978012085]} {"step": 37850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37850, "total_transitions": 155033600, "num_steps_per_env": 1, "wm_loss": 0.4678577780723572, "actor_loss": -8.70791244506836, "critic_loss": 0.03563607856631279, "reward": 0.0702536478638649, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25137069821357727, 0.15964306890964508, 0.25955119729042053], "policy_updates": 37750, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6840.524807495, "contact_bce": 0.3170417547225952, "contact_force_loss": 0.032774653285741806, "terrain_level_mean": 3.171630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9972726106643677, 0.9985311031341553, 2.995980978012085]} {"step": 37860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37860, "total_transitions": 155074560, "num_steps_per_env": 1, "wm_loss": 0.47808873653411865, "actor_loss": -8.736026763916016, "critic_loss": 0.025816014036536217, "reward": 0.07023182511329651, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2500203251838684, 0.15827706456184387, 0.25669535994529724], "policy_updates": 37760, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6844.031999281, "contact_bce": 0.31741929054260254, "contact_force_loss": 0.03353557363152504, "terrain_level_mean": 3.171142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.995980978012085]} {"step": 37870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37870, "total_transitions": 155115520, "num_steps_per_env": 1, "wm_loss": 0.4504360556602478, "actor_loss": -8.706974029541016, "critic_loss": 0.031882259994745255, "reward": 0.07051786035299301, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2472039759159088, 0.15985862910747528, 0.2578289210796356], "policy_updates": 37770, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6847.531307067, "contact_bce": 0.3132644593715668, "contact_force_loss": 0.032714568078517914, "terrain_level_mean": 3.171142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.995980978012085]} {"step": 37880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37880, "total_transitions": 155156480, "num_steps_per_env": 1, "wm_loss": 0.4742257595062256, "actor_loss": -8.688177108764648, "critic_loss": 0.032990969717502594, "reward": 0.07044672966003418, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2458754926919937, 0.15975458920001984, 0.2561667561531067], "policy_updates": 37780, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6851.032279866, "contact_bce": 0.3173857033252716, "contact_force_loss": 0.033404454588890076, "terrain_level_mean": 3.17041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.999161720275879]} {"step": 37890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37890, "total_transitions": 155197440, "num_steps_per_env": 1, "wm_loss": 0.43302592635154724, "actor_loss": -8.747430801391602, "critic_loss": 0.027554625645279884, "reward": 0.07091417163610458, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24472907185554504, 0.16018034517765045, 0.2555427551269531], "policy_updates": 37790, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6854.529838650999, "contact_bce": 0.31237155199050903, "contact_force_loss": 0.03283200040459633, "terrain_level_mean": 3.169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.999161720275879]} {"step": 37900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37900, "total_transitions": 155238400, "num_steps_per_env": 1, "wm_loss": 0.476326584815979, "actor_loss": -8.741094589233398, "critic_loss": 0.03260170295834541, "reward": 0.07073464244604111, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24371211230754852, 0.1580040156841278, 0.25019994378089905], "policy_updates": 37800, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6858.046773292, "contact_bce": 0.3107507526874542, "contact_force_loss": 0.03212638199329376, "terrain_level_mean": 3.170166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.999161720275879]} {"step": 37910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37910, "total_transitions": 155279360, "num_steps_per_env": 1, "wm_loss": 0.4472058415412903, "actor_loss": -8.695296287536621, "critic_loss": 0.02715093456208706, "reward": 0.07082664221525192, "falls": 4, "interval_steps": 10, "velocity_mae": [0.241607666015625, 0.15664537250995636, 0.2509704828262329], "policy_updates": 37810, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6861.568221183, "contact_bce": 0.3174969553947449, "contact_force_loss": 0.033248238265514374, "terrain_level_mean": 3.170654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.999161720275879]} {"step": 37920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37920, "total_transitions": 155320320, "num_steps_per_env": 1, "wm_loss": 0.4635125994682312, "actor_loss": -8.68504524230957, "critic_loss": 0.03003832697868347, "reward": 0.07094182819128036, "falls": 8, "interval_steps": 10, "velocity_mae": [0.23989123106002808, 0.15719762444496155, 0.25045230984687805], "policy_updates": 37820, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6865.081908909, "contact_bce": 0.31291860342025757, "contact_force_loss": 0.03268315643072128, "terrain_level_mean": 3.1708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.999161720275879]} {"step": 37930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37930, "total_transitions": 155361280, "num_steps_per_env": 1, "wm_loss": 0.4319835901260376, "actor_loss": -8.77370834350586, "critic_loss": 0.022824948653578758, "reward": 0.07092437148094177, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24211004376411438, 0.1589008867740631, 0.25137820839881897], "policy_updates": 37830, "skipped_updates": 0, "invalid_env_resets": 59, "elapsed_s": 6868.588067526, "contact_bce": 0.3129287362098694, "contact_force_loss": 0.032278817147016525, "terrain_level_mean": 3.171630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.999161720275879]} RECOVERY reset 1 invalid environments; first IDs=[1025] {"step": 37940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37940, "total_transitions": 155402240, "num_steps_per_env": 1, "wm_loss": 0.43302375078201294, "actor_loss": -8.707027435302734, "critic_loss": 0.028462911024689674, "reward": 0.07025430351495743, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24821794033050537, 0.16077715158462524, 0.25518283247947693], "policy_updates": 37840, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6872.100032794, "contact_bce": 0.30833086371421814, "contact_force_loss": 0.03184663504362106, "terrain_level_mean": 3.173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9972726106643677, 0.9991172552108765, 2.999161720275879]} {"step": 37950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37950, "total_transitions": 155443200, "num_steps_per_env": 1, "wm_loss": 0.4655955135822296, "actor_loss": -8.723273277282715, "critic_loss": 0.02295699156820774, "reward": 0.07020282745361328, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2497902363538742, 0.1597263664007187, 0.2525339424610138], "policy_updates": 37850, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6875.606681593999, "contact_bce": 0.3180353045463562, "contact_force_loss": 0.033752404153347015, "terrain_level_mean": 3.1728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9972726106643677, 0.9958412647247314, 2.999161720275879]} {"step": 37960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37960, "total_transitions": 155484160, "num_steps_per_env": 1, "wm_loss": 0.4504418969154358, "actor_loss": -8.722766876220703, "critic_loss": 0.023020265623927116, "reward": 0.06992701441049576, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25224095582962036, 0.16029998660087585, 0.25529372692108154], "policy_updates": 37860, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6879.108726662999, "contact_bce": 0.3175240755081177, "contact_force_loss": 0.03352800011634827, "terrain_level_mean": 3.1728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9972726106643677, 0.9958412647247314, 2.999161720275879]} {"step": 37970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37970, "total_transitions": 155525120, "num_steps_per_env": 1, "wm_loss": 0.43869221210479736, "actor_loss": -8.683747291564941, "critic_loss": 0.03625262901186943, "reward": 0.07013153284788132, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24989421665668488, 0.1570688635110855, 0.25215059518814087], "policy_updates": 37870, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6882.6126982, "contact_bce": 0.314669132232666, "contact_force_loss": 0.03249054029583931, "terrain_level_mean": 3.171630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9972726106643677, 0.9958412647247314, 2.999161720275879]} {"step": 37980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37980, "total_transitions": 155566080, "num_steps_per_env": 1, "wm_loss": 0.4421963095664978, "actor_loss": -8.72404956817627, "critic_loss": 0.027301792055368423, "reward": 0.0711803063750267, "falls": 0, "interval_steps": 10, "velocity_mae": [0.2485576719045639, 0.1565198004245758, 0.25473639369010925], "policy_updates": 37880, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6886.118292495, "contact_bce": 0.312007337808609, "contact_force_loss": 0.032103441655635834, "terrain_level_mean": 3.172607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9972726106643677, 0.9982313513755798, 2.999161720275879]} {"step": 37990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 37990, "total_transitions": 155607040, "num_steps_per_env": 1, "wm_loss": 0.413884699344635, "actor_loss": -8.73453140258789, "critic_loss": 0.02499261684715748, "reward": 0.0711517259478569, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24846743047237396, 0.1588813215494156, 0.25600188970565796], "policy_updates": 37890, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6889.624446387999, "contact_bce": 0.31717222929000854, "contact_force_loss": 0.03288884460926056, "terrain_level_mean": 3.17236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9972726106643677, 0.9982313513755798, 2.999161720275879]} {"step": 38000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38000, "total_transitions": 155648000, "num_steps_per_env": 1, "wm_loss": 0.4434962570667267, "actor_loss": -8.744068145751953, "critic_loss": 0.024322163313627243, "reward": 0.07108264416456223, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2494753897190094, 0.16054680943489075, 0.2573671042919159], "policy_updates": 37900, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6893.133026097999, "contact_bce": 0.31820547580718994, "contact_force_loss": 0.033353041857481, "terrain_level_mean": 3.173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9972726106643677, 0.9982313513755798, 2.999161720275879]} {"step": 38010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38010, "total_transitions": 155688960, "num_steps_per_env": 1, "wm_loss": 0.44497185945510864, "actor_loss": -8.716033935546875, "critic_loss": 0.024233663454651833, "reward": 0.07103811204433441, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2501465082168579, 0.15831245481967926, 0.25574013590812683], "policy_updates": 37910, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6896.681219005, "contact_bce": 0.31757059693336487, "contact_force_loss": 0.03261055424809456, "terrain_level_mean": 3.17333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9992032051086426, 0.9982313513755798, 2.999161720275879]} {"step": 38020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38020, "total_transitions": 155729920, "num_steps_per_env": 1, "wm_loss": 0.44623440504074097, "actor_loss": -8.771858215332031, "critic_loss": 0.028231430798768997, "reward": 0.07107788324356079, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25057685375213623, 0.15664778649806976, 0.2513534426689148], "policy_updates": 37920, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6900.466336171, "contact_bce": 0.31695035099983215, "contact_force_loss": 0.03255763649940491, "terrain_level_mean": 3.175048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9992032051086426, 0.9982313513755798, 2.999161720275879]} {"step": 38030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38030, "total_transitions": 155770880, "num_steps_per_env": 1, "wm_loss": 0.4469725787639618, "actor_loss": -8.7257080078125, "critic_loss": 0.019678188487887383, "reward": 0.07072768360376358, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2539520561695099, 0.1594042032957077, 0.256590873003006], "policy_updates": 37930, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6903.981235425999, "contact_bce": 0.3168529272079468, "contact_force_loss": 0.03247104957699776, "terrain_level_mean": 3.175537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9992032051086426, 0.9982313513755798, 2.999161720275879]} {"step": 38040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38040, "total_transitions": 155811840, "num_steps_per_env": 1, "wm_loss": 0.447255939245224, "actor_loss": -8.742469787597656, "critic_loss": 0.024048496037721634, "reward": 0.0708952471613884, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2530995309352875, 0.1582905501127243, 0.25473612546920776], "policy_updates": 37940, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6907.474195279, "contact_bce": 0.31240183115005493, "contact_force_loss": 0.03274230659008026, "terrain_level_mean": 3.175537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9992032051086426, 0.9982313513755798, 2.999161720275879]} {"step": 38050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38050, "total_transitions": 155852800, "num_steps_per_env": 1, "wm_loss": 0.41799455881118774, "actor_loss": -8.702258110046387, "critic_loss": 0.028006387874484062, "reward": 0.07109514623880386, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2440704107284546, 0.1576884239912033, 0.25003939867019653], "policy_updates": 37950, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6910.963596666999, "contact_bce": 0.309366911649704, "contact_force_loss": 0.03149249404668808, "terrain_level_mean": 3.1748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.999161720275879]} {"step": 38060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38060, "total_transitions": 155893760, "num_steps_per_env": 1, "wm_loss": 0.45925822854042053, "actor_loss": -8.755454063415527, "critic_loss": 0.030068516731262207, "reward": 0.07176864147186279, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2415063977241516, 0.15651537477970123, 0.24646756052970886], "policy_updates": 37960, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6914.4626323269995, "contact_bce": 0.3172825872898102, "contact_force_loss": 0.0333886593580246, "terrain_level_mean": 3.176513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.999161720275879]} {"step": 38070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38070, "total_transitions": 155934720, "num_steps_per_env": 1, "wm_loss": 0.45965754985809326, "actor_loss": -8.754698753356934, "critic_loss": 0.028728438541293144, "reward": 0.07192543148994446, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24460315704345703, 0.15665335953235626, 0.24735896289348602], "policy_updates": 37970, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6917.96126724, "contact_bce": 0.3125917911529541, "contact_force_loss": 0.03303270787000656, "terrain_level_mean": 3.176513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.999161720275879]} {"step": 38080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38080, "total_transitions": 155975680, "num_steps_per_env": 1, "wm_loss": 0.4670853018760681, "actor_loss": -8.731706619262695, "critic_loss": 0.025033611804246902, "reward": 0.07176359742879868, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2443460375070572, 0.15679548680782318, 0.25030192732810974], "policy_updates": 37980, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6921.460672568, "contact_bce": 0.32010844349861145, "contact_force_loss": 0.033405400812625885, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.999161720275879]} {"step": 38090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38090, "total_transitions": 156016640, "num_steps_per_env": 1, "wm_loss": 0.44017940759658813, "actor_loss": -8.717521667480469, "critic_loss": 0.032703857868909836, "reward": 0.07171385735273361, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24530895054340363, 0.15506936609745026, 0.2536580264568329], "policy_updates": 37990, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6924.960084101999, "contact_bce": 0.3083442151546478, "contact_force_loss": 0.0323304682970047, "terrain_level_mean": 3.1767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.999161720275879]} {"step": 38100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38100, "total_transitions": 156057600, "num_steps_per_env": 1, "wm_loss": 0.4406753182411194, "actor_loss": -8.690439224243164, "critic_loss": 0.02613057568669319, "reward": 0.07133282721042633, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2495630979537964, 0.15446925163269043, 0.254672110080719], "policy_updates": 38000, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6928.4555420159995, "contact_bce": 0.31279256939888, "contact_force_loss": 0.032758552581071854, "terrain_level_mean": 3.1767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.999161720275879]} {"step": 38110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38110, "total_transitions": 156098560, "num_steps_per_env": 1, "wm_loss": 0.46817389130592346, "actor_loss": -8.70058822631836, "critic_loss": 0.022898873314261436, "reward": 0.07098811864852905, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24888113141059875, 0.15591183304786682, 0.25077754259109497], "policy_updates": 38010, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6931.953764833999, "contact_bce": 0.3186999559402466, "contact_force_loss": 0.033257853239774704, "terrain_level_mean": 3.175537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.9983270168304443]} {"step": 38120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38120, "total_transitions": 156139520, "num_steps_per_env": 1, "wm_loss": 0.4234849512577057, "actor_loss": -8.72530460357666, "critic_loss": 0.02651088871061802, "reward": 0.0708613321185112, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24635198712348938, 0.15663650631904602, 0.2523631155490875], "policy_updates": 38020, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6935.456538068999, "contact_bce": 0.31545621156692505, "contact_force_loss": 0.03239007666707039, "terrain_level_mean": 3.1748046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.991495132446289]} {"step": 38130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38130, "total_transitions": 156180480, "num_steps_per_env": 1, "wm_loss": 0.46084898710250854, "actor_loss": -8.735210418701172, "critic_loss": 0.02384517714381218, "reward": 0.07073714584112167, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24732664227485657, 0.15942233800888062, 0.2564413249492645], "policy_updates": 38030, "skipped_updates": 0, "invalid_env_resets": 60, "elapsed_s": 6938.951901803, "contact_bce": 0.32229647040367126, "contact_force_loss": 0.03319535404443741, "terrain_level_mean": 3.175048828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.991495132446289]} RECOVERY reset 1 invalid environments; first IDs=[1036] {"step": 38140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38140, "total_transitions": 156221440, "num_steps_per_env": 1, "wm_loss": 0.4545641541481018, "actor_loss": -8.68029499053955, "critic_loss": 0.031466662883758545, "reward": 0.07102372497320175, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2528279721736908, 0.16114576160907745, 0.26064223051071167], "policy_updates": 38040, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6942.4634742789995, "contact_bce": 0.31697139143943787, "contact_force_loss": 0.03310907259583473, "terrain_level_mean": 3.176025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.9990320205688477]} {"step": 38150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38150, "total_transitions": 156262400, "num_steps_per_env": 1, "wm_loss": 0.44880998134613037, "actor_loss": -8.692946434020996, "critic_loss": 0.026351219043135643, "reward": 0.07080012559890747, "falls": 0, "interval_steps": 10, "velocity_mae": [0.25292056798934937, 0.16125714778900146, 0.2596092224121094], "policy_updates": 38050, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6945.959853968, "contact_bce": 0.31447523832321167, "contact_force_loss": 0.0326710119843483, "terrain_level_mean": 3.17724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.9990320205688477]} {"step": 38160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38160, "total_transitions": 156303360, "num_steps_per_env": 1, "wm_loss": 0.45722538232803345, "actor_loss": -8.74019718170166, "critic_loss": 0.034049324691295624, "reward": 0.07096662372350693, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2513803243637085, 0.16235464811325073, 0.26513588428497314], "policy_updates": 38060, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6949.457429176, "contact_bce": 0.32011982798576355, "contact_force_loss": 0.032784849405288696, "terrain_level_mean": 3.17724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.9990320205688477]} {"step": 38170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38170, "total_transitions": 156344320, "num_steps_per_env": 1, "wm_loss": 0.4557153284549713, "actor_loss": -8.738149642944336, "critic_loss": 0.029651949182152748, "reward": 0.07102933526039124, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2531468868255615, 0.16330736875534058, 0.26285451650619507], "policy_updates": 38070, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6952.961411355, "contact_bce": 0.31987714767456055, "contact_force_loss": 0.033996641635894775, "terrain_level_mean": 3.17724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.9990320205688477]} {"step": 38180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38180, "total_transitions": 156385280, "num_steps_per_env": 1, "wm_loss": 0.4338616132736206, "actor_loss": -8.672161102294922, "critic_loss": 0.03669772669672966, "reward": 0.07102610170841217, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25298359990119934, 0.16259656846523285, 0.2591549754142761], "policy_updates": 38080, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6956.461845412, "contact_bce": 0.3178282380104065, "contact_force_loss": 0.031793251633644104, "terrain_level_mean": 3.177490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.9990320205688477]} {"step": 38190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38190, "total_transitions": 156426240, "num_steps_per_env": 1, "wm_loss": 0.46653085947036743, "actor_loss": -8.711301803588867, "critic_loss": 0.03205287456512451, "reward": 0.07087206840515137, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25275304913520813, 0.16207608580589294, 0.2603801190853119], "policy_updates": 38090, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6959.9627400419995, "contact_bce": 0.31212204694747925, "contact_force_loss": 0.032815974205732346, "terrain_level_mean": 3.1767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9996188879013062, 0.9989098310470581, 2.9990320205688477]} {"step": 38200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38200, "total_transitions": 156467200, "num_steps_per_env": 1, "wm_loss": 0.44870731234550476, "actor_loss": -8.744833946228027, "critic_loss": 0.019501373171806335, "reward": 0.0704687163233757, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2542688846588135, 0.16365399956703186, 0.2627340257167816], "policy_updates": 38100, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6963.4601481909995, "contact_bce": 0.3199610710144043, "contact_force_loss": 0.0324883833527565, "terrain_level_mean": 3.177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38210, "total_transitions": 156508160, "num_steps_per_env": 1, "wm_loss": 0.44232863187789917, "actor_loss": -8.686531066894531, "critic_loss": 0.028714848682284355, "reward": 0.07101130485534668, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2538265585899353, 0.1624642312526703, 0.26022768020629883], "policy_updates": 38110, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6966.964922927, "contact_bce": 0.31717491149902344, "contact_force_loss": 0.032378774136304855, "terrain_level_mean": 3.177490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38220, "total_transitions": 156549120, "num_steps_per_env": 1, "wm_loss": 0.4189162254333496, "actor_loss": -8.728188514709473, "critic_loss": 0.030950922518968582, "reward": 0.07130157947540283, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2530781030654907, 0.16151854395866394, 0.25662732124328613], "policy_updates": 38120, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6970.467383026, "contact_bce": 0.31160008907318115, "contact_force_loss": 0.03279561176896095, "terrain_level_mean": 3.17724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38230, "total_transitions": 156590080, "num_steps_per_env": 1, "wm_loss": 0.4473641514778137, "actor_loss": -8.717323303222656, "critic_loss": 0.030456608161330223, "reward": 0.07151879370212555, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24391032755374908, 0.1598086804151535, 0.2555657923221588], "policy_updates": 38130, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6973.968177821999, "contact_bce": 0.31464624404907227, "contact_force_loss": 0.03306718170642853, "terrain_level_mean": 3.177001953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38240, "total_transitions": 156631040, "num_steps_per_env": 1, "wm_loss": 0.45633336901664734, "actor_loss": -8.765950202941895, "critic_loss": 0.021551696583628654, "reward": 0.07174856960773468, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24006856977939606, 0.15794648230075836, 0.2550163269042969], "policy_updates": 38140, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6977.466730802, "contact_bce": 0.31663596630096436, "contact_force_loss": 0.032838333398103714, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38250, "total_transitions": 156672000, "num_steps_per_env": 1, "wm_loss": 0.443148136138916, "actor_loss": -8.686349868774414, "critic_loss": 0.034648407250642776, "reward": 0.07184242457151413, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24501658976078033, 0.15799392759799957, 0.251571923494339], "policy_updates": 38150, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6980.967913676, "contact_bce": 0.314949631690979, "contact_force_loss": 0.032923053950071335, "terrain_level_mean": 3.176025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38260, "total_transitions": 156712960, "num_steps_per_env": 1, "wm_loss": 0.4298977255821228, "actor_loss": -8.716757774353027, "critic_loss": 0.02562079392373562, "reward": 0.07162477821111679, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2459074705839157, 0.1569761037826538, 0.25142937898635864], "policy_updates": 38160, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6984.46666103, "contact_bce": 0.31570255756378174, "contact_force_loss": 0.0322611965239048, "terrain_level_mean": 3.175537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38270, "total_transitions": 156753920, "num_steps_per_env": 1, "wm_loss": 0.43851011991500854, "actor_loss": -8.744876861572266, "critic_loss": 0.023183755576610565, "reward": 0.07180166989564896, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24664904177188873, 0.15574213862419128, 0.24691174924373627], "policy_updates": 38170, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6987.9849863809995, "contact_bce": 0.31800562143325806, "contact_force_loss": 0.03261678293347359, "terrain_level_mean": 3.17578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38280, "total_transitions": 156794880, "num_steps_per_env": 1, "wm_loss": 0.438289999961853, "actor_loss": -8.722782135009766, "critic_loss": 0.021628526970744133, "reward": 0.07175488024950027, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24672111868858337, 0.15455913543701172, 0.2506348788738251], "policy_updates": 38180, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6991.510610476, "contact_bce": 0.317914754152298, "contact_force_loss": 0.03231845796108246, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} {"step": 38290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38290, "total_transitions": 156835840, "num_steps_per_env": 1, "wm_loss": 0.42979294061660767, "actor_loss": -8.687650680541992, "critic_loss": 0.03011453151702881, "reward": 0.07160993665456772, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24914774298667908, 0.15523448586463928, 0.24816496670246124], "policy_updates": 38190, "skipped_updates": 0, "invalid_env_resets": 61, "elapsed_s": 6995.020123863, "contact_bce": 0.316121906042099, "contact_force_loss": 0.03201154246926308, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9972317218780518, 0.9989098310470581, 2.9990320205688477]} RECOVERY reset 1 invalid environments; first IDs=[2768] {"step": 38300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38300, "total_transitions": 156876800, "num_steps_per_env": 1, "wm_loss": 0.4437069594860077, "actor_loss": -8.738054275512695, "critic_loss": 0.03527432307600975, "reward": 0.07094057649374008, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25129783153533936, 0.1547057032585144, 0.25199657678604126], "policy_updates": 38200, "skipped_updates": 0, "invalid_env_resets": 62, "elapsed_s": 6998.5561585979995, "contact_bce": 0.3177720308303833, "contact_force_loss": 0.03347961604595184, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9983714818954468, 0.9989098310470581, 2.9990320205688477]} {"step": 38310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38310, "total_transitions": 156917760, "num_steps_per_env": 1, "wm_loss": 0.43536698818206787, "actor_loss": -8.694709777832031, "critic_loss": 0.024294449016451836, "reward": 0.0710621029138565, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24818487465381622, 0.15807290375232697, 0.2580121159553528], "policy_updates": 38210, "skipped_updates": 0, "invalid_env_resets": 62, "elapsed_s": 7002.061839847, "contact_bce": 0.3098968267440796, "contact_force_loss": 0.032830365002155304, "terrain_level_mean": 3.175537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9983714818954468, 0.9989098310470581, 2.9990320205688477]} {"step": 38320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38320, "total_transitions": 156958720, "num_steps_per_env": 1, "wm_loss": 0.43579360842704773, "actor_loss": -8.750919342041016, "critic_loss": 0.02857222594320774, "reward": 0.07080619782209396, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2462952435016632, 0.15880084037780762, 0.2570312023162842], "policy_updates": 38220, "skipped_updates": 0, "invalid_env_resets": 62, "elapsed_s": 7005.583913801999, "contact_bce": 0.3149559199810028, "contact_force_loss": 0.03284220024943352, "terrain_level_mean": 3.175537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9983714818954468, 0.9989098310470581, 2.9990320205688477]} {"step": 38330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38330, "total_transitions": 156999680, "num_steps_per_env": 1, "wm_loss": 0.4164871573448181, "actor_loss": -8.734672546386719, "critic_loss": 0.02485865354537964, "reward": 0.07045543938875198, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24792972207069397, 0.1583983153104782, 0.2525581121444702], "policy_updates": 38230, "skipped_updates": 0, "invalid_env_resets": 62, "elapsed_s": 7009.105931923, "contact_bce": 0.31768032908439636, "contact_force_loss": 0.032071951776742935, "terrain_level_mean": 3.17578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9983714818954468, 0.9989098310470581, 2.9990320205688477]} RECOVERY reset 1 invalid environments; first IDs=[1689] {"step": 38340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38340, "total_transitions": 157040640, "num_steps_per_env": 1, "wm_loss": 0.4119834303855896, "actor_loss": -8.70947265625, "critic_loss": 0.026799237355589867, "reward": 0.07070757448673248, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24468404054641724, 0.1603262722492218, 0.25186124444007874], "policy_updates": 38240, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7012.641815694, "contact_bce": 0.31123778223991394, "contact_force_loss": 0.03298268839716911, "terrain_level_mean": 3.17578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.9990320205688477]} {"step": 38350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38350, "total_transitions": 157081600, "num_steps_per_env": 1, "wm_loss": 0.4316377341747284, "actor_loss": -8.719642639160156, "critic_loss": 0.030864715576171875, "reward": 0.07061871886253357, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25009456276893616, 0.1614789068698883, 0.25325295329093933], "policy_updates": 38250, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7016.1569699619995, "contact_bce": 0.31261104345321655, "contact_force_loss": 0.031864866614341736, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.9990320205688477]} {"step": 38360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38360, "total_transitions": 157122560, "num_steps_per_env": 1, "wm_loss": 0.4492693543434143, "actor_loss": -8.719356536865234, "critic_loss": 0.023743892088532448, "reward": 0.0707830935716629, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2481914460659027, 0.15848295390605927, 0.25300073623657227], "policy_updates": 38260, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7019.670859899999, "contact_bce": 0.3237975835800171, "contact_force_loss": 0.032935529947280884, "terrain_level_mean": 3.176513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.9990320205688477]} {"step": 38370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38370, "total_transitions": 157163520, "num_steps_per_env": 1, "wm_loss": 0.4611183702945709, "actor_loss": -8.694169998168945, "critic_loss": 0.030796706676483154, "reward": 0.07054425776004791, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24877336621284485, 0.1590188890695572, 0.2532915472984314], "policy_updates": 38270, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7023.180919754, "contact_bce": 0.316351979970932, "contact_force_loss": 0.03242836520075798, "terrain_level_mean": 3.17724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.999150276184082]} {"step": 38380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38380, "total_transitions": 157204480, "num_steps_per_env": 1, "wm_loss": 0.4188828468322754, "actor_loss": -8.750686645507812, "critic_loss": 0.0342450812458992, "reward": 0.07076830416917801, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24636802077293396, 0.1576840877532959, 0.24832560122013092], "policy_updates": 38280, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7026.69012221, "contact_bce": 0.3148459792137146, "contact_force_loss": 0.032420575618743896, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.999150276184082]} {"step": 38390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38390, "total_transitions": 157245440, "num_steps_per_env": 1, "wm_loss": 0.44755813479423523, "actor_loss": -8.770872116088867, "critic_loss": 0.024618860334157944, "reward": 0.0711321234703064, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24782510101795197, 0.1561509668827057, 0.24752740561962128], "policy_updates": 38290, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7030.194284701, "contact_bce": 0.31914466619491577, "contact_force_loss": 0.03293889760971069, "terrain_level_mean": 3.17626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.999150276184082]} {"step": 38400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38400, "total_transitions": 157286400, "num_steps_per_env": 1, "wm_loss": 0.41935020685195923, "actor_loss": -8.696099281311035, "critic_loss": 0.024589991196990013, "reward": 0.0710010901093483, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24484407901763916, 0.15581144392490387, 0.2521252930164337], "policy_updates": 38300, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7033.692582322, "contact_bce": 0.3146364986896515, "contact_force_loss": 0.031649112701416016, "terrain_level_mean": 3.1767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.999150276184082]} {"step": 38410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38410, "total_transitions": 157327360, "num_steps_per_env": 1, "wm_loss": 0.43901926279067993, "actor_loss": -8.759315490722656, "critic_loss": 0.019831065088510513, "reward": 0.07106231898069382, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2421741932630539, 0.15590231120586395, 0.25320732593536377], "policy_updates": 38310, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7037.198955751, "contact_bce": 0.31525129079818726, "contact_force_loss": 0.03294311463832855, "terrain_level_mean": 3.17724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.999150276184082]} {"step": 38420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38420, "total_transitions": 157368320, "num_steps_per_env": 1, "wm_loss": 0.43657004833221436, "actor_loss": -8.723434448242188, "critic_loss": 0.023118047043681145, "reward": 0.07085295021533966, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24408017098903656, 0.1588178128004074, 0.2513725459575653], "policy_updates": 38320, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7040.711253779, "contact_bce": 0.31684911251068115, "contact_force_loss": 0.032415721565485, "terrain_level_mean": 3.177490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9983714818954468, 0.9990044832229614, 2.999150276184082]} {"step": 38430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38430, "total_transitions": 157409280, "num_steps_per_env": 1, "wm_loss": 0.4362107515335083, "actor_loss": -8.730011940002441, "critic_loss": 0.023894870653748512, "reward": 0.07096733897924423, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23878848552703857, 0.15859773755073547, 0.2524667978286743], "policy_updates": 38330, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7044.248588914, "contact_bce": 0.318473756313324, "contact_force_loss": 0.032501619309186935, "terrain_level_mean": 3.177490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38440, "total_transitions": 157450240, "num_steps_per_env": 1, "wm_loss": 0.44034501910209656, "actor_loss": -8.771106719970703, "critic_loss": 0.02299039624631405, "reward": 0.07136901468038559, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24214133620262146, 0.15678280591964722, 0.2522975206375122], "policy_updates": 38340, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7047.747720314, "contact_bce": 0.3159582316875458, "contact_force_loss": 0.033079441636800766, "terrain_level_mean": 3.177978515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38450, "total_transitions": 157491200, "num_steps_per_env": 1, "wm_loss": 0.4428308606147766, "actor_loss": -8.741665840148926, "critic_loss": 0.027718959376215935, "reward": 0.07137131690979004, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2410803586244583, 0.15769489109516144, 0.2529846727848053], "policy_updates": 38350, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7051.244322615, "contact_bce": 0.31232038140296936, "contact_force_loss": 0.03371734917163849, "terrain_level_mean": 3.1787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38460, "total_transitions": 157532160, "num_steps_per_env": 1, "wm_loss": 0.4274876117706299, "actor_loss": -8.685760498046875, "critic_loss": 0.04485021159052849, "reward": 0.07137052714824677, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24298866093158722, 0.15881562232971191, 0.25083816051483154], "policy_updates": 38360, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7054.7478814099995, "contact_bce": 0.316386878490448, "contact_force_loss": 0.03251459822058678, "terrain_level_mean": 3.1787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330322265625, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38470, "total_transitions": 157573120, "num_steps_per_env": 1, "wm_loss": 0.41527122259140015, "actor_loss": -8.744333267211914, "critic_loss": 0.02267846278846264, "reward": 0.0713794156908989, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2438245713710785, 0.15664386749267578, 0.25037533044815063], "policy_updates": 38370, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7058.247458913, "contact_bce": 0.31558048725128174, "contact_force_loss": 0.03257893770933151, "terrain_level_mean": 3.179443359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327880859375, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38480, "total_transitions": 157614080, "num_steps_per_env": 1, "wm_loss": 0.46046289801597595, "actor_loss": -8.757299423217773, "critic_loss": 0.027306485921144485, "reward": 0.07099948078393936, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24659201502799988, 0.1584988683462143, 0.2511879503726959], "policy_updates": 38380, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7061.740422149999, "contact_bce": 0.30923891067504883, "contact_force_loss": 0.03208707645535469, "terrain_level_mean": 3.178955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.327880859375, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38490, "total_transitions": 157655040, "num_steps_per_env": 1, "wm_loss": 0.4182092249393463, "actor_loss": -8.739744186401367, "critic_loss": 0.02138211578130722, "reward": 0.07113275676965714, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24654187262058258, 0.15662872791290283, 0.2522358298301697], "policy_updates": 38390, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7065.2326610459995, "contact_bce": 0.3152357339859009, "contact_force_loss": 0.03253792226314545, "terrain_level_mean": 3.178955078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328857421875, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38500, "total_transitions": 157696000, "num_steps_per_env": 1, "wm_loss": 0.4575622081756592, "actor_loss": -8.739559173583984, "critic_loss": 0.03200515732169151, "reward": 0.07098225504159927, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24783578515052795, 0.15750744938850403, 0.25193706154823303], "policy_updates": 38400, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7068.7305785359995, "contact_bce": 0.30931612849235535, "contact_force_loss": 0.03266182914376259, "terrain_level_mean": 3.1806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38510, "total_transitions": 157736960, "num_steps_per_env": 1, "wm_loss": 0.44465550780296326, "actor_loss": -8.751486778259277, "critic_loss": 0.02473991923034191, "reward": 0.07087945193052292, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24964162707328796, 0.15746986865997314, 0.25233614444732666], "policy_updates": 38410, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7072.276308875, "contact_bce": 0.31958234310150146, "contact_force_loss": 0.0333210825920105, "terrain_level_mean": 3.180419921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38520, "total_transitions": 157777920, "num_steps_per_env": 1, "wm_loss": 0.45928332209587097, "actor_loss": -8.779708862304688, "critic_loss": 0.030452433973550797, "reward": 0.0704384446144104, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2518167793750763, 0.15919004380702972, 0.25758329033851624], "policy_updates": 38420, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7075.783685404999, "contact_bce": 0.3161047101020813, "contact_force_loss": 0.03293110802769661, "terrain_level_mean": 3.18017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38530, "total_transitions": 157818880, "num_steps_per_env": 1, "wm_loss": 0.46695250272750854, "actor_loss": -8.731590270996094, "critic_loss": 0.026135964319109917, "reward": 0.07091876119375229, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24794061481952667, 0.15939919650554657, 0.25232839584350586], "policy_updates": 38430, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7079.548021029, "contact_bce": 0.31229573488235474, "contact_force_loss": 0.032527703791856766, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38540, "total_transitions": 157859840, "num_steps_per_env": 1, "wm_loss": 0.4429303705692291, "actor_loss": -8.732646942138672, "critic_loss": 0.02767089568078518, "reward": 0.07117544859647751, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2465212494134903, 0.1565457433462143, 0.25081008672714233], "policy_updates": 38440, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7083.071791351999, "contact_bce": 0.3160437047481537, "contact_force_loss": 0.03289830684661865, "terrain_level_mean": 3.18115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38550, "total_transitions": 157900800, "num_steps_per_env": 1, "wm_loss": 0.4893588721752167, "actor_loss": -8.743086814880371, "critic_loss": 0.02788713574409485, "reward": 0.07134559005498886, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24152034521102905, 0.15492410957813263, 0.25294652581214905], "policy_updates": 38450, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7086.592424807, "contact_bce": 0.31866320967674255, "contact_force_loss": 0.033331502228975296, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38560, "total_transitions": 157941760, "num_steps_per_env": 1, "wm_loss": 0.45145225524902344, "actor_loss": -8.727489471435547, "critic_loss": 0.024100078269839287, "reward": 0.07136495411396027, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24258531630039215, 0.15770894289016724, 0.25410667061805725], "policy_updates": 38460, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7090.110204443, "contact_bce": 0.3150293529033661, "contact_force_loss": 0.032520245760679245, "terrain_level_mean": 3.180908203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9983714818954468, 0.9992728233337402, 2.999150276184082]} {"step": 38570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38570, "total_transitions": 157982720, "num_steps_per_env": 1, "wm_loss": 0.4523489475250244, "actor_loss": -8.791232109069824, "critic_loss": 0.019940277561545372, "reward": 0.07152918726205826, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2457372397184372, 0.1589890420436859, 0.2536154091358185], "policy_updates": 38470, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7093.6330024339995, "contact_bce": 0.3209812045097351, "contact_force_loss": 0.03288108855485916, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.999150276184082]} {"step": 38580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38580, "total_transitions": 158023680, "num_steps_per_env": 1, "wm_loss": 0.463386207818985, "actor_loss": -8.716489791870117, "critic_loss": 0.02004210464656353, "reward": 0.0712997242808342, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24805893003940582, 0.15876555442810059, 0.2535842955112457], "policy_updates": 38480, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7097.153965719, "contact_bce": 0.31086602807044983, "contact_force_loss": 0.03200246021151543, "terrain_level_mean": 3.1806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.999150276184082]} {"step": 38590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38590, "total_transitions": 158064640, "num_steps_per_env": 1, "wm_loss": 0.42077845335006714, "actor_loss": -8.742650985717773, "critic_loss": 0.02338220551609993, "reward": 0.07095454633235931, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24804577231407166, 0.16097241640090942, 0.2565891146659851], "policy_updates": 38490, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7100.682384817, "contact_bce": 0.30931657552719116, "contact_force_loss": 0.03189638629555702, "terrain_level_mean": 3.181884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.999150276184082]} {"step": 38600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38600, "total_transitions": 158105600, "num_steps_per_env": 1, "wm_loss": 0.44751042127609253, "actor_loss": -8.7652587890625, "critic_loss": 0.018325699493288994, "reward": 0.07103346288204193, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24520869553089142, 0.15736405551433563, 0.2525721788406372], "policy_updates": 38500, "skipped_updates": 0, "invalid_env_resets": 63, "elapsed_s": 7104.190420454, "contact_bce": 0.3183227479457855, "contact_force_loss": 0.032821375876665115, "terrain_level_mean": 3.18115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.9986824989318848]} RECOVERY reset 1 invalid environments; first IDs=[530] {"step": 38610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38610, "total_transitions": 158146560, "num_steps_per_env": 1, "wm_loss": 0.4234814941883087, "actor_loss": -8.742666244506836, "critic_loss": 0.025312235578894615, "reward": 0.07074350118637085, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24689367413520813, 0.15611889958381653, 0.2545056939125061], "policy_updates": 38510, "skipped_updates": 0, "invalid_env_resets": 64, "elapsed_s": 7107.711599939, "contact_bce": 0.32163724303245544, "contact_force_loss": 0.03315958008170128, "terrain_level_mean": 3.18115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.9986824989318848]} {"step": 38620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38620, "total_transitions": 158187520, "num_steps_per_env": 1, "wm_loss": 0.4489291310310364, "actor_loss": -8.744436264038086, "critic_loss": 0.026467829942703247, "reward": 0.07103174924850464, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2487684190273285, 0.15668043494224548, 0.25623825192451477], "policy_updates": 38520, "skipped_updates": 0, "invalid_env_resets": 64, "elapsed_s": 7111.217124151, "contact_bce": 0.3134961724281311, "contact_force_loss": 0.03265373781323433, "terrain_level_mean": 3.179931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.9986824989318848]} RECOVERY reset 1 invalid environments; first IDs=[978] {"step": 38630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38630, "total_transitions": 158228480, "num_steps_per_env": 1, "wm_loss": 0.42443814873695374, "actor_loss": -8.782022476196289, "critic_loss": 0.0234773438423872, "reward": 0.0716579407453537, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24458643794059753, 0.15709656476974487, 0.24796073138713837], "policy_updates": 38530, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7114.733217030999, "contact_bce": 0.3143288195133209, "contact_force_loss": 0.03249024599790573, "terrain_level_mean": 3.180419921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.998267650604248]} {"step": 38640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38640, "total_transitions": 158269440, "num_steps_per_env": 1, "wm_loss": 0.42673131823539734, "actor_loss": -8.717447280883789, "critic_loss": 0.036427952349185944, "reward": 0.07154515385627747, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24012966454029083, 0.1549336463212967, 0.24942387640476227], "policy_updates": 38540, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7118.236392854999, "contact_bce": 0.31622642278671265, "contact_force_loss": 0.03219575434923172, "terrain_level_mean": 3.179931640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9989240169525146, 0.9992728233337402, 2.998267650604248]} {"step": 38650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38650, "total_transitions": 158310400, "num_steps_per_env": 1, "wm_loss": 0.438960999250412, "actor_loss": -8.747722625732422, "critic_loss": 0.022927388548851013, "reward": 0.07109441608190536, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24649885296821594, 0.15799564123153687, 0.25043031573295593], "policy_updates": 38550, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7121.757517032, "contact_bce": 0.3170487582683563, "contact_force_loss": 0.03255215659737587, "terrain_level_mean": 3.18115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38660, "total_transitions": 158351360, "num_steps_per_env": 1, "wm_loss": 0.4474896490573883, "actor_loss": -8.692378997802734, "critic_loss": 0.034118276089429855, "reward": 0.07083912938833237, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24650363624095917, 0.15911975502967834, 0.25148478150367737], "policy_updates": 38560, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7125.277610106999, "contact_bce": 0.30891653895378113, "contact_force_loss": 0.03169681504368782, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38670, "total_transitions": 158392320, "num_steps_per_env": 1, "wm_loss": 0.434367299079895, "actor_loss": -8.729001998901367, "critic_loss": 0.029032543301582336, "reward": 0.07096843421459198, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2430904060602188, 0.15844781696796417, 0.254741907119751], "policy_updates": 38570, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7128.771344764, "contact_bce": 0.31469252705574036, "contact_force_loss": 0.03217338025569916, "terrain_level_mean": 3.181884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38680, "total_transitions": 158433280, "num_steps_per_env": 1, "wm_loss": 0.41909661889076233, "actor_loss": -8.745267868041992, "critic_loss": 0.022393567487597466, "reward": 0.0709066167473793, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24680489301681519, 0.15974636375904083, 0.25607115030288696], "policy_updates": 38580, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7132.280387106, "contact_bce": 0.32045167684555054, "contact_force_loss": 0.032289426773786545, "terrain_level_mean": 3.18115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38690, "total_transitions": 158474240, "num_steps_per_env": 1, "wm_loss": 0.4257676303386688, "actor_loss": -8.7329683303833, "critic_loss": 0.02642253413796425, "reward": 0.07084944099187851, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24829711019992828, 0.16446082293987274, 0.2540753185749054], "policy_updates": 38590, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7135.7806266709995, "contact_bce": 0.31845712661743164, "contact_force_loss": 0.03282376751303673, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38700, "total_transitions": 158515200, "num_steps_per_env": 1, "wm_loss": 0.42985019087791443, "actor_loss": -8.759408950805664, "critic_loss": 0.02150731533765793, "reward": 0.07065324485301971, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2478494495153427, 0.16716794669628143, 0.25689443945884705], "policy_updates": 38600, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7139.279855834, "contact_bce": 0.3123457729816437, "contact_force_loss": 0.03157692775130272, "terrain_level_mean": 3.182373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38710, "total_transitions": 158556160, "num_steps_per_env": 1, "wm_loss": 0.44973087310791016, "actor_loss": -8.739262580871582, "critic_loss": 0.027606045827269554, "reward": 0.07073454558849335, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24723459780216217, 0.16167406737804413, 0.2529202401638031], "policy_updates": 38610, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7142.786467923999, "contact_bce": 0.31040623784065247, "contact_force_loss": 0.03238961845636368, "terrain_level_mean": 3.18212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38720, "total_transitions": 158597120, "num_steps_per_env": 1, "wm_loss": 0.4360526502132416, "actor_loss": -8.753480911254883, "critic_loss": 0.02245502918958664, "reward": 0.07073330134153366, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2459452599287033, 0.16104112565517426, 0.2534336447715759], "policy_updates": 38620, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7146.302407554, "contact_bce": 0.3123015761375427, "contact_force_loss": 0.03274667263031006, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359375, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38730, "total_transitions": 158638080, "num_steps_per_env": 1, "wm_loss": 0.42492005228996277, "actor_loss": -8.762849807739258, "critic_loss": 0.03291307017207146, "reward": 0.07100168615579605, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2451372593641281, 0.1606518030166626, 0.255363404750824], "policy_updates": 38630, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7149.819624092, "contact_bce": 0.31124207377433777, "contact_force_loss": 0.03268864378333092, "terrain_level_mean": 3.181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38740, "total_transitions": 158679040, "num_steps_per_env": 1, "wm_loss": 0.4375739097595215, "actor_loss": -8.772393226623535, "critic_loss": 0.020240891724824905, "reward": 0.07075955718755722, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24737951159477234, 0.16117200255393982, 0.2570323944091797], "policy_updates": 38640, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7153.329443914, "contact_bce": 0.3150677978992462, "contact_force_loss": 0.03259808570146561, "terrain_level_mean": 3.181884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38750, "total_transitions": 158720000, "num_steps_per_env": 1, "wm_loss": 0.42846935987472534, "actor_loss": -8.77532958984375, "critic_loss": 0.02756558172404766, "reward": 0.0707462951540947, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2449396699666977, 0.15932469069957733, 0.2594389021396637], "policy_updates": 38650, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7156.8321896669995, "contact_bce": 0.3125734329223633, "contact_force_loss": 0.03218325972557068, "terrain_level_mean": 3.181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9989240169525146, 0.9994900226593018, 2.998267650604248]} {"step": 38760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38760, "total_transitions": 158760960, "num_steps_per_env": 1, "wm_loss": 0.43921148777008057, "actor_loss": -8.779153823852539, "critic_loss": 0.021318314597010612, "reward": 0.07099954038858414, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24166172742843628, 0.15569113194942474, 0.2511041462421417], "policy_updates": 38660, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7160.334588295, "contact_bce": 0.31293314695358276, "contact_force_loss": 0.031961582601070404, "terrain_level_mean": 3.181884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9989240169525146, 0.9991950988769531, 2.998267650604248]} {"step": 38770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38770, "total_transitions": 158801920, "num_steps_per_env": 1, "wm_loss": 0.44792690873146057, "actor_loss": -8.74395751953125, "critic_loss": 0.020003175362944603, "reward": 0.07081645727157593, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24691122770309448, 0.15793612599372864, 0.2556000351905823], "policy_updates": 38670, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7163.8357591369995, "contact_bce": 0.3173232078552246, "contact_force_loss": 0.03250015899538994, "terrain_level_mean": 3.181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9989240169525146, 0.9991950988769531, 2.998267650604248]} {"step": 38780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38780, "total_transitions": 158842880, "num_steps_per_env": 1, "wm_loss": 0.43739694356918335, "actor_loss": -8.750523567199707, "critic_loss": 0.02288229949772358, "reward": 0.07087687402963638, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24939358234405518, 0.16087716817855835, 0.2578524649143219], "policy_updates": 38680, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7167.335605353999, "contact_bce": 0.3175543546676636, "contact_force_loss": 0.032199833542108536, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9989240169525146, 0.9991950988769531, 2.9979472160339355]} {"step": 38790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38790, "total_transitions": 158883840, "num_steps_per_env": 1, "wm_loss": 0.4823981523513794, "actor_loss": -8.705235481262207, "critic_loss": 0.02408069185912609, "reward": 0.07125597447156906, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2470136135816574, 0.16179513931274414, 0.2569364011287689], "policy_updates": 38690, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7170.841883192, "contact_bce": 0.3114529252052307, "contact_force_loss": 0.032607514411211014, "terrain_level_mean": 3.18115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9989240169525146, 0.9991950988769531, 2.9979472160339355]} {"step": 38800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38800, "total_transitions": 158924800, "num_steps_per_env": 1, "wm_loss": 0.41829198598861694, "actor_loss": -8.74156665802002, "critic_loss": 0.022757917642593384, "reward": 0.07093490660190582, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24870772659778595, 0.1618087887763977, 0.25861209630966187], "policy_updates": 38700, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7174.344521055999, "contact_bce": 0.3109043538570404, "contact_force_loss": 0.032258063554763794, "terrain_level_mean": 3.1806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9996943473815918, 0.9991950988769531, 2.9979472160339355]} {"step": 38810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38810, "total_transitions": 158965760, "num_steps_per_env": 1, "wm_loss": 0.42273297905921936, "actor_loss": -8.765111923217773, "critic_loss": 0.02975967526435852, "reward": 0.07067535072565079, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2508713901042938, 0.16128888726234436, 0.2552257776260376], "policy_updates": 38710, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7177.847040072, "contact_bce": 0.31367942690849304, "contact_force_loss": 0.03259368985891342, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9996943473815918, 0.9991950988769531, 2.9979472160339355]} {"step": 38820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38820, "total_transitions": 159006720, "num_steps_per_env": 1, "wm_loss": 0.44443538784980774, "actor_loss": -8.725990295410156, "critic_loss": 0.022387715056538582, "reward": 0.06994914263486862, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2502146363258362, 0.16134417057037354, 0.2563396394252777], "policy_updates": 38720, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7181.35278234, "contact_bce": 0.31281688809394836, "contact_force_loss": 0.03232188895344734, "terrain_level_mean": 3.181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9955410957336426]} {"step": 38830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38830, "total_transitions": 159047680, "num_steps_per_env": 1, "wm_loss": 0.45152589678764343, "actor_loss": -8.755277633666992, "critic_loss": 0.022533589974045753, "reward": 0.0697079449892044, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2483048141002655, 0.16496314108371735, 0.2578190565109253], "policy_updates": 38730, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7184.850835263, "contact_bce": 0.3136483430862427, "contact_force_loss": 0.031823400408029556, "terrain_level_mean": 3.18017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38840, "total_transitions": 159088640, "num_steps_per_env": 1, "wm_loss": 0.42238789796829224, "actor_loss": -8.72291088104248, "critic_loss": 0.028081005439162254, "reward": 0.07034451514482498, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24838042259216309, 0.16299137473106384, 0.2560865879058838], "policy_updates": 38740, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7188.348864343, "contact_bce": 0.3150099515914917, "contact_force_loss": 0.032743532210588455, "terrain_level_mean": 3.181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38850, "total_transitions": 159129600, "num_steps_per_env": 1, "wm_loss": 0.4703005254268646, "actor_loss": -8.718034744262695, "critic_loss": 0.027477461844682693, "reward": 0.07055678218603134, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24830849468708038, 0.1613231599330902, 0.25390860438346863], "policy_updates": 38750, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7191.846226311, "contact_bce": 0.3085862398147583, "contact_force_loss": 0.03263876959681511, "terrain_level_mean": 3.18212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38860, "total_transitions": 159170560, "num_steps_per_env": 1, "wm_loss": 0.4609989821910858, "actor_loss": -8.73251724243164, "critic_loss": 0.03879993036389351, "reward": 0.07058142125606537, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2451532483100891, 0.16136501729488373, 0.2553803622722626], "policy_updates": 38760, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7195.341614206, "contact_bce": 0.3164973258972168, "contact_force_loss": 0.03290862217545509, "terrain_level_mean": 3.182373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38870, "total_transitions": 159211520, "num_steps_per_env": 1, "wm_loss": 0.4297579228878021, "actor_loss": -8.717116355895996, "critic_loss": 0.030482802540063858, "reward": 0.0705832690000534, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24296101927757263, 0.16127422451972961, 0.25529658794403076], "policy_updates": 38770, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7198.848930446, "contact_bce": 0.31360533833503723, "contact_force_loss": 0.03165479004383087, "terrain_level_mean": 3.182861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38880, "total_transitions": 159252480, "num_steps_per_env": 1, "wm_loss": 0.42044520378112793, "actor_loss": -8.68077278137207, "critic_loss": 0.03301676735281944, "reward": 0.07095716893672943, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24221578240394592, 0.15982899069786072, 0.25448742508888245], "policy_updates": 38780, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7202.366300475, "contact_bce": 0.3107835054397583, "contact_force_loss": 0.031311534345149994, "terrain_level_mean": 3.18310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38890, "total_transitions": 159293440, "num_steps_per_env": 1, "wm_loss": 0.4501497149467468, "actor_loss": -8.705073356628418, "critic_loss": 0.03281192108988762, "reward": 0.070816271007061, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24568942189216614, 0.16193953156471252, 0.2570398449897766], "policy_updates": 38790, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7205.884130427, "contact_bce": 0.31815990805625916, "contact_force_loss": 0.03322745859622955, "terrain_level_mean": 3.184326171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38900, "total_transitions": 159334400, "num_steps_per_env": 1, "wm_loss": 0.41362062096595764, "actor_loss": -8.68675422668457, "critic_loss": 0.0327037051320076, "reward": 0.07071834057569504, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24442608654499054, 0.16048426926136017, 0.25490856170654297], "policy_updates": 38800, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7209.394396631, "contact_bce": 0.31342199444770813, "contact_force_loss": 0.03285621106624603, "terrain_level_mean": 3.183837890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38910, "total_transitions": 159375360, "num_steps_per_env": 1, "wm_loss": 0.4318239390850067, "actor_loss": -8.703147888183594, "critic_loss": 0.027646023780107498, "reward": 0.0704975426197052, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2503751516342163, 0.15817035734653473, 0.2567012310028076], "policy_updates": 38810, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7212.904826331999, "contact_bce": 0.30898988246917725, "contact_force_loss": 0.03211066126823425, "terrain_level_mean": 3.184326171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38920, "total_transitions": 159416320, "num_steps_per_env": 1, "wm_loss": 0.4348585903644562, "actor_loss": -8.74917221069336, "critic_loss": 0.027752608060836792, "reward": 0.07072170823812485, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24996444582939148, 0.1545722484588623, 0.25904983282089233], "policy_updates": 38820, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7216.415556477999, "contact_bce": 0.31585314869880676, "contact_force_loss": 0.03208370506763458, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38930, "total_transitions": 159457280, "num_steps_per_env": 1, "wm_loss": 0.4849287271499634, "actor_loss": -8.762748718261719, "critic_loss": 0.020818402990698814, "reward": 0.07101257890462875, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2532283663749695, 0.15506316721439362, 0.25591805577278137], "policy_updates": 38830, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7219.927856167999, "contact_bce": 0.31938761472702026, "contact_force_loss": 0.03406254202127457, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38940, "total_transitions": 159498240, "num_steps_per_env": 1, "wm_loss": 0.4320157766342163, "actor_loss": -8.77817440032959, "critic_loss": 0.02054757997393608, "reward": 0.07097820937633514, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24833379685878754, 0.15742698311805725, 0.25687122344970703], "policy_updates": 38840, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7223.4423787979995, "contact_bce": 0.31119194626808167, "contact_force_loss": 0.031985074281692505, "terrain_level_mean": 3.182861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38950, "total_transitions": 159539200, "num_steps_per_env": 1, "wm_loss": 0.4392731189727783, "actor_loss": -8.689311981201172, "critic_loss": 0.022374840453267097, "reward": 0.0708015188574791, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24403637647628784, 0.15707625448703766, 0.2537519931793213], "policy_updates": 38850, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7226.95734717, "contact_bce": 0.31614455580711365, "contact_force_loss": 0.03250284492969513, "terrain_level_mean": 3.183349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9996943473815918, 0.9980566501617432, 2.9966278076171875]} {"step": 38960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38960, "total_transitions": 159580160, "num_steps_per_env": 1, "wm_loss": 0.41499778628349304, "actor_loss": -8.762954711914062, "critic_loss": 0.021200185641646385, "reward": 0.07092548906803131, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24091659486293793, 0.15680120885372162, 0.24744243919849396], "policy_updates": 38860, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7230.464198412999, "contact_bce": 0.30947640538215637, "contact_force_loss": 0.031874872744083405, "terrain_level_mean": 3.184814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.9966278076171875]} {"step": 38970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38970, "total_transitions": 159621120, "num_steps_per_env": 1, "wm_loss": 0.39947596192359924, "actor_loss": -8.750175476074219, "critic_loss": 0.029506130144000053, "reward": 0.0705716535449028, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2466883361339569, 0.1557198017835617, 0.2490922510623932], "policy_updates": 38870, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7233.971672334999, "contact_bce": 0.3106660544872284, "contact_force_loss": 0.031581562012434006, "terrain_level_mean": 3.185546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.9966278076171875]} {"step": 38980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38980, "total_transitions": 159662080, "num_steps_per_env": 1, "wm_loss": 0.42520028352737427, "actor_loss": -8.692399024963379, "critic_loss": 0.02534390054643154, "reward": 0.0710204467177391, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2495594173669815, 0.15740369260311127, 0.24855703115463257], "policy_updates": 38880, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7237.486133019999, "contact_bce": 0.30828356742858887, "contact_force_loss": 0.03233560547232628, "terrain_level_mean": 3.185791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.9966278076171875]} {"step": 38990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 38990, "total_transitions": 159703040, "num_steps_per_env": 1, "wm_loss": 0.4470992684364319, "actor_loss": -8.733193397521973, "critic_loss": 0.02010360173881054, "reward": 0.07030247896909714, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24826642870903015, 0.15932266414165497, 0.2555413842201233], "policy_updates": 38890, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7241.004822364999, "contact_bce": 0.312078595161438, "contact_force_loss": 0.0327097587287426, "terrain_level_mean": 3.185791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.991703748703003]} {"step": 39000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39000, "total_transitions": 159744000, "num_steps_per_env": 1, "wm_loss": 0.42549946904182434, "actor_loss": -8.703193664550781, "critic_loss": 0.02951475977897644, "reward": 0.07043005526065826, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24677978456020355, 0.15928126871585846, 0.25552845001220703], "policy_updates": 38900, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7244.525131762, "contact_bce": 0.31293079257011414, "contact_force_loss": 0.03142450749874115, "terrain_level_mean": 3.184326171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.991703748703003]} {"step": 39010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39010, "total_transitions": 159784960, "num_steps_per_env": 1, "wm_loss": 0.4456981122493744, "actor_loss": -8.724471092224121, "critic_loss": 0.02561921812593937, "reward": 0.07083455473184586, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2532706558704376, 0.15840379893779755, 0.25570768117904663], "policy_updates": 38910, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7248.047358264999, "contact_bce": 0.30729418992996216, "contact_force_loss": 0.03174655884504318, "terrain_level_mean": 3.18603515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.991703748703003]} {"step": 39020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39020, "total_transitions": 159825920, "num_steps_per_env": 1, "wm_loss": 0.4192904531955719, "actor_loss": -8.765907287597656, "critic_loss": 0.016001811251044273, "reward": 0.07084842771291733, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2535516619682312, 0.15897201001644135, 0.25169429183006287], "policy_updates": 38920, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7251.553648536, "contact_bce": 0.31402939558029175, "contact_force_loss": 0.032407864928245544, "terrain_level_mean": 3.186279296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.991703748703003]} {"step": 39030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39030, "total_transitions": 159866880, "num_steps_per_env": 1, "wm_loss": 0.423814982175827, "actor_loss": -8.729085922241211, "critic_loss": 0.021680017933249474, "reward": 0.0709414929151535, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2519596517086029, 0.1568155288696289, 0.25198596715927124], "policy_updates": 38930, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7255.326521653, "contact_bce": 0.3095211386680603, "contact_force_loss": 0.03169107064604759, "terrain_level_mean": 3.1865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.992953300476074]} {"step": 39040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39040, "total_transitions": 159907840, "num_steps_per_env": 1, "wm_loss": 0.4132198989391327, "actor_loss": -8.753807067871094, "critic_loss": 0.02261490933597088, "reward": 0.07103104889392853, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2516172528266907, 0.15702950954437256, 0.251014769077301], "policy_updates": 38940, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7258.847384199, "contact_bce": 0.31161409616470337, "contact_force_loss": 0.032150715589523315, "terrain_level_mean": 3.18701171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.992953300476074]} {"step": 39050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39050, "total_transitions": 159948800, "num_steps_per_env": 1, "wm_loss": 0.42679229378700256, "actor_loss": -8.763863563537598, "critic_loss": 0.022471478208899498, "reward": 0.07117649167776108, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24659450352191925, 0.15543140470981598, 0.24988600611686707], "policy_updates": 38950, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7262.367620311999, "contact_bce": 0.3192518651485443, "contact_force_loss": 0.03283822163939476, "terrain_level_mean": 3.188232421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9996943473815918, 0.9998583793640137, 2.992953300476074]} {"step": 39060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39060, "total_transitions": 159989760, "num_steps_per_env": 1, "wm_loss": 0.4448447525501251, "actor_loss": -8.705228805541992, "critic_loss": 0.028886711224913597, "reward": 0.07108436524868011, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24608874320983887, 0.15460841357707977, 0.24915072321891785], "policy_updates": 38960, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7265.887205913999, "contact_bce": 0.31504663825035095, "contact_force_loss": 0.03292502835392952, "terrain_level_mean": 3.189208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9994779825210571, 0.9998583793640137, 2.992953300476074]} {"step": 39070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39070, "total_transitions": 160030720, "num_steps_per_env": 1, "wm_loss": 0.45377737283706665, "actor_loss": -8.689319610595703, "critic_loss": 0.02940325438976288, "reward": 0.07081594318151474, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2485828846693039, 0.15495091676712036, 0.25174733996391296], "policy_updates": 38970, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7269.3970302259995, "contact_bce": 0.31633812189102173, "contact_force_loss": 0.03251811861991882, "terrain_level_mean": 3.189208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9994779825210571, 0.9998583793640137, 2.992953300476074]} {"step": 39080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39080, "total_transitions": 160071680, "num_steps_per_env": 1, "wm_loss": 0.4354386329650879, "actor_loss": -8.729791641235352, "critic_loss": 0.02442782185971737, "reward": 0.07124456018209457, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2502637803554535, 0.15402153134346008, 0.2473645657300949], "policy_updates": 38980, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7272.915038532, "contact_bce": 0.3136707842350006, "contact_force_loss": 0.032403163611888885, "terrain_level_mean": 3.18701171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9994779825210571, 0.9998583793640137, 2.992953300476074]} {"step": 39090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39090, "total_transitions": 160112640, "num_steps_per_env": 1, "wm_loss": 0.4053349196910858, "actor_loss": -8.734795570373535, "critic_loss": 0.03038622811436653, "reward": 0.0709931030869484, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25495201349258423, 0.15637019276618958, 0.25549113750457764], "policy_updates": 38990, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7276.431132823999, "contact_bce": 0.3128337264060974, "contact_force_loss": 0.03192754089832306, "terrain_level_mean": 3.186767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9994779825210571, 0.9998583793640137, 2.992953300476074]} {"step": 39100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39100, "total_transitions": 160153600, "num_steps_per_env": 1, "wm_loss": 0.44680383801460266, "actor_loss": -8.729375839233398, "critic_loss": 0.028889814391732216, "reward": 0.07062031328678131, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25649845600128174, 0.15873567759990692, 0.2573004364967346], "policy_updates": 39000, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7279.949016666, "contact_bce": 0.3148926794528961, "contact_force_loss": 0.03290535509586334, "terrain_level_mean": 3.1865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9994779825210571, 0.9998583793640137, 2.992953300476074]} {"step": 39110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39110, "total_transitions": 160194560, "num_steps_per_env": 1, "wm_loss": 0.470147043466568, "actor_loss": -8.727792739868164, "critic_loss": 0.029011625796556473, "reward": 0.07075594365596771, "falls": 5, "interval_steps": 10, "velocity_mae": [0.26034829020500183, 0.15700338780879974, 0.25535157322883606], "policy_updates": 39010, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7283.447828724999, "contact_bce": 0.32204920053482056, "contact_force_loss": 0.0329662524163723, "terrain_level_mean": 3.187255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9994779825210571, 0.9998583793640137, 2.992953300476074]} {"step": 39120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39120, "total_transitions": 160235520, "num_steps_per_env": 1, "wm_loss": 0.42661944031715393, "actor_loss": -8.667095184326172, "critic_loss": 0.02984752133488655, "reward": 0.07087267935276031, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2577294409275055, 0.1553054302930832, 0.2522091567516327], "policy_updates": 39020, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7286.945834157, "contact_bce": 0.31435203552246094, "contact_force_loss": 0.032049573957920074, "terrain_level_mean": 3.187744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9994779825210571, 0.9998583793640137, 2.992953300476074]} {"step": 39130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39130, "total_transitions": 160276480, "num_steps_per_env": 1, "wm_loss": 0.4332488477230072, "actor_loss": -8.758386611938477, "critic_loss": 0.09550287574529648, "reward": 0.07095050811767578, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25285494327545166, 0.15663066506385803, 0.25326284766197205], "policy_updates": 39030, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7290.447220317999, "contact_bce": 0.3143591284751892, "contact_force_loss": 0.03282958269119263, "terrain_level_mean": 3.18798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9991958141326904, 0.9988306760787964, 2.992953300476074]} {"step": 39140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39140, "total_transitions": 160317440, "num_steps_per_env": 1, "wm_loss": 0.3953586220741272, "actor_loss": -8.739052772521973, "critic_loss": 0.02514197863638401, "reward": 0.07051310688257217, "falls": 12, "interval_steps": 10, "velocity_mae": [0.258041650056839, 0.15863938629627228, 0.25395041704177856], "policy_updates": 39040, "skipped_updates": 0, "invalid_env_resets": 65, "elapsed_s": 7293.946420793, "contact_bce": 0.31247302889823914, "contact_force_loss": 0.032463617622852325, "terrain_level_mean": 3.186767578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9991958141326904, 0.9988306760787964, 2.992953300476074]} RECOVERY reset 1 invalid environments; first IDs=[1572] {"step": 39150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39150, "total_transitions": 160358400, "num_steps_per_env": 1, "wm_loss": 0.40672823786735535, "actor_loss": -8.705535888671875, "critic_loss": 0.028528211638331413, "reward": 0.07079140841960907, "falls": 8, "interval_steps": 10, "velocity_mae": [0.250394731760025, 0.15951330959796906, 0.2552042007446289], "policy_updates": 39050, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7297.46143196, "contact_bce": 0.31399255990982056, "contact_force_loss": 0.03211225941777229, "terrain_level_mean": 3.1865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9991958141326904, 0.9999130368232727, 2.9998464584350586]} {"step": 39160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39160, "total_transitions": 160399360, "num_steps_per_env": 1, "wm_loss": 0.44798779487609863, "actor_loss": -8.717500686645508, "critic_loss": 0.04095184803009033, "reward": 0.0708000585436821, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24761590361595154, 0.1578911542892456, 0.2531898617744446], "policy_updates": 39060, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7300.956780386, "contact_bce": 0.31524503231048584, "contact_force_loss": 0.0320572704076767, "terrain_level_mean": 3.1865234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9991958141326904, 0.9999130368232727, 2.9998464584350586]} {"step": 39170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39170, "total_transitions": 160440320, "num_steps_per_env": 1, "wm_loss": 0.4431149661540985, "actor_loss": -8.682406425476074, "critic_loss": 0.029177075251936913, "reward": 0.07073259353637695, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24898025393486023, 0.15489475429058075, 0.2533912658691406], "policy_updates": 39070, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7304.450342767, "contact_bce": 0.311917781829834, "contact_force_loss": 0.032368846237659454, "terrain_level_mean": 3.185791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.996663212776184, 0.9999130368232727, 2.9998464584350586]} {"step": 39180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39180, "total_transitions": 160481280, "num_steps_per_env": 1, "wm_loss": 0.4314112961292267, "actor_loss": -8.757326126098633, "critic_loss": 0.025278467684984207, "reward": 0.07101919502019882, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2470908761024475, 0.1525200754404068, 0.2541273832321167], "policy_updates": 39080, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7307.944038805999, "contact_bce": 0.314528226852417, "contact_force_loss": 0.03323741629719734, "terrain_level_mean": 3.184814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.996663212776184, 0.9999130368232727, 2.9998464584350586]} {"step": 39190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39190, "total_transitions": 160522240, "num_steps_per_env": 1, "wm_loss": 0.43284499645233154, "actor_loss": -8.732419967651367, "critic_loss": 0.025316452607512474, "reward": 0.07086323946714401, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2459057867527008, 0.15513379871845245, 0.2475762665271759], "policy_updates": 39090, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7311.4502239799995, "contact_bce": 0.3176153898239136, "contact_force_loss": 0.03290325775742531, "terrain_level_mean": 3.185302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9964520931243896, 0.9999130368232727, 2.9998464584350586]} {"step": 39200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39200, "total_transitions": 160563200, "num_steps_per_env": 1, "wm_loss": 0.4322328567504883, "actor_loss": -8.750635147094727, "critic_loss": 0.024510657414793968, "reward": 0.07019614428281784, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24530306458473206, 0.15854443609714508, 0.24937927722930908], "policy_updates": 39100, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7314.951612190999, "contact_bce": 0.3160765469074249, "contact_force_loss": 0.03206080570816994, "terrain_level_mean": 3.185791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.99801504611969, 0.9999130368232727, 2.9998464584350586]} {"step": 39210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39210, "total_transitions": 160604160, "num_steps_per_env": 1, "wm_loss": 0.43882542848587036, "actor_loss": -8.72205638885498, "critic_loss": 0.027972644194960594, "reward": 0.070196732878685, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24501211941242218, 0.15968340635299683, 0.25373515486717224], "policy_updates": 39110, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7318.451426778, "contact_bce": 0.3145790696144104, "contact_force_loss": 0.03273079916834831, "terrain_level_mean": 3.18603515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9985944032669067, 0.9999130368232727, 2.9998464584350586]} {"step": 39220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39220, "total_transitions": 160645120, "num_steps_per_env": 1, "wm_loss": 0.4283565878868103, "actor_loss": -8.749040603637695, "critic_loss": 0.025308964774012566, "reward": 0.07041793316602707, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24593913555145264, 0.15556757152080536, 0.2529110014438629], "policy_updates": 39120, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7321.951166602999, "contact_bce": 0.31054961681365967, "contact_force_loss": 0.03234228491783142, "terrain_level_mean": 3.1845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9985944032669067, 0.9999130368232727, 2.9998464584350586]} {"step": 39230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39230, "total_transitions": 160686080, "num_steps_per_env": 1, "wm_loss": 0.4117802679538727, "actor_loss": -8.685806274414062, "critic_loss": 0.03226732462644577, "reward": 0.0704365000128746, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24395312368869781, 0.15353982150554657, 0.25037840008735657], "policy_updates": 39130, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7325.454210587, "contact_bce": 0.31040462851524353, "contact_force_loss": 0.032361987978219986, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9985944032669067, 0.9999130368232727, 2.9998464584350586]} {"step": 39240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39240, "total_transitions": 160727040, "num_steps_per_env": 1, "wm_loss": 0.42970529198646545, "actor_loss": -8.755023002624512, "critic_loss": 0.021483374759554863, "reward": 0.07124609500169754, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2427435964345932, 0.15182603895664215, 0.24982358515262604], "policy_updates": 39140, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7328.954365275, "contact_bce": 0.30879178643226624, "contact_force_loss": 0.03230668976902962, "terrain_level_mean": 3.183349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9985944032669067, 0.9999130368232727, 2.9998464584350586]} {"step": 39250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39250, "total_transitions": 160768000, "num_steps_per_env": 1, "wm_loss": 0.4294171631336212, "actor_loss": -8.745498657226562, "critic_loss": 0.032100316137075424, "reward": 0.071494460105896, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24270178377628326, 0.15200543403625488, 0.24680942296981812], "policy_updates": 39150, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7332.460386864999, "contact_bce": 0.3139505684375763, "contact_force_loss": 0.0320301279425621, "terrain_level_mean": 3.183837890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9985944032669067, 0.999972939491272, 2.9998464584350586]} {"step": 39260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39260, "total_transitions": 160808960, "num_steps_per_env": 1, "wm_loss": 0.45357900857925415, "actor_loss": -8.742179870605469, "critic_loss": 0.029441511258482933, "reward": 0.07150151580572128, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24341067671775818, 0.15318021178245544, 0.24441078305244446], "policy_updates": 39160, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7335.960230041, "contact_bce": 0.3127893805503845, "contact_force_loss": 0.03294823318719864, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39270, "total_transitions": 160849920, "num_steps_per_env": 1, "wm_loss": 0.4476938843727112, "actor_loss": -8.774084091186523, "critic_loss": 0.021656828001141548, "reward": 0.07168363779783249, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24185208976268768, 0.15692701935768127, 0.24623818695545197], "policy_updates": 39170, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7339.465911263, "contact_bce": 0.31993988156318665, "contact_force_loss": 0.033467188477516174, "terrain_level_mean": 3.183349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39280, "total_transitions": 160890880, "num_steps_per_env": 1, "wm_loss": 0.4018794298171997, "actor_loss": -8.670902252197266, "critic_loss": 0.025318214669823647, "reward": 0.0713919922709465, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24264934659004211, 0.15717321634292603, 0.24935883283615112], "policy_updates": 39180, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7342.966592215, "contact_bce": 0.30699145793914795, "contact_force_loss": 0.031867850571870804, "terrain_level_mean": 3.1826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39290, "total_transitions": 160931840, "num_steps_per_env": 1, "wm_loss": 0.43879055976867676, "actor_loss": -8.69880485534668, "critic_loss": 0.024911751970648766, "reward": 0.07109884172677994, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24580006301403046, 0.1561662256717682, 0.25436049699783325], "policy_updates": 39190, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7346.470900073, "contact_bce": 0.312906950712204, "contact_force_loss": 0.03238969296216965, "terrain_level_mean": 3.182373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39300, "total_transitions": 160972800, "num_steps_per_env": 1, "wm_loss": 0.4224599003791809, "actor_loss": -8.709238052368164, "critic_loss": 0.0201716348528862, "reward": 0.07120823860168457, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24483683705329895, 0.1564764529466629, 0.2546256184577942], "policy_updates": 39200, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7350.000482025, "contact_bce": 0.3187843859195709, "contact_force_loss": 0.032933253794908524, "terrain_level_mean": 3.1826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39310, "total_transitions": 161013760, "num_steps_per_env": 1, "wm_loss": 0.42192646861076355, "actor_loss": -8.71787166595459, "critic_loss": 0.026702994480729103, "reward": 0.0706898495554924, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24322271347045898, 0.15700724720954895, 0.25390416383743286], "policy_updates": 39210, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7353.521096758, "contact_bce": 0.3137410581111908, "contact_force_loss": 0.03271393105387688, "terrain_level_mean": 3.181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39320, "total_transitions": 161054720, "num_steps_per_env": 1, "wm_loss": 0.4427710771560669, "actor_loss": -8.77437973022461, "critic_loss": 0.02388654462993145, "reward": 0.07075540721416473, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24610716104507446, 0.15756018459796906, 0.253038614988327], "policy_updates": 39220, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7357.043435031, "contact_bce": 0.3143160045146942, "contact_force_loss": 0.03231765702366829, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39330, "total_transitions": 161095680, "num_steps_per_env": 1, "wm_loss": 0.435344398021698, "actor_loss": -8.766359329223633, "critic_loss": 0.02322697825729847, "reward": 0.07065799087285995, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2494203895330429, 0.15720868110656738, 0.25056830048561096], "policy_updates": 39230, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7360.571304696, "contact_bce": 0.3115605413913727, "contact_force_loss": 0.03153441101312637, "terrain_level_mean": 3.183349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39340, "total_transitions": 161136640, "num_steps_per_env": 1, "wm_loss": 0.4408803880214691, "actor_loss": -8.736387252807617, "critic_loss": 0.03130288049578667, "reward": 0.07021108269691467, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2516079246997833, 0.15840137004852295, 0.2514714002609253], "policy_updates": 39240, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7364.094193532999, "contact_bce": 0.3077933192253113, "contact_force_loss": 0.03205585852265358, "terrain_level_mean": 3.1826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9989631175994873, 0.999972939491272, 2.9998464584350586]} {"step": 39350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39350, "total_transitions": 161177600, "num_steps_per_env": 1, "wm_loss": 0.4138757586479187, "actor_loss": -8.719629287719727, "critic_loss": 0.026802068576216698, "reward": 0.07021930068731308, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2513107359409332, 0.15649740397930145, 0.2518307566642761], "policy_updates": 39250, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7367.621944142999, "contact_bce": 0.3113535940647125, "contact_force_loss": 0.03160535544157028, "terrain_level_mean": 3.182861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9985944032669067, 0.999972939491272, 2.9998464584350586]} {"step": 39360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39360, "total_transitions": 161218560, "num_steps_per_env": 1, "wm_loss": 0.4708879292011261, "actor_loss": -8.743602752685547, "critic_loss": 0.03212977200746536, "reward": 0.07017099857330322, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25061437487602234, 0.15981167554855347, 0.25164368748664856], "policy_updates": 39260, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7371.138117357, "contact_bce": 0.31030726432800293, "contact_force_loss": 0.031697843223810196, "terrain_level_mean": 3.18212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9985944032669067, 0.999972939491272, 2.9998464584350586]} {"step": 39370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39370, "total_transitions": 161259520, "num_steps_per_env": 1, "wm_loss": 0.4277500510215759, "actor_loss": -8.795196533203125, "critic_loss": 0.01752716861665249, "reward": 0.0698346421122551, "falls": 11, "interval_steps": 10, "velocity_mae": [0.2528204619884491, 0.16023914515972137, 0.2515515089035034], "policy_updates": 39270, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7374.655551663999, "contact_bce": 0.31356388330459595, "contact_force_loss": 0.03269340842962265, "terrain_level_mean": 3.180908203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9985944032669067, 0.999972939491272, 2.9998464584350586]} {"step": 39380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39380, "total_transitions": 161300480, "num_steps_per_env": 1, "wm_loss": 0.4529641568660736, "actor_loss": -8.735339164733887, "critic_loss": 0.025447731837630272, "reward": 0.06988678872585297, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2562386095523834, 0.1614624559879303, 0.25028669834136963], "policy_updates": 39280, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7378.1689754789995, "contact_bce": 0.31616371870040894, "contact_force_loss": 0.032855305820703506, "terrain_level_mean": 3.182373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9985944032669067, 0.999972939491272, 2.9998464584350586]} {"step": 39390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39390, "total_transitions": 161341440, "num_steps_per_env": 1, "wm_loss": 0.46129730343818665, "actor_loss": -8.721891403198242, "critic_loss": 0.023280462250113487, "reward": 0.0699302926659584, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2561695873737335, 0.16319392621517181, 0.2554123103618622], "policy_updates": 39290, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7381.682703070999, "contact_bce": 0.31550225615501404, "contact_force_loss": 0.032918475568294525, "terrain_level_mean": 3.18310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9993035793304443, 0.999972939491272, 2.9998464584350586]} {"step": 39400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39400, "total_transitions": 161382400, "num_steps_per_env": 1, "wm_loss": 0.4311530292034149, "actor_loss": -8.704383850097656, "critic_loss": 0.033957354724407196, "reward": 0.07019837945699692, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24828289449214935, 0.16088663041591644, 0.2515386641025543], "policy_updates": 39300, "skipped_updates": 0, "invalid_env_resets": 66, "elapsed_s": 7385.199181655, "contact_bce": 0.3110063076019287, "contact_force_loss": 0.032411348074674606, "terrain_level_mean": 3.1826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9993035793304443, 0.999972939491272, 2.9998464584350586]} RECOVERY reset 1 invalid environments; first IDs=[2590] {"step": 39410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39410, "total_transitions": 161423360, "num_steps_per_env": 1, "wm_loss": 0.42810532450675964, "actor_loss": -8.729942321777344, "critic_loss": 0.026185626164078712, "reward": 0.07025465369224548, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25101417303085327, 0.1577128767967224, 0.25629723072052], "policy_updates": 39310, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7388.710098097999, "contact_bce": 0.3128938376903534, "contact_force_loss": 0.03143764287233353, "terrain_level_mean": 3.181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9993035793304443, 0.999972939491272, 2.9998464584350586]} {"step": 39420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39420, "total_transitions": 161464320, "num_steps_per_env": 1, "wm_loss": 0.41471853852272034, "actor_loss": -8.765235900878906, "critic_loss": 0.023138921707868576, "reward": 0.0701085552573204, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25163406133651733, 0.15979431569576263, 0.25430789589881897], "policy_updates": 39320, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7392.208018265, "contact_bce": 0.31292060017585754, "contact_force_loss": 0.03214024007320404, "terrain_level_mean": 3.181396484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9993035793304443, 0.999972939491272, 2.9998464584350586]} {"step": 39430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39430, "total_transitions": 161505280, "num_steps_per_env": 1, "wm_loss": 0.42464014887809753, "actor_loss": -8.738407135009766, "critic_loss": 0.026404818519949913, "reward": 0.07012387365102768, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2501652240753174, 0.16062895953655243, 0.2549528479576111], "policy_updates": 39330, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7395.7082697139995, "contact_bce": 0.3081309497356415, "contact_force_loss": 0.03287937864661217, "terrain_level_mean": 3.1806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9998464584350586]} {"step": 39440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39440, "total_transitions": 161546240, "num_steps_per_env": 1, "wm_loss": 0.4683305621147156, "actor_loss": -8.714563369750977, "critic_loss": 0.02615748718380928, "reward": 0.0699828639626503, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24665696918964386, 0.16251179575920105, 0.2592000961303711], "policy_updates": 39340, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7399.203947704999, "contact_bce": 0.31392842531204224, "contact_force_loss": 0.033499643206596375, "terrain_level_mean": 3.182373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9998464584350586]} {"step": 39450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39450, "total_transitions": 161587200, "num_steps_per_env": 1, "wm_loss": 0.4152917265892029, "actor_loss": -8.756717681884766, "critic_loss": 0.023394914343953133, "reward": 0.070163793861866, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24333935976028442, 0.16198967397212982, 0.25192752480506897], "policy_updates": 39350, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7402.706539964, "contact_bce": 0.3121120035648346, "contact_force_loss": 0.03169025853276253, "terrain_level_mean": 3.182861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9998464584350586]} {"step": 39460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39460, "total_transitions": 161628160, "num_steps_per_env": 1, "wm_loss": 0.4271848201751709, "actor_loss": -8.717825889587402, "critic_loss": 0.026766199618577957, "reward": 0.07066924124956131, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24593164026737213, 0.16037532687187195, 0.25463417172431946], "policy_updates": 39360, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7406.215807379999, "contact_bce": 0.3125045597553253, "contact_force_loss": 0.03272602707147598, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9998464584350586]} {"step": 39470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39470, "total_transitions": 161669120, "num_steps_per_env": 1, "wm_loss": 0.42088961601257324, "actor_loss": -8.721549987792969, "critic_loss": 0.02485732175409794, "reward": 0.07081850618124008, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2484961599111557, 0.1607671082019806, 0.25217947363853455], "policy_updates": 39370, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7409.709362299, "contact_bce": 0.3071363568305969, "contact_force_loss": 0.031568799167871475, "terrain_level_mean": 3.18505859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9998464584350586]} {"step": 39480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39480, "total_transitions": 161710080, "num_steps_per_env": 1, "wm_loss": 0.44372087717056274, "actor_loss": -8.753925323486328, "critic_loss": 0.0222307275980711, "reward": 0.07080298662185669, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2503378093242645, 0.1622685194015503, 0.25343814492225647], "policy_updates": 39380, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7413.216618785999, "contact_bce": 0.30854663252830505, "contact_force_loss": 0.03247902914881706, "terrain_level_mean": 3.185791015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9998464584350586]} {"step": 39490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39490, "total_transitions": 161751040, "num_steps_per_env": 1, "wm_loss": 0.4487540125846863, "actor_loss": -8.749015808105469, "critic_loss": 0.020381124690175056, "reward": 0.07055237889289856, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2528632879257202, 0.16026552021503448, 0.25247591733932495], "policy_updates": 39390, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7416.731247072, "contact_bce": 0.3133679926395416, "contact_force_loss": 0.03282853588461876, "terrain_level_mean": 3.18408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9980573654174805]} {"step": 39500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39500, "total_transitions": 161792000, "num_steps_per_env": 1, "wm_loss": 0.4459086060523987, "actor_loss": -8.718194961547852, "critic_loss": 0.022216444835066795, "reward": 0.07062793523073196, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2476523220539093, 0.15940487384796143, 0.2512213885784149], "policy_updates": 39400, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7420.255407707, "contact_bce": 0.3120999336242676, "contact_force_loss": 0.03252987191081047, "terrain_level_mean": 3.18310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9980573654174805]} {"step": 39510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39510, "total_transitions": 161832960, "num_steps_per_env": 1, "wm_loss": 0.4491875469684601, "actor_loss": -8.705756187438965, "critic_loss": 0.023624559864401817, "reward": 0.07006999850273132, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24872852861881256, 0.16047392785549164, 0.25478553771972656], "policy_updates": 39410, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7423.80494079, "contact_bce": 0.3107685148715973, "contact_force_loss": 0.03252040222287178, "terrain_level_mean": 3.183349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9980573654174805]} {"step": 39520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39520, "total_transitions": 161873920, "num_steps_per_env": 1, "wm_loss": 0.4258933961391449, "actor_loss": -8.731803894042969, "critic_loss": 0.02429933100938797, "reward": 0.06998860090970993, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25449103116989136, 0.1600532978773117, 0.256833553314209], "policy_updates": 39420, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7427.3234513219995, "contact_bce": 0.31038498878479004, "contact_force_loss": 0.03178583085536957, "terrain_level_mean": 3.18310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9980573654174805]} {"step": 39530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39530, "total_transitions": 161914880, "num_steps_per_env": 1, "wm_loss": 0.42182961106300354, "actor_loss": -8.706521987915039, "critic_loss": 0.027224505320191383, "reward": 0.07034497708082199, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2510378956794739, 0.15906290709972382, 0.2515663802623749], "policy_updates": 39430, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7431.0984444489995, "contact_bce": 0.3160245716571808, "contact_force_loss": 0.03269387036561966, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9980573654174805]} {"step": 39540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39540, "total_transitions": 161955840, "num_steps_per_env": 1, "wm_loss": 0.4460591673851013, "actor_loss": -8.736241340637207, "critic_loss": 0.02619865909218788, "reward": 0.07031311094760895, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2530064284801483, 0.1585080325603485, 0.25745388865470886], "policy_updates": 39440, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7434.621364862, "contact_bce": 0.3142341673374176, "contact_force_loss": 0.03270449861884117, "terrain_level_mean": 3.1845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9980573654174805]} {"step": 39550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39550, "total_transitions": 161996800, "num_steps_per_env": 1, "wm_loss": 0.4601704180240631, "actor_loss": -8.749702453613281, "critic_loss": 0.0243843887001276, "reward": 0.07004905492067337, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2511110305786133, 0.15747712552547455, 0.2581528425216675], "policy_updates": 39450, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7438.134941061, "contact_bce": 0.3191523849964142, "contact_force_loss": 0.032706789672374725, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9993035793304443, 0.9998710751533508, 2.9980573654174805]} {"step": 39560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39560, "total_transitions": 162037760, "num_steps_per_env": 1, "wm_loss": 0.4392980933189392, "actor_loss": -8.666386604309082, "critic_loss": 0.02474810741841793, "reward": 0.06990047544240952, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25726377964019775, 0.16039811074733734, 0.2576061189174652], "policy_updates": 39460, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7441.652336216999, "contact_bce": 0.3096279799938202, "contact_force_loss": 0.032494258135557175, "terrain_level_mean": 3.183349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9993035793304443, 0.9993389844894409, 2.9980573654174805]} {"step": 39570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39570, "total_transitions": 162078720, "num_steps_per_env": 1, "wm_loss": 0.4217434525489807, "actor_loss": -8.687234878540039, "critic_loss": 0.0326165072619915, "reward": 0.06987225264310837, "falls": 5, "interval_steps": 10, "velocity_mae": [0.26253676414489746, 0.1618906408548355, 0.25958800315856934], "policy_updates": 39470, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7445.165424883, "contact_bce": 0.30808499455451965, "contact_force_loss": 0.03198337182402611, "terrain_level_mean": 3.182861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9993035793304443, 0.9993331432342529, 2.9980573654174805]} {"step": 39580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39580, "total_transitions": 162119680, "num_steps_per_env": 1, "wm_loss": 0.4428030252456665, "actor_loss": -8.733742713928223, "critic_loss": 0.02335197478532791, "reward": 0.07003186643123627, "falls": 7, "interval_steps": 10, "velocity_mae": [0.26331448554992676, 0.16300542652606964, 0.2573555111885071], "policy_updates": 39480, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7448.672141786, "contact_bce": 0.31104254722595215, "contact_force_loss": 0.032785117626190186, "terrain_level_mean": 3.1826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9993035793304443, 0.9993331432342529, 2.9980573654174805]} {"step": 39590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39590, "total_transitions": 162160640, "num_steps_per_env": 1, "wm_loss": 0.42294153571128845, "actor_loss": -8.720727920532227, "critic_loss": 0.02992265298962593, "reward": 0.07008233666419983, "falls": 4, "interval_steps": 10, "velocity_mae": [0.265292763710022, 0.159601092338562, 0.2577027380466461], "policy_updates": 39490, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7452.181104747, "contact_bce": 0.3137798607349396, "contact_force_loss": 0.03256525099277496, "terrain_level_mean": 3.182373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9993035793304443, 0.9993331432342529, 2.9980573654174805]} {"step": 39600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39600, "total_transitions": 162201600, "num_steps_per_env": 1, "wm_loss": 0.4291203022003174, "actor_loss": -8.746002197265625, "critic_loss": 0.02315930835902691, "reward": 0.0704239085316658, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2598501741886139, 0.15991930663585663, 0.2537177801132202], "policy_updates": 39500, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7455.697826414, "contact_bce": 0.3158498704433441, "contact_force_loss": 0.03259817510843277, "terrain_level_mean": 3.1826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9964185953140259, 0.9993331432342529, 2.9980573654174805]} {"step": 39610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39610, "total_transitions": 162242560, "num_steps_per_env": 1, "wm_loss": 0.4263473153114319, "actor_loss": -8.706147193908691, "critic_loss": 0.02269146405160427, "reward": 0.0711924135684967, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2530381977558136, 0.15846048295497894, 0.2541927695274353], "policy_updates": 39510, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7459.2016659579995, "contact_bce": 0.3155909776687622, "contact_force_loss": 0.032856810837984085, "terrain_level_mean": 3.18310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9938310384750366, 0.9993331432342529, 2.9980573654174805]} {"step": 39620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39620, "total_transitions": 162283520, "num_steps_per_env": 1, "wm_loss": 0.4326164424419403, "actor_loss": -8.76266098022461, "critic_loss": 0.02684711292386055, "reward": 0.07070442289113998, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2540903687477112, 0.15839722752571106, 0.25836417078971863], "policy_updates": 39520, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7462.703651393999, "contact_bce": 0.3165115714073181, "contact_force_loss": 0.03355097770690918, "terrain_level_mean": 3.1826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9938310384750366, 0.9993331432342529, 2.9980573654174805]} {"step": 39630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39630, "total_transitions": 162324480, "num_steps_per_env": 1, "wm_loss": 0.4665168225765228, "actor_loss": -8.73293399810791, "critic_loss": 0.021201372146606445, "reward": 0.07041888684034348, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2551872432231903, 0.15757928788661957, 0.25573980808258057], "policy_updates": 39530, "skipped_updates": 0, "invalid_env_resets": 67, "elapsed_s": 7466.217198885, "contact_bce": 0.3176781237125397, "contact_force_loss": 0.033154454082250595, "terrain_level_mean": 3.18408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9938310384750366, 0.9993331432342529, 2.9980573654174805]} RECOVERY reset 1 invalid environments; first IDs=[978] {"step": 39640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39640, "total_transitions": 162365440, "num_steps_per_env": 1, "wm_loss": 0.4606066048145294, "actor_loss": -8.703095436096191, "critic_loss": 0.035101424902677536, "reward": 0.07059217989444733, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25501129031181335, 0.15764549374580383, 0.252707839012146], "policy_updates": 39540, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7469.75023532, "contact_bce": 0.31293752789497375, "contact_force_loss": 0.03338600695133209, "terrain_level_mean": 3.18408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9978500604629517, 0.9993331432342529, 2.9980573654174805]} {"step": 39650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39650, "total_transitions": 162406400, "num_steps_per_env": 1, "wm_loss": 0.41578590869903564, "actor_loss": -8.687660217285156, "critic_loss": 0.03646659478545189, "reward": 0.07062874734401703, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25028637051582336, 0.1580490618944168, 0.25583988428115845], "policy_updates": 39550, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7473.260762108, "contact_bce": 0.3130430281162262, "contact_force_loss": 0.031955618411302567, "terrain_level_mean": 3.18359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9978500604629517, 0.9993331432342529, 2.9980573654174805]} {"step": 39660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39660, "total_transitions": 162447360, "num_steps_per_env": 1, "wm_loss": 0.42069464921951294, "actor_loss": -8.75634765625, "critic_loss": 0.02508339285850525, "reward": 0.07058828324079514, "falls": 7, "interval_steps": 10, "velocity_mae": [0.250535786151886, 0.157280832529068, 0.26071470975875854], "policy_updates": 39560, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7476.776011051999, "contact_bce": 0.31176483631134033, "contact_force_loss": 0.03283597156405449, "terrain_level_mean": 3.182373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9978500604629517, 0.9993331432342529, 2.9980573654174805]} {"step": 39670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39670, "total_transitions": 162488320, "num_steps_per_env": 1, "wm_loss": 0.43112197518348694, "actor_loss": -8.716830253601074, "critic_loss": 0.030887192115187645, "reward": 0.07037654519081116, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2512910068035126, 0.1601293832063675, 0.2612909972667694], "policy_updates": 39570, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7480.284412010999, "contact_bce": 0.316589891910553, "contact_force_loss": 0.03310265392065048, "terrain_level_mean": 3.18310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9978500604629517, 0.9993331432342529, 2.9980573654174805]} {"step": 39680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39680, "total_transitions": 162529280, "num_steps_per_env": 1, "wm_loss": 0.4614851474761963, "actor_loss": -8.690949440002441, "critic_loss": 0.019982069730758667, "reward": 0.07084769755601883, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24968329071998596, 0.15965496003627777, 0.25587373971939087], "policy_updates": 39580, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7483.822867964999, "contact_bce": 0.31840723752975464, "contact_force_loss": 0.033896513283252716, "terrain_level_mean": 3.18408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9978500604629517, 0.9993331432342529, 2.9980573654174805]} {"step": 39690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39690, "total_transitions": 162570240, "num_steps_per_env": 1, "wm_loss": 0.44029131531715393, "actor_loss": -8.742204666137695, "critic_loss": 0.025433287024497986, "reward": 0.07117383182048798, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24733954668045044, 0.15794993937015533, 0.2561417818069458], "policy_updates": 39590, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7487.338734217999, "contact_bce": 0.31380346417427063, "contact_force_loss": 0.03312163054943085, "terrain_level_mean": 3.183837890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9978500604629517, 0.9993331432342529, 2.9980573654174805]} {"step": 39700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39700, "total_transitions": 162611200, "num_steps_per_env": 1, "wm_loss": 0.4266817569732666, "actor_loss": -8.711051940917969, "critic_loss": 0.022799380123615265, "reward": 0.07123972475528717, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2476746290922165, 0.1579890102148056, 0.2541903555393219], "policy_updates": 39600, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7490.860991193999, "contact_bce": 0.31423231959342957, "contact_force_loss": 0.0328514538705349, "terrain_level_mean": 3.182861328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9978500604629517, 0.9987626075744629, 2.9980573654174805]} {"step": 39710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39710, "total_transitions": 162652160, "num_steps_per_env": 1, "wm_loss": 0.43917885422706604, "actor_loss": -8.77657413482666, "critic_loss": 0.022863158956170082, "reward": 0.07177624851465225, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24559436738491058, 0.15524937212467194, 0.2535612881183624], "policy_updates": 39610, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7494.378365326, "contact_bce": 0.31342577934265137, "contact_force_loss": 0.03335530310869217, "terrain_level_mean": 3.183349609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9978500604629517, 0.9987626075744629, 2.9980573654174805]} {"step": 39720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39720, "total_transitions": 162693120, "num_steps_per_env": 1, "wm_loss": 0.45338547229766846, "actor_loss": -8.732719421386719, "critic_loss": 0.023457035422325134, "reward": 0.07125096768140793, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24714195728302002, 0.15828661620616913, 0.25403523445129395], "policy_updates": 39620, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7497.883350151, "contact_bce": 0.31425657868385315, "contact_force_loss": 0.03363236039876938, "terrain_level_mean": 3.184814453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9978500604629517, 0.9987626075744629, 2.9980573654174805]} {"step": 39730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39730, "total_transitions": 162734080, "num_steps_per_env": 1, "wm_loss": 0.42419081926345825, "actor_loss": -8.652231216430664, "critic_loss": 0.03147614374756813, "reward": 0.07146303355693817, "falls": 4, "interval_steps": 10, "velocity_mae": [0.244760662317276, 0.15975823998451233, 0.25571945309638977], "policy_updates": 39630, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7501.393515172999, "contact_bce": 0.313400536775589, "contact_force_loss": 0.032128509134054184, "terrain_level_mean": 3.18505859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9978500604629517, 0.9987626075744629, 2.9980573654174805]} {"step": 39740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39740, "total_transitions": 162775040, "num_steps_per_env": 1, "wm_loss": 0.46580612659454346, "actor_loss": -8.702178955078125, "critic_loss": 0.029379213228821754, "reward": 0.07135728746652603, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24649366736412048, 0.15913470089435577, 0.25799405574798584], "policy_updates": 39640, "skipped_updates": 0, "invalid_env_resets": 68, "elapsed_s": 7504.89773722, "contact_bce": 0.31665170192718506, "contact_force_loss": 0.03315697982907295, "terrain_level_mean": 3.185302734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.9980573654174805]} RECOVERY reset 1 invalid environments; first IDs=[755] {"step": 39750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39750, "total_transitions": 162816000, "num_steps_per_env": 1, "wm_loss": 0.44981563091278076, "actor_loss": -8.702407836914062, "critic_loss": 0.028856148943305016, "reward": 0.07113034278154373, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2506100833415985, 0.15763363242149353, 0.25568678975105286], "policy_updates": 39650, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7508.433274282999, "contact_bce": 0.3159472644329071, "contact_force_loss": 0.033396538347005844, "terrain_level_mean": 3.1845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39760, "total_transitions": 162856960, "num_steps_per_env": 1, "wm_loss": 0.42129141092300415, "actor_loss": -8.728935241699219, "critic_loss": 0.019450202584266663, "reward": 0.07135975360870361, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24864093959331512, 0.15988785028457642, 0.25660789012908936], "policy_updates": 39660, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7511.931250482, "contact_bce": 0.31594035029411316, "contact_force_loss": 0.033022183924913406, "terrain_level_mean": 3.186279296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39770, "total_transitions": 162897920, "num_steps_per_env": 1, "wm_loss": 0.4448588192462921, "actor_loss": -8.756303787231445, "critic_loss": 0.023854760453104973, "reward": 0.07138191908597946, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24754348397254944, 0.15776999294757843, 0.25210660696029663], "policy_updates": 39670, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7515.422910048999, "contact_bce": 0.31391727924346924, "contact_force_loss": 0.03225491940975189, "terrain_level_mean": 3.186279296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39780, "total_transitions": 162938880, "num_steps_per_env": 1, "wm_loss": 0.40151041746139526, "actor_loss": -8.779179573059082, "critic_loss": 0.03383692726492882, "reward": 0.07118266075849533, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2456810623407364, 0.1550072431564331, 0.2532650828361511], "policy_updates": 39680, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7518.920166315, "contact_bce": 0.3117373585700989, "contact_force_loss": 0.032628271728754044, "terrain_level_mean": 3.187255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39790, "total_transitions": 162979840, "num_steps_per_env": 1, "wm_loss": 0.4209652841091156, "actor_loss": -8.731361389160156, "critic_loss": 0.027035340666770935, "reward": 0.07085753977298737, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2466379702091217, 0.15567874908447266, 0.25828075408935547], "policy_updates": 39690, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7522.420368851999, "contact_bce": 0.3117070198059082, "contact_force_loss": 0.03203554451465607, "terrain_level_mean": 3.187744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39800, "total_transitions": 163020800, "num_steps_per_env": 1, "wm_loss": 0.42189547419548035, "actor_loss": -8.73912239074707, "critic_loss": 0.021734334528446198, "reward": 0.07076442986726761, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24764281511306763, 0.1561833620071411, 0.2618453800678253], "policy_updates": 39700, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7525.917762450999, "contact_bce": 0.312558650970459, "contact_force_loss": 0.033188510686159134, "terrain_level_mean": 3.18798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39810, "total_transitions": 163061760, "num_steps_per_env": 1, "wm_loss": 0.42064306139945984, "actor_loss": -8.719669342041016, "critic_loss": 0.03018788993358612, "reward": 0.07129689306020737, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24501587450504303, 0.1536945253610611, 0.2543661892414093], "policy_updates": 39710, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7529.418554733, "contact_bce": 0.3093865215778351, "contact_force_loss": 0.03191488981246948, "terrain_level_mean": 3.188720703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39820, "total_transitions": 163102720, "num_steps_per_env": 1, "wm_loss": 0.43175485730171204, "actor_loss": -8.769975662231445, "critic_loss": 0.01895163021981716, "reward": 0.07101486623287201, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2467176616191864, 0.15593262016773224, 0.2559562921524048], "policy_updates": 39720, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7532.919485920999, "contact_bce": 0.3113767206668854, "contact_force_loss": 0.032577257603406906, "terrain_level_mean": 3.1884765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39830, "total_transitions": 163143680, "num_steps_per_env": 1, "wm_loss": 0.4215729832649231, "actor_loss": -8.709747314453125, "critic_loss": 0.029430720955133438, "reward": 0.07128607481718063, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24873857200145721, 0.15662045776844025, 0.25092262029647827], "policy_updates": 39730, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7536.4185086689995, "contact_bce": 0.30991131067276, "contact_force_loss": 0.03283684328198433, "terrain_level_mean": 3.187744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39840, "total_transitions": 163184640, "num_steps_per_env": 1, "wm_loss": 0.43079525232315063, "actor_loss": -8.716170310974121, "critic_loss": 0.03575409576296806, "reward": 0.07092514634132385, "falls": 3, "interval_steps": 10, "velocity_mae": [0.250967413187027, 0.15640078485012054, 0.24942971765995026], "policy_updates": 39740, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7539.922618144, "contact_bce": 0.31579023599624634, "contact_force_loss": 0.03272389993071556, "terrain_level_mean": 3.187744140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39850, "total_transitions": 163225600, "num_steps_per_env": 1, "wm_loss": 0.42743539810180664, "actor_loss": -8.680431365966797, "critic_loss": 0.02756095491349697, "reward": 0.07081598043441772, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25787949562072754, 0.1574094593524933, 0.25031325221061707], "policy_updates": 39750, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7543.4226906409995, "contact_bce": 0.3146389126777649, "contact_force_loss": 0.033539216965436935, "terrain_level_mean": 3.189208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} Warning: EPA horizon = 24 isn't large enough. {"step": 39860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39860, "total_transitions": 163266560, "num_steps_per_env": 1, "wm_loss": 0.4409056603908539, "actor_loss": -8.729227066040039, "critic_loss": 0.024513930082321167, "reward": 0.07060598582029343, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25706854462623596, 0.1584969460964203, 0.25535956025123596], "policy_updates": 39760, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7546.922349681, "contact_bce": 0.3138945698738098, "contact_force_loss": 0.03286667913198471, "terrain_level_mean": 3.18896484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39870, "total_transitions": 163307520, "num_steps_per_env": 1, "wm_loss": 0.41421160101890564, "actor_loss": -8.692014694213867, "critic_loss": 0.039698611944913864, "reward": 0.07101111859083176, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2549275755882263, 0.15330056846141815, 0.2527695596218109], "policy_updates": 39770, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7550.425013317, "contact_bce": 0.31517133116722107, "contact_force_loss": 0.03288113698363304, "terrain_level_mean": 3.189453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39880, "total_transitions": 163348480, "num_steps_per_env": 1, "wm_loss": 0.4491584599018097, "actor_loss": -8.699557304382324, "critic_loss": 0.028298664838075638, "reward": 0.07093372941017151, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2525339126586914, 0.15176349878311157, 0.25374636054039], "policy_updates": 39780, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7553.92741023, "contact_bce": 0.3104724586009979, "contact_force_loss": 0.03323731943964958, "terrain_level_mean": 3.189697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39890, "total_transitions": 163389440, "num_steps_per_env": 1, "wm_loss": 0.4212993383407593, "actor_loss": -8.740797996520996, "critic_loss": 0.02254185453057289, "reward": 0.0705329105257988, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25424888730049133, 0.15476207435131073, 0.2530224025249481], "policy_updates": 39790, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7557.42712106, "contact_bce": 0.31316429376602173, "contact_force_loss": 0.03223039209842682, "terrain_level_mean": 3.190185546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39900, "total_transitions": 163430400, "num_steps_per_env": 1, "wm_loss": 0.474693238735199, "actor_loss": -8.727580070495605, "critic_loss": 0.029109453782439232, "reward": 0.07090049237012863, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25204503536224365, 0.15438328683376312, 0.2529357373714447], "policy_updates": 39800, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7560.928600169, "contact_bce": 0.3136689066886902, "contact_force_loss": 0.03341515362262726, "terrain_level_mean": 3.18994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39910, "total_transitions": 163471360, "num_steps_per_env": 1, "wm_loss": 0.43603724241256714, "actor_loss": -8.688265800476074, "critic_loss": 0.02686392329633236, "reward": 0.07103417068719864, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24718351662158966, 0.15197694301605225, 0.25664564967155457], "policy_updates": 39810, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7564.427243464999, "contact_bce": 0.31556180119514465, "contact_force_loss": 0.03287819027900696, "terrain_level_mean": 3.189697265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39920, "total_transitions": 163512320, "num_steps_per_env": 1, "wm_loss": 0.39557287096977234, "actor_loss": -8.722992897033691, "critic_loss": 0.022316062822937965, "reward": 0.0708375871181488, "falls": 1, "interval_steps": 10, "velocity_mae": [0.252401202917099, 0.1514415293931961, 0.2524462640285492], "policy_updates": 39820, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7567.930130694, "contact_bce": 0.31059473752975464, "contact_force_loss": 0.031674887984991074, "terrain_level_mean": 3.191162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39930, "total_transitions": 163553280, "num_steps_per_env": 1, "wm_loss": 0.44157806038856506, "actor_loss": -8.737550735473633, "critic_loss": 0.024837283417582512, "reward": 0.07018492370843887, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25683486461639404, 0.1538912057876587, 0.25545600056648254], "policy_updates": 39830, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7571.436522196999, "contact_bce": 0.3132779598236084, "contact_force_loss": 0.03347359970211983, "terrain_level_mean": 3.191162109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39940, "total_transitions": 163594240, "num_steps_per_env": 1, "wm_loss": 0.4029240012168884, "actor_loss": -8.766300201416016, "critic_loss": 0.025160742923617363, "reward": 0.07015515118837357, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25679925084114075, 0.15294182300567627, 0.25748705863952637], "policy_updates": 39840, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7574.940832492, "contact_bce": 0.3090061545372009, "contact_force_loss": 0.03234481438994408, "terrain_level_mean": 3.19140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39950, "total_transitions": 163635200, "num_steps_per_env": 1, "wm_loss": 0.419633150100708, "actor_loss": -8.739015579223633, "critic_loss": 0.025637386366724968, "reward": 0.07022830098867416, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25837376713752747, 0.1542406678199768, 0.25521212816238403], "policy_updates": 39850, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7578.444436821999, "contact_bce": 0.3141986131668091, "contact_force_loss": 0.03262356296181679, "terrain_level_mean": 3.19091796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39960, "total_transitions": 163676160, "num_steps_per_env": 1, "wm_loss": 0.40343180298805237, "actor_loss": -8.751710891723633, "critic_loss": 0.02432006411254406, "reward": 0.0709061548113823, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2529947757720947, 0.15388627350330353, 0.2530922591686249], "policy_updates": 39860, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7581.949606239, "contact_bce": 0.3099985122680664, "contact_force_loss": 0.033066075295209885, "terrain_level_mean": 3.19189453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9978500604629517, 0.9989591836929321, 2.996657609939575]} {"step": 39970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39970, "total_transitions": 163717120, "num_steps_per_env": 1, "wm_loss": 0.4728870093822479, "actor_loss": -8.686187744140625, "critic_loss": 0.023016123101115227, "reward": 0.0709020122885704, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2491065114736557, 0.1524481475353241, 0.2547253966331482], "policy_updates": 39870, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7585.448432931999, "contact_bce": 0.3171100914478302, "contact_force_loss": 0.034186363220214844, "terrain_level_mean": 3.193115234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9978500604629517, 0.9991878271102905, 2.996657609939575]} {"step": 39980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39980, "total_transitions": 163758080, "num_steps_per_env": 1, "wm_loss": 0.437933087348938, "actor_loss": -8.700577735900879, "critic_loss": 0.03419480472803116, "reward": 0.07114170491695404, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24916261434555054, 0.15221382677555084, 0.25078102946281433], "policy_updates": 39880, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7588.966460289, "contact_bce": 0.3117764890193939, "contact_force_loss": 0.033148638904094696, "terrain_level_mean": 3.1943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9978500604629517, 0.9991878271102905, 2.996657609939575]} {"step": 39990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 39990, "total_transitions": 163799040, "num_steps_per_env": 1, "wm_loss": 0.4446270167827606, "actor_loss": -8.73576545715332, "critic_loss": 0.026916248723864555, "reward": 0.07117615640163422, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25017714500427246, 0.1547640860080719, 0.25080606341362], "policy_updates": 39890, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7592.477488678, "contact_bce": 0.3065943121910095, "contact_force_loss": 0.03219002112746239, "terrain_level_mean": 3.19482421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.996657609939575]} {"step": 40000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40000, "total_transitions": 163840000, "num_steps_per_env": 1, "wm_loss": 0.435573935508728, "actor_loss": -8.743471145629883, "critic_loss": 0.02225389890372753, "reward": 0.07109881192445755, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24747855961322784, 0.15467192232608795, 0.25263404846191406], "policy_updates": 39900, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7595.969298966999, "contact_bce": 0.3145011365413666, "contact_force_loss": 0.033180736005306244, "terrain_level_mean": 3.195068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.996657609939575]} {"step": 40010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40010, "total_transitions": 163880960, "num_steps_per_env": 1, "wm_loss": 0.43718695640563965, "actor_loss": -8.746196746826172, "critic_loss": 0.04067237302660942, "reward": 0.07081683725118637, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24489812552928925, 0.15553167462348938, 0.2541015148162842], "policy_updates": 39910, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7599.5093560099995, "contact_bce": 0.3152318000793457, "contact_force_loss": 0.03367307782173157, "terrain_level_mean": 3.195556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.996657609939575]} {"step": 40020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40020, "total_transitions": 163921920, "num_steps_per_env": 1, "wm_loss": 0.42762577533721924, "actor_loss": -8.739630699157715, "critic_loss": 0.020667854696512222, "reward": 0.07083819061517715, "falls": 0, "interval_steps": 10, "velocity_mae": [0.2401125729084015, 0.1546822041273117, 0.2551213502883911], "policy_updates": 39920, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7603.024314752, "contact_bce": 0.31678450107574463, "contact_force_loss": 0.03334738686680794, "terrain_level_mean": 3.197509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.996657609939575]} {"step": 40030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40030, "total_transitions": 163962880, "num_steps_per_env": 1, "wm_loss": 0.4301721751689911, "actor_loss": -8.703217506408691, "critic_loss": 0.025297466665506363, "reward": 0.07058268040418625, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24549442529678345, 0.15294736623764038, 0.25645866990089417], "policy_updates": 39930, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7606.793854496, "contact_bce": 0.3168511688709259, "contact_force_loss": 0.033586204051971436, "terrain_level_mean": 3.198486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.9962949752807617]} {"step": 40040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40040, "total_transitions": 164003840, "num_steps_per_env": 1, "wm_loss": 0.445176899433136, "actor_loss": -8.75455379486084, "critic_loss": 0.02561095915734768, "reward": 0.07106810808181763, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24663546681404114, 0.15296895802021027, 0.25336894392967224], "policy_updates": 39940, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7610.322094358, "contact_bce": 0.3157923221588135, "contact_force_loss": 0.032907404005527496, "terrain_level_mean": 3.1982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.9962949752807617]} {"step": 40050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40050, "total_transitions": 164044800, "num_steps_per_env": 1, "wm_loss": 0.4388112723827362, "actor_loss": -8.733530044555664, "critic_loss": 0.027571965008974075, "reward": 0.07093734294176102, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2502822279930115, 0.15511147677898407, 0.25432488322257996], "policy_updates": 39950, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7613.834474888, "contact_bce": 0.3152042627334595, "contact_force_loss": 0.032904334366321564, "terrain_level_mean": 3.19873046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.9962949752807617]} {"step": 40060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40060, "total_transitions": 164085760, "num_steps_per_env": 1, "wm_loss": 0.4129471480846405, "actor_loss": -8.731344223022461, "critic_loss": 0.029164433479309082, "reward": 0.070546954870224, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25002503395080566, 0.15720327198505402, 0.2513205409049988], "policy_updates": 39960, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7617.348368366, "contact_bce": 0.31425586342811584, "contact_force_loss": 0.03178149834275246, "terrain_level_mean": 3.199462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.9962949752807617]} {"step": 40070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40070, "total_transitions": 164126720, "num_steps_per_env": 1, "wm_loss": 0.4267750084400177, "actor_loss": -8.69967269897461, "critic_loss": 0.020423652604222298, "reward": 0.07085396349430084, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24904893338680267, 0.15772363543510437, 0.2571922540664673], "policy_updates": 39970, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7620.845817738999, "contact_bce": 0.3151695430278778, "contact_force_loss": 0.03304929658770561, "terrain_level_mean": 3.2001953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.995413064956665, 0.9991878271102905, 2.9962949752807617]} {"step": 40080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40080, "total_transitions": 164167680, "num_steps_per_env": 1, "wm_loss": 0.44741061329841614, "actor_loss": -8.794195175170898, "critic_loss": 0.030515972524881363, "reward": 0.07080131024122238, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24839510023593903, 0.15706409513950348, 0.2549441456794739], "policy_updates": 39980, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7624.363610777, "contact_bce": 0.3175281286239624, "contact_force_loss": 0.03283120319247246, "terrain_level_mean": 3.19921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40090, "total_transitions": 164208640, "num_steps_per_env": 1, "wm_loss": 0.3909674286842346, "actor_loss": -8.716039657592773, "critic_loss": 0.018058380112051964, "reward": 0.0711323544383049, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2461434155702591, 0.15627802908420563, 0.2532491385936737], "policy_updates": 39990, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7627.883772335999, "contact_bce": 0.30830657482147217, "contact_force_loss": 0.03210791200399399, "terrain_level_mean": 3.19970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40100, "total_transitions": 164249600, "num_steps_per_env": 1, "wm_loss": 0.4008464813232422, "actor_loss": -8.724072456359863, "critic_loss": 0.029901912435889244, "reward": 0.0709439218044281, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2467845380306244, 0.15566442906856537, 0.2570500075817108], "policy_updates": 40000, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7631.385826979, "contact_bce": 0.3142957091331482, "contact_force_loss": 0.033347561955451965, "terrain_level_mean": 3.19970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40110, "total_transitions": 164290560, "num_steps_per_env": 1, "wm_loss": 0.4199255108833313, "actor_loss": -8.703020095825195, "critic_loss": 0.025930209085345268, "reward": 0.07140090316534042, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24548976123332977, 0.15461967885494232, 0.2550651729106903], "policy_updates": 40010, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7634.909323043, "contact_bce": 0.31622278690338135, "contact_force_loss": 0.03199845924973488, "terrain_level_mean": 3.198974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40120, "total_transitions": 164331520, "num_steps_per_env": 1, "wm_loss": 0.4217544496059418, "actor_loss": -8.732184410095215, "critic_loss": 0.017862198874354362, "reward": 0.07154951989650726, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24774621427059174, 0.15563182532787323, 0.25086620450019836], "policy_updates": 40020, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7638.421890645, "contact_bce": 0.31498080492019653, "contact_force_loss": 0.03254908323287964, "terrain_level_mean": 3.1982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40130, "total_transitions": 164372480, "num_steps_per_env": 1, "wm_loss": 0.4119561016559601, "actor_loss": -8.760356903076172, "critic_loss": 0.026982827112078667, "reward": 0.0713716521859169, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24832583963871002, 0.1541520357131958, 0.2516185939311981], "policy_updates": 40030, "skipped_updates": 0, "invalid_env_resets": 69, "elapsed_s": 7641.930178279, "contact_bce": 0.316850483417511, "contact_force_loss": 0.03226456791162491, "terrain_level_mean": 3.197509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} RECOVERY reset 1 invalid environments; first IDs=[1281] {"step": 40140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40140, "total_transitions": 164413440, "num_steps_per_env": 1, "wm_loss": 0.4322112500667572, "actor_loss": -8.720928192138672, "critic_loss": 0.022900549694895744, "reward": 0.07140868157148361, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24970851838588715, 0.15314602851867676, 0.25052034854888916], "policy_updates": 40040, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7645.4453235109995, "contact_bce": 0.3135765790939331, "contact_force_loss": 0.032009951770305634, "terrain_level_mean": 3.19775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40150, "total_transitions": 164454400, "num_steps_per_env": 1, "wm_loss": 0.4208061993122101, "actor_loss": -8.78646183013916, "critic_loss": 0.022097624838352203, "reward": 0.07130878418684006, "falls": 0, "interval_steps": 10, "velocity_mae": [0.2507878839969635, 0.15619587898254395, 0.24787624180316925], "policy_updates": 40050, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7648.9442737, "contact_bce": 0.3180433213710785, "contact_force_loss": 0.032979365438222885, "terrain_level_mean": 3.198486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40160, "total_transitions": 164495360, "num_steps_per_env": 1, "wm_loss": 0.4231744110584259, "actor_loss": -8.721790313720703, "critic_loss": 0.032376743853092194, "reward": 0.07079773396253586, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24909880757331848, 0.15625222027301788, 0.2512957453727722], "policy_updates": 40060, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7652.452853694, "contact_bce": 0.31379231810569763, "contact_force_loss": 0.03246832638978958, "terrain_level_mean": 3.198486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40170, "total_transitions": 164536320, "num_steps_per_env": 1, "wm_loss": 0.4218582212924957, "actor_loss": -8.71172046661377, "critic_loss": 0.03240582346916199, "reward": 0.07098089903593063, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24212580919265747, 0.15522173047065735, 0.2509913146495819], "policy_updates": 40070, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7655.957496616999, "contact_bce": 0.3081754744052887, "contact_force_loss": 0.03269688040018082, "terrain_level_mean": 3.1982421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40180, "total_transitions": 164577280, "num_steps_per_env": 1, "wm_loss": 0.4491857588291168, "actor_loss": -8.731746673583984, "critic_loss": 0.02695789374411106, "reward": 0.07137774676084518, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24048063158988953, 0.15309011936187744, 0.25385257601737976], "policy_updates": 40080, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7659.455947797, "contact_bce": 0.31535157561302185, "contact_force_loss": 0.0334913395345211, "terrain_level_mean": 3.19921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40190, "total_transitions": 164618240, "num_steps_per_env": 1, "wm_loss": 0.4303503930568695, "actor_loss": -8.726097106933594, "critic_loss": 0.02864598110318184, "reward": 0.07170242816209793, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23855912685394287, 0.15417592227458954, 0.25257357954978943], "policy_updates": 40090, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7662.957032466999, "contact_bce": 0.3151014745235443, "contact_force_loss": 0.03269386664032936, "terrain_level_mean": 3.198974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40200, "total_transitions": 164659200, "num_steps_per_env": 1, "wm_loss": 0.4257999062538147, "actor_loss": -8.732097625732422, "critic_loss": 0.025951189920306206, "reward": 0.0713469460606575, "falls": 3, "interval_steps": 10, "velocity_mae": [0.244377002120018, 0.15311652421951294, 0.2555604875087738], "policy_updates": 40100, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7666.458714091, "contact_bce": 0.3119390308856964, "contact_force_loss": 0.03253025561571121, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9962949752807617]} {"step": 40210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40210, "total_transitions": 164700160, "num_steps_per_env": 1, "wm_loss": 0.4431277811527252, "actor_loss": -8.715185165405273, "critic_loss": 0.02141326107084751, "reward": 0.07091747224330902, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24915191531181335, 0.15728801488876343, 0.254885733127594], "policy_updates": 40110, "skipped_updates": 0, "invalid_env_resets": 70, "elapsed_s": 7669.9573708729995, "contact_bce": 0.31690749526023865, "contact_force_loss": 0.03352153301239014, "terrain_level_mean": 3.19970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.991915702819824]} RECOVERY reset 1 invalid environments; first IDs=[2055] {"step": 40220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40220, "total_transitions": 164741120, "num_steps_per_env": 1, "wm_loss": 0.4019773304462433, "actor_loss": -8.730916976928711, "critic_loss": 0.02115180715918541, "reward": 0.07099618762731552, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24727144837379456, 0.15688952803611755, 0.25647059082984924], "policy_updates": 40120, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7673.476701072999, "contact_bce": 0.3149068355560303, "contact_force_loss": 0.03174734488129616, "terrain_level_mean": 3.19970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40230, "total_transitions": 164782080, "num_steps_per_env": 1, "wm_loss": 0.4178946614265442, "actor_loss": -8.773365020751953, "critic_loss": 0.030084827914834023, "reward": 0.07087885588407516, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24716787040233612, 0.1572015881538391, 0.2553989887237549], "policy_updates": 40130, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7676.98962178, "contact_bce": 0.31506282091140747, "contact_force_loss": 0.03221704065799713, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40240, "total_transitions": 164823040, "num_steps_per_env": 1, "wm_loss": 0.41324862837791443, "actor_loss": -8.743125915527344, "critic_loss": 0.02711045742034912, "reward": 0.07067807018756866, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24759206175804138, 0.15822753310203552, 0.25635582208633423], "policy_updates": 40140, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7680.499569801999, "contact_bce": 0.3162103593349457, "contact_force_loss": 0.03232589736580849, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40250, "total_transitions": 164864000, "num_steps_per_env": 1, "wm_loss": 0.42053255438804626, "actor_loss": -8.724889755249023, "critic_loss": 0.037216223776340485, "reward": 0.0702923908829689, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2494126409292221, 0.16006100177764893, 0.2568298578262329], "policy_updates": 40150, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7684.002917494, "contact_bce": 0.3142320513725281, "contact_force_loss": 0.0323936827480793, "terrain_level_mean": 3.2001953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40260, "total_transitions": 164904960, "num_steps_per_env": 1, "wm_loss": 0.42108431458473206, "actor_loss": -8.751349449157715, "critic_loss": 0.030508458614349365, "reward": 0.0706721693277359, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2465018481016159, 0.15933743119239807, 0.25494131445884705], "policy_updates": 40160, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7687.519002515, "contact_bce": 0.30769747495651245, "contact_force_loss": 0.032734572887420654, "terrain_level_mean": 3.19921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40270, "total_transitions": 164945920, "num_steps_per_env": 1, "wm_loss": 0.43410786986351013, "actor_loss": -8.721503257751465, "critic_loss": 0.024332402274012566, "reward": 0.07048242539167404, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24451124668121338, 0.15816791355609894, 0.25389400124549866], "policy_updates": 40170, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7691.03536981, "contact_bce": 0.31696486473083496, "contact_force_loss": 0.033105820417404175, "terrain_level_mean": 3.200439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40280, "total_transitions": 164986880, "num_steps_per_env": 1, "wm_loss": 0.43349507451057434, "actor_loss": -8.73756217956543, "critic_loss": 0.026559485122561455, "reward": 0.07072070240974426, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2407114952802658, 0.16109924018383026, 0.2565511167049408], "policy_updates": 40180, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7694.5458923119995, "contact_bce": 0.31024762988090515, "contact_force_loss": 0.032233040779829025, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40290, "total_transitions": 165027840, "num_steps_per_env": 1, "wm_loss": 0.41545090079307556, "actor_loss": -8.78043270111084, "critic_loss": 0.025937331840395927, "reward": 0.07084810733795166, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24133887887001038, 0.15734544396400452, 0.25544220209121704], "policy_updates": 40190, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7698.054917267999, "contact_bce": 0.31264275312423706, "contact_force_loss": 0.03260479122400284, "terrain_level_mean": 3.19970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40300, "total_transitions": 165068800, "num_steps_per_env": 1, "wm_loss": 0.4420771300792694, "actor_loss": -8.682608604431152, "critic_loss": 0.02467995695769787, "reward": 0.07116606086492538, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2354680448770523, 0.1567545235157013, 0.2567490339279175], "policy_updates": 40200, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7701.592921922, "contact_bce": 0.31285297870635986, "contact_force_loss": 0.03275049850344658, "terrain_level_mean": 3.200927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40310, "total_transitions": 165109760, "num_steps_per_env": 1, "wm_loss": 0.4215640723705292, "actor_loss": -8.738694190979004, "critic_loss": 0.0293497946113348, "reward": 0.0712035521864891, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23705986142158508, 0.15747201442718506, 0.256824254989624], "policy_updates": 40210, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7705.103204034, "contact_bce": 0.3129369616508484, "contact_force_loss": 0.03193100541830063, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40320, "total_transitions": 165150720, "num_steps_per_env": 1, "wm_loss": 0.44954028725624084, "actor_loss": -8.716343879699707, "critic_loss": 0.02345695160329342, "reward": 0.07138232886791229, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23531368374824524, 0.1546722799539566, 0.2562125027179718], "policy_updates": 40220, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7708.615727179999, "contact_bce": 0.31631332635879517, "contact_force_loss": 0.033301278948783875, "terrain_level_mean": 3.19970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9976539611816406, 0.9991878271102905, 2.9971022605895996]} {"step": 40330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40330, "total_transitions": 165191680, "num_steps_per_env": 1, "wm_loss": 0.4276696741580963, "actor_loss": -8.672782897949219, "critic_loss": 0.04155474156141281, "reward": 0.07159917801618576, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23865002393722534, 0.15446552634239197, 0.2509007155895233], "policy_updates": 40230, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7712.121639764, "contact_bce": 0.3171725869178772, "contact_force_loss": 0.03283986449241638, "terrain_level_mean": 3.200927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9976539611816406, 0.9985909461975098, 2.9971022605895996]} {"step": 40340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40340, "total_transitions": 165232640, "num_steps_per_env": 1, "wm_loss": 0.4351978600025177, "actor_loss": -8.809651374816895, "critic_loss": 0.016995832324028015, "reward": 0.0713750347495079, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24228762090206146, 0.15599152445793152, 0.2522721290588379], "policy_updates": 40240, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7715.623409666, "contact_bce": 0.3105478286743164, "contact_force_loss": 0.03218093886971474, "terrain_level_mean": 3.201416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9976539611816406, 0.9985909461975098, 2.998311996459961]} {"step": 40350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40350, "total_transitions": 165273600, "num_steps_per_env": 1, "wm_loss": 0.39523160457611084, "actor_loss": -8.794536590576172, "critic_loss": 0.021648110821843147, "reward": 0.07136546820402145, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24049372971057892, 0.155771866440773, 0.2508457899093628], "policy_updates": 40250, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7719.146907812999, "contact_bce": 0.312543660402298, "contact_force_loss": 0.031589969992637634, "terrain_level_mean": 3.2021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9976539611816406, 0.9985909461975098, 2.998311996459961]} {"step": 40360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40360, "total_transitions": 165314560, "num_steps_per_env": 1, "wm_loss": 0.42948174476623535, "actor_loss": -8.709709167480469, "critic_loss": 0.021993203088641167, "reward": 0.07132432609796524, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23725979030132294, 0.15420883893966675, 0.25138235092163086], "policy_updates": 40260, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7722.645787281, "contact_bce": 0.3148966133594513, "contact_force_loss": 0.032220810651779175, "terrain_level_mean": 3.203857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9976539611816406, 0.9993643164634705, 2.998311996459961]} {"step": 40370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40370, "total_transitions": 165355520, "num_steps_per_env": 1, "wm_loss": 0.42867204546928406, "actor_loss": -8.716795921325684, "critic_loss": 0.0179012268781662, "reward": 0.07157229632139206, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2347635179758072, 0.15293678641319275, 0.251565545797348], "policy_updates": 40270, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7726.144955461999, "contact_bce": 0.31100785732269287, "contact_force_loss": 0.03210015967488289, "terrain_level_mean": 3.20458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9976539611816406, 0.9993643164634705, 2.998311996459961]} {"step": 40380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40380, "total_transitions": 165396480, "num_steps_per_env": 1, "wm_loss": 0.43344613909721375, "actor_loss": -8.723908424377441, "critic_loss": 0.03428628295660019, "reward": 0.07121985405683517, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24035434424877167, 0.15234169363975525, 0.25000157952308655], "policy_updates": 40280, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7729.646991893999, "contact_bce": 0.31177273392677307, "contact_force_loss": 0.032652538269758224, "terrain_level_mean": 3.203857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9976539611816406, 0.9993643164634705, 2.998311996459961]} {"step": 40390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40390, "total_transitions": 165437440, "num_steps_per_env": 1, "wm_loss": 0.4239429831504822, "actor_loss": -8.761129379272461, "critic_loss": 0.02223440818488598, "reward": 0.07144426554441452, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23847533762454987, 0.15250848233699799, 0.249379962682724], "policy_updates": 40290, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7733.1466021139995, "contact_bce": 0.3190004229545593, "contact_force_loss": 0.03195386007428169, "terrain_level_mean": 3.204345703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9976539611816406, 0.9993643164634705, 2.998311996459961]} {"step": 40400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40400, "total_transitions": 165478400, "num_steps_per_env": 1, "wm_loss": 0.4492908716201782, "actor_loss": -8.738707542419434, "critic_loss": 0.031372617930173874, "reward": 0.07134056836366653, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23819859325885773, 0.1557808369398117, 0.2521471083164215], "policy_updates": 40300, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7736.645600063, "contact_bce": 0.3113236129283905, "contact_force_loss": 0.03244074434041977, "terrain_level_mean": 3.203857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9976539611816406, 0.999946653842926, 2.998311996459961]} {"step": 40410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40410, "total_transitions": 165519360, "num_steps_per_env": 1, "wm_loss": 0.3948345184326172, "actor_loss": -8.71864128112793, "critic_loss": 0.032826948910951614, "reward": 0.0710207000374794, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2420191615819931, 0.1550772786140442, 0.24942803382873535], "policy_updates": 40310, "skipped_updates": 0, "invalid_env_resets": 71, "elapsed_s": 7740.146431444, "contact_bce": 0.3119542598724365, "contact_force_loss": 0.03205502778291702, "terrain_level_mean": 3.204833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9976539611816406, 0.999946653842926, 2.998311996459961]} RECOVERY reset 1 invalid environments; first IDs=[2001] {"step": 40420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40420, "total_transitions": 165560320, "num_steps_per_env": 1, "wm_loss": 0.41653335094451904, "actor_loss": -8.753351211547852, "critic_loss": 0.029335061088204384, "reward": 0.07062921673059464, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24383048713207245, 0.15476854145526886, 0.25143206119537354], "policy_updates": 40320, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7743.660116677999, "contact_bce": 0.3107073903083801, "contact_force_loss": 0.03233490139245987, "terrain_level_mean": 3.20458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9976539611816406, 0.999946653842926, 2.998311996459961]} {"step": 40430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40430, "total_transitions": 165601280, "num_steps_per_env": 1, "wm_loss": 0.430294007062912, "actor_loss": -8.768696784973145, "critic_loss": 0.01963709108531475, "reward": 0.070684514939785, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24519455432891846, 0.15479141473770142, 0.2594609558582306], "policy_updates": 40330, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7747.161392589999, "contact_bce": 0.31570926308631897, "contact_force_loss": 0.0322713628411293, "terrain_level_mean": 3.204833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9976539611816406, 0.999946653842926, 2.998311996459961]} {"step": 40440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40440, "total_transitions": 165642240, "num_steps_per_env": 1, "wm_loss": 0.43337488174438477, "actor_loss": -8.744083404541016, "critic_loss": 0.02281239628791809, "reward": 0.07057799398899078, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2494802623987198, 0.1579897552728653, 0.25799360871315], "policy_updates": 40340, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7750.660551724, "contact_bce": 0.31895941495895386, "contact_force_loss": 0.0316423624753952, "terrain_level_mean": 3.2060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.997166633605957, 0.999946653842926, 2.998311996459961]} {"step": 40450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40450, "total_transitions": 165683200, "num_steps_per_env": 1, "wm_loss": 0.4311915636062622, "actor_loss": -8.7322416305542, "critic_loss": 0.036506976932287216, "reward": 0.07100974023342133, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2487514168024063, 0.15850189328193665, 0.2548999488353729], "policy_updates": 40350, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7754.159081154, "contact_bce": 0.31673604249954224, "contact_force_loss": 0.03251286968588829, "terrain_level_mean": 3.205322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9941411018371582, 0.999946653842926, 2.998311996459961]} {"step": 40460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40460, "total_transitions": 165724160, "num_steps_per_env": 1, "wm_loss": 0.4271332919597626, "actor_loss": -8.718450546264648, "critic_loss": 0.03335059806704521, "reward": 0.07054811716079712, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2499009221792221, 0.16114909946918488, 0.25969916582107544], "policy_updates": 40360, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7757.664323293, "contact_bce": 0.3123319447040558, "contact_force_loss": 0.03235134109854698, "terrain_level_mean": 3.205322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9941411018371582, 0.999946653842926, 2.998311996459961]} {"step": 40470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40470, "total_transitions": 165765120, "num_steps_per_env": 1, "wm_loss": 0.43368667364120483, "actor_loss": -8.676813125610352, "critic_loss": 0.029715700075030327, "reward": 0.07073461264371872, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24830231070518494, 0.1619533747434616, 0.2564067244529724], "policy_updates": 40370, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7761.163812092, "contact_bce": 0.3141821324825287, "contact_force_loss": 0.03299781307578087, "terrain_level_mean": 3.2041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9941411018371582, 0.999946653842926, 2.998311996459961]} {"step": 40480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40480, "total_transitions": 165806080, "num_steps_per_env": 1, "wm_loss": 0.4156080484390259, "actor_loss": -8.755788803100586, "critic_loss": 0.026534145697951317, "reward": 0.07103423029184341, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24541334807872772, 0.16006691753864288, 0.2506362497806549], "policy_updates": 40380, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7764.665623581, "contact_bce": 0.3156890571117401, "contact_force_loss": 0.032798442989587784, "terrain_level_mean": 3.202880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} {"step": 40490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40490, "total_transitions": 165847040, "num_steps_per_env": 1, "wm_loss": 0.427477091550827, "actor_loss": -8.810077667236328, "critic_loss": 0.02520088665187359, "reward": 0.07091652601957321, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24701519310474396, 0.15715037286281586, 0.2538204491138458], "policy_updates": 40390, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7768.16602465, "contact_bce": 0.31482866406440735, "contact_force_loss": 0.03215060383081436, "terrain_level_mean": 3.203857421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} {"step": 40500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40500, "total_transitions": 165888000, "num_steps_per_env": 1, "wm_loss": 0.4163896441459656, "actor_loss": -8.785111427307129, "critic_loss": 0.02632979117333889, "reward": 0.07101036608219147, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24357403814792633, 0.1565476357936859, 0.2554927170276642], "policy_updates": 40400, "skipped_updates": 0, "invalid_env_resets": 72, "elapsed_s": 7771.682508381, "contact_bce": 0.31141942739486694, "contact_force_loss": 0.031570207327604294, "terrain_level_mean": 3.20458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_040500.mp4 RECOVERY reset 1 invalid environments; first IDs=[516] {"step": 40510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40510, "total_transitions": 165928960, "num_steps_per_env": 1, "wm_loss": 0.4093402922153473, "actor_loss": -8.726629257202148, "critic_loss": 0.018427977338433266, "reward": 0.07125157862901688, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24390555918216705, 0.1574123054742813, 0.25491201877593994], "policy_updates": 40410, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7781.02295172, "contact_bce": 0.3101706802845001, "contact_force_loss": 0.03250116482377052, "terrain_level_mean": 3.205322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} {"step": 40520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40520, "total_transitions": 165969920, "num_steps_per_env": 1, "wm_loss": 0.4252733290195465, "actor_loss": -8.761026382446289, "critic_loss": 0.019809015095233917, "reward": 0.07139427214860916, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24885916709899902, 0.15897001326084137, 0.2529919743537903], "policy_updates": 40420, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7784.534532934, "contact_bce": 0.3123144507408142, "contact_force_loss": 0.03353595361113548, "terrain_level_mean": 3.20556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} {"step": 40530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40530, "total_transitions": 166010880, "num_steps_per_env": 1, "wm_loss": 0.41395100951194763, "actor_loss": -8.749061584472656, "critic_loss": 0.020428156480193138, "reward": 0.07123640179634094, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2482135146856308, 0.16018101572990417, 0.2535879909992218], "policy_updates": 40430, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7788.041230497, "contact_bce": 0.31635814905166626, "contact_force_loss": 0.03214152157306671, "terrain_level_mean": 3.2060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} {"step": 40540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40540, "total_transitions": 166051840, "num_steps_per_env": 1, "wm_loss": 0.40962281823158264, "actor_loss": -8.71179485321045, "critic_loss": 0.02632768824696541, "reward": 0.07086413353681564, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2514336109161377, 0.16112567484378815, 0.25611838698387146], "policy_updates": 40440, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7791.566395770999, "contact_bce": 0.3139682412147522, "contact_force_loss": 0.03244059160351753, "terrain_level_mean": 3.20654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} {"step": 40550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40550, "total_transitions": 166092800, "num_steps_per_env": 1, "wm_loss": 0.4138801693916321, "actor_loss": -8.636985778808594, "critic_loss": 0.033172667026519775, "reward": 0.07067856937646866, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2514568567276001, 0.16130031645298004, 0.2541234493255615], "policy_updates": 40450, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7795.08753833, "contact_bce": 0.31650254130363464, "contact_force_loss": 0.03234069049358368, "terrain_level_mean": 3.20703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9967975616455078, 0.999946653842926, 2.998311996459961]} {"step": 40560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40560, "total_transitions": 166133760, "num_steps_per_env": 1, "wm_loss": 0.41298240423202515, "actor_loss": -8.805370330810547, "critic_loss": 0.028701383620500565, "reward": 0.07100554555654526, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24783514440059662, 0.15759876370429993, 0.2549794912338257], "policy_updates": 40460, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7798.612006357999, "contact_bce": 0.3123103976249695, "contact_force_loss": 0.03187169134616852, "terrain_level_mean": 3.206787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.997274398803711, 0.999946653842926, 2.998311996459961]} {"step": 40570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40570, "total_transitions": 166174720, "num_steps_per_env": 1, "wm_loss": 0.4514837861061096, "actor_loss": -8.758855819702148, "critic_loss": 0.02363492362201214, "reward": 0.07099077850580215, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24672749638557434, 0.15806631743907928, 0.25446397066116333], "policy_updates": 40470, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7802.130386758, "contact_bce": 0.31581807136535645, "contact_force_loss": 0.03285803645849228, "terrain_level_mean": 3.206787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.997274398803711, 0.999946653842926, 2.998311996459961]} {"step": 40580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40580, "total_transitions": 166215680, "num_steps_per_env": 1, "wm_loss": 0.4178125560283661, "actor_loss": -8.744388580322266, "critic_loss": 0.026004528626799583, "reward": 0.07107778638601303, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24928602576255798, 0.15864308178424835, 0.252483993768692], "policy_updates": 40480, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7805.642904708, "contact_bce": 0.31536173820495605, "contact_force_loss": 0.03267421945929527, "terrain_level_mean": 3.20703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.997274398803711, 0.999946653842926, 2.998311996459961]} {"step": 40590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40590, "total_transitions": 166256640, "num_steps_per_env": 1, "wm_loss": 0.44452622532844543, "actor_loss": -8.750223159790039, "critic_loss": 0.029868319630622864, "reward": 0.07084660977125168, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24903082847595215, 0.1584569662809372, 0.25272423028945923], "policy_updates": 40490, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7809.159241777999, "contact_bce": 0.31792962551116943, "contact_force_loss": 0.03264126926660538, "terrain_level_mean": 3.20654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356689453125, "command_abs_max": [1.997274398803711, 0.999946653842926, 2.998311996459961]} {"step": 40600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40600, "total_transitions": 166297600, "num_steps_per_env": 1, "wm_loss": 0.4047728180885315, "actor_loss": -8.706912994384766, "critic_loss": 0.02225545607507229, "reward": 0.07133980095386505, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24616338312625885, 0.1583421230316162, 0.25461429357528687], "policy_updates": 40500, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7812.934749464, "contact_bce": 0.3151797950267792, "contact_force_loss": 0.03205518051981926, "terrain_level_mean": 3.205322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.998311996459961]} {"step": 40610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40610, "total_transitions": 166338560, "num_steps_per_env": 1, "wm_loss": 0.4317744970321655, "actor_loss": -8.747623443603516, "critic_loss": 0.029597649350762367, "reward": 0.07148123532533646, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24458849430084229, 0.1558571457862854, 0.25461170077323914], "policy_updates": 40510, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7816.438835375, "contact_bce": 0.3155152201652527, "contact_force_loss": 0.03263717144727707, "terrain_level_mean": 3.205322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.998311996459961]} {"step": 40620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40620, "total_transitions": 166379520, "num_steps_per_env": 1, "wm_loss": 0.4239453077316284, "actor_loss": -8.745210647583008, "critic_loss": 0.024834180250763893, "reward": 0.07145963609218597, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24665215611457825, 0.15718139708042145, 0.25607603788375854], "policy_updates": 40520, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7819.960008122, "contact_bce": 0.3126543164253235, "contact_force_loss": 0.032725922763347626, "terrain_level_mean": 3.2060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.998311996459961]} {"step": 40630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40630, "total_transitions": 166420480, "num_steps_per_env": 1, "wm_loss": 0.42605286836624146, "actor_loss": -8.68222427368164, "critic_loss": 0.022587819024920464, "reward": 0.0704968124628067, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25174209475517273, 0.15798155963420868, 0.2617779076099396], "policy_updates": 40530, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7823.483972821, "contact_bce": 0.3114798069000244, "contact_force_loss": 0.0318291112780571, "terrain_level_mean": 3.205810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.998311996459961]} {"step": 40640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40640, "total_transitions": 166461440, "num_steps_per_env": 1, "wm_loss": 0.4509202837944031, "actor_loss": -8.732916831970215, "critic_loss": 0.02326590195298195, "reward": 0.070616714656353, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2526693344116211, 0.1597209870815277, 0.2592531144618988], "policy_updates": 40540, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7826.991192619, "contact_bce": 0.3190653920173645, "contact_force_loss": 0.033022768795490265, "terrain_level_mean": 3.205810546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40650, "total_transitions": 166502400, "num_steps_per_env": 1, "wm_loss": 0.43883800506591797, "actor_loss": -8.733034133911133, "critic_loss": 0.023503854870796204, "reward": 0.07102078944444656, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24882522225379944, 0.1579236537218094, 0.2516016960144043], "policy_updates": 40550, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7830.508743881999, "contact_bce": 0.3123413026332855, "contact_force_loss": 0.03239833936095238, "terrain_level_mean": 3.20556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40660, "total_transitions": 166543360, "num_steps_per_env": 1, "wm_loss": 0.42645353078842163, "actor_loss": -8.705183029174805, "critic_loss": 0.033608827739953995, "reward": 0.07138947397470474, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24624405801296234, 0.15793925523757935, 0.2500493824481964], "policy_updates": 40560, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7834.011537611, "contact_bce": 0.31916579604148865, "contact_force_loss": 0.032210029661655426, "terrain_level_mean": 3.20556640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40670, "total_transitions": 166584320, "num_steps_per_env": 1, "wm_loss": 0.40438657999038696, "actor_loss": -8.742805480957031, "critic_loss": 0.02741800621151924, "reward": 0.0709393247961998, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24747833609580994, 0.15844221413135529, 0.2500646412372589], "policy_updates": 40570, "skipped_updates": 0, "invalid_env_resets": 73, "elapsed_s": 7837.512274205999, "contact_bce": 0.31463298201560974, "contact_force_loss": 0.03223568946123123, "terrain_level_mean": 3.205322265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} RECOVERY reset 1 invalid environments; first IDs=[1142] {"step": 40680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40680, "total_transitions": 166625280, "num_steps_per_env": 1, "wm_loss": 0.41197723150253296, "actor_loss": -8.725963592529297, "critic_loss": 0.033098891377449036, "reward": 0.07091572135686874, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24505119025707245, 0.1571650207042694, 0.2517000436782837], "policy_updates": 40580, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7841.032632324, "contact_bce": 0.31116175651550293, "contact_force_loss": 0.032037340104579926, "terrain_level_mean": 3.20458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40690, "total_transitions": 166666240, "num_steps_per_env": 1, "wm_loss": 0.4648950695991516, "actor_loss": -8.72429084777832, "critic_loss": 0.028255654498934746, "reward": 0.0715436264872551, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24493183195590973, 0.1556561291217804, 0.24922797083854675], "policy_updates": 40590, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7844.535026304, "contact_bce": 0.31820476055145264, "contact_force_loss": 0.03352081775665283, "terrain_level_mean": 3.20361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40700, "total_transitions": 166707200, "num_steps_per_env": 1, "wm_loss": 0.41213342547416687, "actor_loss": -8.679712295532227, "critic_loss": 0.03132978454232216, "reward": 0.0714195966720581, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24323837459087372, 0.1570935696363449, 0.25354644656181335], "policy_updates": 40600, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7848.032458039999, "contact_bce": 0.3205384314060211, "contact_force_loss": 0.03270207718014717, "terrain_level_mean": 3.203369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40710, "total_transitions": 166748160, "num_steps_per_env": 1, "wm_loss": 0.40396925806999207, "actor_loss": -8.790262222290039, "critic_loss": 0.021232089027762413, "reward": 0.07137715816497803, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24309495091438293, 0.15627506375312805, 0.25278347730636597], "policy_updates": 40610, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7851.53754107, "contact_bce": 0.31522130966186523, "contact_force_loss": 0.03221519663929939, "terrain_level_mean": 3.203369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40720, "total_transitions": 166789120, "num_steps_per_env": 1, "wm_loss": 0.4204537570476532, "actor_loss": -8.75010871887207, "critic_loss": 0.02427670732140541, "reward": 0.07133754342794418, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24475954473018646, 0.15433065593242645, 0.2555592954158783], "policy_updates": 40620, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7855.045788523999, "contact_bce": 0.3067329525947571, "contact_force_loss": 0.031829021871089935, "terrain_level_mean": 3.203369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40730, "total_transitions": 166830080, "num_steps_per_env": 1, "wm_loss": 0.45087215304374695, "actor_loss": -8.749307632446289, "critic_loss": 0.024487465620040894, "reward": 0.07145940512418747, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24587054550647736, 0.1560061275959015, 0.2569783926010132], "policy_updates": 40630, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7858.547379512, "contact_bce": 0.31727126240730286, "contact_force_loss": 0.03176799416542053, "terrain_level_mean": 3.203369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.997274398803711, 0.9990741014480591, 2.9991965293884277]} {"step": 40740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40740, "total_transitions": 166871040, "num_steps_per_env": 1, "wm_loss": 0.39850175380706787, "actor_loss": -8.73309326171875, "critic_loss": 0.02377338707447052, "reward": 0.0712665244936943, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24643489718437195, 0.15848614275455475, 0.25370535254478455], "policy_updates": 40640, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7862.053605777, "contact_bce": 0.3063080310821533, "contact_force_loss": 0.03157736361026764, "terrain_level_mean": 3.20361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9961658716201782, 0.9990741014480591, 2.9991965293884277]} {"step": 40750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40750, "total_transitions": 166912000, "num_steps_per_env": 1, "wm_loss": 0.4287402629852295, "actor_loss": -8.721851348876953, "critic_loss": 0.027143612504005432, "reward": 0.07114189863204956, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24427862465381622, 0.15781553089618683, 0.2538025677204132], "policy_updates": 40650, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7865.554006865999, "contact_bce": 0.31551772356033325, "contact_force_loss": 0.032648976892232895, "terrain_level_mean": 3.203369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9961658716201782, 0.9990741014480591, 2.9991965293884277]} {"step": 40760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40760, "total_transitions": 166952960, "num_steps_per_env": 1, "wm_loss": 0.4047302007675171, "actor_loss": -8.676251411437988, "critic_loss": 0.03803835064172745, "reward": 0.0712185800075531, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2452802211046219, 0.16000306606292725, 0.2523897886276245], "policy_updates": 40660, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7869.058752831, "contact_bce": 0.31235334277153015, "contact_force_loss": 0.03184328228235245, "terrain_level_mean": 3.202880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9961658716201782, 0.9990741014480591, 2.9991965293884277]} {"step": 40770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40770, "total_transitions": 166993920, "num_steps_per_env": 1, "wm_loss": 0.41256779432296753, "actor_loss": -8.763452529907227, "critic_loss": 0.025317920371890068, "reward": 0.0708727240562439, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24876022338867188, 0.16049452126026154, 0.2588132321834564], "policy_updates": 40670, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7872.585484638999, "contact_bce": 0.32143256068229675, "contact_force_loss": 0.03228485956788063, "terrain_level_mean": 3.2021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9961658716201782, 0.9990741014480591, 2.9991965293884277]} {"step": 40780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40780, "total_transitions": 167034880, "num_steps_per_env": 1, "wm_loss": 0.4120507538318634, "actor_loss": -8.759063720703125, "critic_loss": 0.02155347168445587, "reward": 0.07087330520153046, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24555662274360657, 0.1575803905725479, 0.25642138719558716], "policy_updates": 40680, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7876.104825439999, "contact_bce": 0.31723296642303467, "contact_force_loss": 0.032601356506347656, "terrain_level_mean": 3.201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9961658716201782, 0.9993540048599243, 2.9991965293884277]} {"step": 40790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40790, "total_transitions": 167075840, "num_steps_per_env": 1, "wm_loss": 0.45358166098594666, "actor_loss": -8.690998077392578, "critic_loss": 0.02181435190141201, "reward": 0.07065414637327194, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24392738938331604, 0.15820303559303284, 0.2578335702419281], "policy_updates": 40690, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7879.631402479, "contact_bce": 0.311686247587204, "contact_force_loss": 0.032625481486320496, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9961658716201782, 0.9993540048599243, 2.9991965293884277]} {"step": 40800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40800, "total_transitions": 167116800, "num_steps_per_env": 1, "wm_loss": 0.43689945340156555, "actor_loss": -8.779600143432617, "critic_loss": 0.021971536800265312, "reward": 0.0707007646560669, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24644255638122559, 0.1575121134519577, 0.2539430856704712], "policy_updates": 40700, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7883.1577588869995, "contact_bce": 0.31027328968048096, "contact_force_loss": 0.032293256372213364, "terrain_level_mean": 3.200927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9961658716201782, 0.9993540048599243, 2.9991965293884277]} {"step": 40810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40810, "total_transitions": 167157760, "num_steps_per_env": 1, "wm_loss": 0.4124267101287842, "actor_loss": -8.732339859008789, "critic_loss": 0.029555296525359154, "reward": 0.07075012475252151, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24966131150722504, 0.1573917716741562, 0.25536200404167175], "policy_updates": 40710, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7886.6834936039995, "contact_bce": 0.31347182393074036, "contact_force_loss": 0.032157689332962036, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9961658716201782, 0.9993540048599243, 2.9991965293884277]} {"step": 40820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40820, "total_transitions": 167198720, "num_steps_per_env": 1, "wm_loss": 0.4275195598602295, "actor_loss": -8.719686508178711, "critic_loss": 0.0316540002822876, "reward": 0.07085002958774567, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2446792721748352, 0.15664462745189667, 0.2533091902732849], "policy_updates": 40720, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7890.201703291999, "contact_bce": 0.3186199367046356, "contact_force_loss": 0.03187142312526703, "terrain_level_mean": 3.201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9997997283935547, 0.9993540048599243, 2.9991965293884277]} {"step": 40830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40830, "total_transitions": 167239680, "num_steps_per_env": 1, "wm_loss": 0.43057867884635925, "actor_loss": -8.78696060180664, "critic_loss": 0.02700255624949932, "reward": 0.07085264474153519, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24929897487163544, 0.1555716097354889, 0.2535983622074127], "policy_updates": 40730, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7893.7226733669995, "contact_bce": 0.31378763914108276, "contact_force_loss": 0.03196102753281593, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9997997283935547, 0.9993540048599243, 2.9991965293884277]} {"step": 40840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40840, "total_transitions": 167280640, "num_steps_per_env": 1, "wm_loss": 0.4499455988407135, "actor_loss": -8.76301383972168, "critic_loss": 0.023198619484901428, "reward": 0.07097606360912323, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24644161760807037, 0.15321128070354462, 0.24998131394386292], "policy_updates": 40740, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7897.234539388, "contact_bce": 0.3111366331577301, "contact_force_loss": 0.032703787088394165, "terrain_level_mean": 3.200439453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9997997283935547, 0.9993540048599243, 2.999692916870117]} {"step": 40850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40850, "total_transitions": 167321600, "num_steps_per_env": 1, "wm_loss": 0.4208608865737915, "actor_loss": -8.708535194396973, "critic_loss": 0.025808483362197876, "reward": 0.07123853266239166, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24484091997146606, 0.15432503819465637, 0.2484005093574524], "policy_updates": 40750, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7900.7520795519995, "contact_bce": 0.3185681700706482, "contact_force_loss": 0.03269996866583824, "terrain_level_mean": 3.199951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9997997283935547, 0.9993540048599243, 2.999692916870117]} {"step": 40860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40860, "total_transitions": 167362560, "num_steps_per_env": 1, "wm_loss": 0.42248180508613586, "actor_loss": -8.732491493225098, "critic_loss": 0.02546030282974243, "reward": 0.07144772261381149, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24628566205501556, 0.15456920862197876, 0.24974769353866577], "policy_updates": 40760, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7904.269096225999, "contact_bce": 0.31687280535697937, "contact_force_loss": 0.03319551423192024, "terrain_level_mean": 3.2001953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9997997283935547, 0.9993540048599243, 2.999692916870117]} {"step": 40870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40870, "total_transitions": 167403520, "num_steps_per_env": 1, "wm_loss": 0.4118410050868988, "actor_loss": -8.698266983032227, "critic_loss": 0.0396822951734066, "reward": 0.07122067362070084, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2471478283405304, 0.15493281185626984, 0.25175386667251587], "policy_updates": 40770, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7907.792482532, "contact_bce": 0.3186429738998413, "contact_force_loss": 0.03273451328277588, "terrain_level_mean": 3.20068359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40880, "total_transitions": 167444480, "num_steps_per_env": 1, "wm_loss": 0.42394426465034485, "actor_loss": -8.755001068115234, "critic_loss": 0.027939727529883385, "reward": 0.0712369754910469, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24510353803634644, 0.15674501657485962, 0.2512473165988922], "policy_updates": 40780, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7911.3162806029995, "contact_bce": 0.31181105971336365, "contact_force_loss": 0.031755898147821426, "terrain_level_mean": 3.201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40890, "total_transitions": 167485440, "num_steps_per_env": 1, "wm_loss": 0.4362463057041168, "actor_loss": -8.729087829589844, "critic_loss": 0.019478902220726013, "reward": 0.07140018790960312, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2428038865327835, 0.15626919269561768, 0.24982650578022003], "policy_updates": 40790, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7914.837508125, "contact_bce": 0.31144148111343384, "contact_force_loss": 0.03266618773341179, "terrain_level_mean": 3.201416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40900, "total_transitions": 167526400, "num_steps_per_env": 1, "wm_loss": 0.40404999256134033, "actor_loss": -8.73466968536377, "critic_loss": 0.03634212166070938, "reward": 0.07162245362997055, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24405555427074432, 0.1568199247121811, 0.24992437660694122], "policy_updates": 40800, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7918.351527927, "contact_bce": 0.3127535283565521, "contact_force_loss": 0.031652603298425674, "terrain_level_mean": 3.20166015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40910, "total_transitions": 167567360, "num_steps_per_env": 1, "wm_loss": 0.3942950963973999, "actor_loss": -8.73248291015625, "critic_loss": 0.02168668806552887, "reward": 0.07185021787881851, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2422606647014618, 0.15608766674995422, 0.2489025741815567], "policy_updates": 40810, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7922.12331412, "contact_bce": 0.3079679310321808, "contact_force_loss": 0.031240055337548256, "terrain_level_mean": 3.201904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40920, "total_transitions": 167608320, "num_steps_per_env": 1, "wm_loss": 0.41444775462150574, "actor_loss": -8.719501495361328, "critic_loss": 0.01913539133965969, "reward": 0.07173396646976471, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24017482995986938, 0.154588982462883, 0.251282662153244], "policy_updates": 40820, "skipped_updates": 0, "invalid_env_resets": 74, "elapsed_s": 7925.645923421, "contact_bce": 0.3111986815929413, "contact_force_loss": 0.03241128474473953, "terrain_level_mean": 3.203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} RECOVERY reset 1 invalid environments; first IDs=[1331] {"step": 40930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40930, "total_transitions": 167649280, "num_steps_per_env": 1, "wm_loss": 0.45322415232658386, "actor_loss": -8.756857872009277, "critic_loss": 0.025751739740371704, "reward": 0.07102843374013901, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24212896823883057, 0.1588796079158783, 0.25689059495925903], "policy_updates": 40830, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7929.183397311999, "contact_bce": 0.314208060503006, "contact_force_loss": 0.033443037420511246, "terrain_level_mean": 3.202880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40940, "total_transitions": 167690240, "num_steps_per_env": 1, "wm_loss": 0.43241310119628906, "actor_loss": -8.739546775817871, "critic_loss": 0.0216818880289793, "reward": 0.07042670249938965, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24648109078407288, 0.15990574657917023, 0.2544582188129425], "policy_updates": 40840, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7932.709661014, "contact_bce": 0.311800092458725, "contact_force_loss": 0.03193363919854164, "terrain_level_mean": 3.203369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40950, "total_transitions": 167731200, "num_steps_per_env": 1, "wm_loss": 0.4234083890914917, "actor_loss": -8.727888107299805, "critic_loss": 0.02077285759150982, "reward": 0.07041507959365845, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24512095749378204, 0.1608656942844391, 0.2565849721431732], "policy_updates": 40850, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7936.232259173, "contact_bce": 0.3134970963001251, "contact_force_loss": 0.032359976321458817, "terrain_level_mean": 3.203369140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40960, "total_transitions": 167772160, "num_steps_per_env": 1, "wm_loss": 0.43244633078575134, "actor_loss": -8.787568092346191, "critic_loss": 0.028772467747330666, "reward": 0.07070612907409668, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2427348643541336, 0.16032427549362183, 0.2547760307788849], "policy_updates": 40860, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7939.750136559999, "contact_bce": 0.314603328704834, "contact_force_loss": 0.032239753752946854, "terrain_level_mean": 3.20263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40970, "total_transitions": 167813120, "num_steps_per_env": 1, "wm_loss": 0.40106356143951416, "actor_loss": -8.73535442352295, "critic_loss": 0.024587970227003098, "reward": 0.07084828615188599, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24022838473320007, 0.15670916438102722, 0.25569602847099304], "policy_updates": 40870, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7943.269208250999, "contact_bce": 0.31642135977745056, "contact_force_loss": 0.03146794065833092, "terrain_level_mean": 3.202880859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40980, "total_transitions": 167854080, "num_steps_per_env": 1, "wm_loss": 0.4163743853569031, "actor_loss": -8.728049278259277, "critic_loss": 0.025377720594406128, "reward": 0.07097647339105606, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24213571846485138, 0.15901415050029755, 0.25537800788879395], "policy_updates": 40880, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7946.785534803999, "contact_bce": 0.3126782476902008, "contact_force_loss": 0.032326456159353256, "terrain_level_mean": 3.2041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9997997283935547, 0.9999581575393677, 2.999692916870117]} {"step": 40990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 40990, "total_transitions": 167895040, "num_steps_per_env": 1, "wm_loss": 0.4068397581577301, "actor_loss": -8.727676391601562, "critic_loss": 0.02479073777794838, "reward": 0.07105280458927155, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2457774430513382, 0.1589457243680954, 0.2533140778541565], "policy_updates": 40890, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7950.291734197999, "contact_bce": 0.3113308548927307, "contact_force_loss": 0.03157486021518707, "terrain_level_mean": 3.204833984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9994490146636963, 0.9999581575393677, 2.999692916870117]} {"step": 41000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41000, "total_transitions": 167936000, "num_steps_per_env": 1, "wm_loss": 0.4204080104827881, "actor_loss": -8.730378150939941, "critic_loss": 0.024426784366369247, "reward": 0.07118282467126846, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24317538738250732, 0.15784808993339539, 0.2510611116886139], "policy_updates": 40900, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7953.797347432, "contact_bce": 0.311300128698349, "contact_force_loss": 0.031279440969228745, "terrain_level_mean": 3.204345703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9994490146636963, 0.9999581575393677, 2.999692916870117]} {"step": 41010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41010, "total_transitions": 167976960, "num_steps_per_env": 1, "wm_loss": 0.45082026720046997, "actor_loss": -8.777505874633789, "critic_loss": 0.022251980379223824, "reward": 0.07103657722473145, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24284929037094116, 0.15664778649806976, 0.25232967734336853], "policy_updates": 40910, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7957.348249936999, "contact_bce": 0.31608209013938904, "contact_force_loss": 0.03396117314696312, "terrain_level_mean": 3.2041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9994490146636963, 0.9999581575393677, 2.999692916870117]} {"step": 41020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41020, "total_transitions": 168017920, "num_steps_per_env": 1, "wm_loss": 0.4365712106227875, "actor_loss": -8.781893730163574, "critic_loss": 0.018272023648023605, "reward": 0.07109587639570236, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24001726508140564, 0.15724453330039978, 0.25715172290802], "policy_updates": 40920, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7960.859702342999, "contact_bce": 0.3144878149032593, "contact_force_loss": 0.032451827079057693, "terrain_level_mean": 3.20458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9994490146636963, 0.9999581575393677, 2.999692916870117]} {"step": 41030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41030, "total_transitions": 168058880, "num_steps_per_env": 1, "wm_loss": 0.4212251901626587, "actor_loss": -8.761174201965332, "critic_loss": 0.026106322184205055, "reward": 0.0711631253361702, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23985815048217773, 0.1584131270647049, 0.25676387548446655], "policy_updates": 40930, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7964.372855426, "contact_bce": 0.31210026144981384, "contact_force_loss": 0.03202444687485695, "terrain_level_mean": 3.206298828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9994490146636963, 0.9996975660324097, 2.999692916870117]} {"step": 41040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41040, "total_transitions": 168099840, "num_steps_per_env": 1, "wm_loss": 0.4182778298854828, "actor_loss": -8.750797271728516, "critic_loss": 0.02606992982327938, "reward": 0.07124676555395126, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2387690246105194, 0.15591061115264893, 0.25227972865104675], "policy_updates": 40940, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7967.877780049, "contact_bce": 0.308837354183197, "contact_force_loss": 0.032446663826704025, "terrain_level_mean": 3.20703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9978805780410767, 0.9996975660324097, 2.999692916870117]} {"step": 41050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41050, "total_transitions": 168140800, "num_steps_per_env": 1, "wm_loss": 0.41615912318229675, "actor_loss": -8.779876708984375, "critic_loss": 0.020266499370336533, "reward": 0.07099150866270065, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2415611296892166, 0.15742652118206024, 0.2498757243156433], "policy_updates": 40950, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7971.3928818839995, "contact_bce": 0.312353253364563, "contact_force_loss": 0.03262653574347496, "terrain_level_mean": 3.2080078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9978805780410767, 0.9996975660324097, 2.999692916870117]} {"step": 41060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41060, "total_transitions": 168181760, "num_steps_per_env": 1, "wm_loss": 0.40872496366500854, "actor_loss": -8.734092712402344, "critic_loss": 0.02127407304942608, "reward": 0.07099463045597076, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24067015945911407, 0.15813961625099182, 0.2531435489654541], "policy_updates": 40960, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7974.902992228999, "contact_bce": 0.3174428641796112, "contact_force_loss": 0.0325162447988987, "terrain_level_mean": 3.207275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9978805780410767, 0.9996975660324097, 2.999692916870117]} {"step": 41070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41070, "total_transitions": 168222720, "num_steps_per_env": 1, "wm_loss": 0.39949262142181396, "actor_loss": -8.744190216064453, "critic_loss": 0.02027379535138607, "reward": 0.07111238688230515, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24301236867904663, 0.1593495011329651, 0.2557840049266815], "policy_updates": 40970, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7978.413864466999, "contact_bce": 0.31156402826309204, "contact_force_loss": 0.0319221131503582, "terrain_level_mean": 3.20654296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9978805780410767, 0.9996975660324097, 2.999692916870117]} {"step": 41080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41080, "total_transitions": 168263680, "num_steps_per_env": 1, "wm_loss": 0.4074089229106903, "actor_loss": -8.749517440795898, "critic_loss": 0.02656223438680172, "reward": 0.07107212394475937, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24781109392642975, 0.15981149673461914, 0.25667139887809753], "policy_updates": 40980, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7981.927932762, "contact_bce": 0.31032830476760864, "contact_force_loss": 0.03204590082168579, "terrain_level_mean": 3.206787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9978805780410767, 0.9996975660324097, 2.999692916870117]} {"step": 41090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41090, "total_transitions": 168304640, "num_steps_per_env": 1, "wm_loss": 0.4072566628456116, "actor_loss": -8.77160930633545, "critic_loss": 0.017136892303824425, "reward": 0.07061504572629929, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2506044805049896, 0.16025979816913605, 0.25854387879371643], "policy_updates": 40990, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7985.424889520999, "contact_bce": 0.30763158202171326, "contact_force_loss": 0.031481802463531494, "terrain_level_mean": 3.207275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9978805780410767, 0.9996975660324097, 2.999692916870117]} {"step": 41100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41100, "total_transitions": 168345600, "num_steps_per_env": 1, "wm_loss": 0.4165702164173126, "actor_loss": -8.757349014282227, "critic_loss": 0.02268805541098118, "reward": 0.07063757628202438, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2513370215892792, 0.15946979820728302, 0.25714439153671265], "policy_updates": 41000, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7988.933827307, "contact_bce": 0.3112834692001343, "contact_force_loss": 0.03231876716017723, "terrain_level_mean": 3.206787109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9978805780410767, 0.9988182783126831, 2.999692916870117]} {"step": 41110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41110, "total_transitions": 168386560, "num_steps_per_env": 1, "wm_loss": 0.42461952567100525, "actor_loss": -8.748082160949707, "critic_loss": 0.035785987973213196, "reward": 0.07075073570013046, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2508358359336853, 0.1596338450908661, 0.2543288767337799], "policy_updates": 41010, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7992.455213349999, "contact_bce": 0.31541740894317627, "contact_force_loss": 0.03229931369423866, "terrain_level_mean": 3.20751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9978805780410767, 0.9988182783126831, 2.999692916870117]} {"step": 41120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41120, "total_transitions": 168427520, "num_steps_per_env": 1, "wm_loss": 0.4414201080799103, "actor_loss": -8.756447792053223, "critic_loss": 0.02520430088043213, "reward": 0.07073479145765305, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2488848716020584, 0.1592242419719696, 0.25368595123291016], "policy_updates": 41020, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7995.973293864, "contact_bce": 0.31079697608947754, "contact_force_loss": 0.031966228038072586, "terrain_level_mean": 3.20849609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9978805780410767, 0.9988182783126831, 2.999692916870117]} {"step": 41130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41130, "total_transitions": 168468480, "num_steps_per_env": 1, "wm_loss": 0.46546638011932373, "actor_loss": -8.665559768676758, "critic_loss": 0.024619771167635918, "reward": 0.0709916427731514, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24818091094493866, 0.1599615216255188, 0.26085320115089417], "policy_updates": 41030, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 7999.493443884, "contact_bce": 0.31533533334732056, "contact_force_loss": 0.03285277634859085, "terrain_level_mean": 3.20947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9978805780410767, 0.9988182783126831, 2.999692916870117]} {"step": 41140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41140, "total_transitions": 168509440, "num_steps_per_env": 1, "wm_loss": 0.4162384271621704, "actor_loss": -8.732942581176758, "critic_loss": 0.022395147010684013, "reward": 0.07083453983068466, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24901406466960907, 0.15970240533351898, 0.25843578577041626], "policy_updates": 41040, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8003.012972095, "contact_bce": 0.3069989085197449, "contact_force_loss": 0.031897082924842834, "terrain_level_mean": 3.208740234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9978805780410767, 0.9988182783126831, 2.999692916870117]} {"step": 41150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41150, "total_transitions": 168550400, "num_steps_per_env": 1, "wm_loss": 0.4037313759326935, "actor_loss": -8.762279510498047, "critic_loss": 0.024148566648364067, "reward": 0.07065536826848984, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24944034218788147, 0.15993806719779968, 0.25658857822418213], "policy_updates": 41050, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8006.525645596, "contact_bce": 0.31479600071907043, "contact_force_loss": 0.032012954354286194, "terrain_level_mean": 3.209228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9978805780410767, 0.9988182783126831, 2.999692916870117]} {"step": 41160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41160, "total_transitions": 168591360, "num_steps_per_env": 1, "wm_loss": 0.46116766333580017, "actor_loss": -8.717745780944824, "critic_loss": 0.02729596570134163, "reward": 0.07039681822061539, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2534578740596771, 0.15976256132125854, 0.25238683819770813], "policy_updates": 41060, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8010.047324169999, "contact_bce": 0.31404584646224976, "contact_force_loss": 0.03176426514983177, "terrain_level_mean": 3.209228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9978805780410767, 0.9988182783126831, 2.999692916870117]} {"step": 41170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41170, "total_transitions": 168632320, "num_steps_per_env": 1, "wm_loss": 0.42018741369247437, "actor_loss": -8.728860855102539, "critic_loss": 0.030948659405112267, "reward": 0.07070808857679367, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25223931670188904, 0.1584303230047226, 0.25109347701072693], "policy_updates": 41070, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8013.560238605999, "contact_bce": 0.3158341646194458, "contact_force_loss": 0.032809607684612274, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9978805780410767, 0.9972911477088928, 2.999692916870117]} {"step": 41180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41180, "total_transitions": 168673280, "num_steps_per_env": 1, "wm_loss": 0.4164870083332062, "actor_loss": -8.73101806640625, "critic_loss": 0.022289013490080833, "reward": 0.0707462877035141, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2528516948223114, 0.15926501154899597, 0.2559081017971039], "policy_updates": 41080, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8017.324990373999, "contact_bce": 0.3094424903392792, "contact_force_loss": 0.031898681074380875, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.999692916870117]} {"step": 41190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41190, "total_transitions": 168714240, "num_steps_per_env": 1, "wm_loss": 0.4357873201370239, "actor_loss": -8.74239730834961, "critic_loss": 0.0270127784460783, "reward": 0.07052594423294067, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24944394826889038, 0.16079066693782806, 0.2551657557487488], "policy_updates": 41090, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8020.830578205999, "contact_bce": 0.31714874505996704, "contact_force_loss": 0.032582838088274, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.9993808269500732]} {"step": 41200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41200, "total_transitions": 168755200, "num_steps_per_env": 1, "wm_loss": 0.40597108006477356, "actor_loss": -8.763570785522461, "critic_loss": 0.01687001623213291, "reward": 0.0705941841006279, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24890749156475067, 0.15845203399658203, 0.25360938906669617], "policy_updates": 41100, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8024.327219, "contact_bce": 0.3146423399448395, "contact_force_loss": 0.0319872722029686, "terrain_level_mean": 3.20947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.9993808269500732]} {"step": 41210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41210, "total_transitions": 168796160, "num_steps_per_env": 1, "wm_loss": 0.4144749343395233, "actor_loss": -8.70793628692627, "critic_loss": 0.03608966991305351, "reward": 0.07073795050382614, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25197991728782654, 0.1611170619726181, 0.2531670928001404], "policy_updates": 41110, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8027.819183506, "contact_bce": 0.30699673295021057, "contact_force_loss": 0.03201090544462204, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.9993808269500732]} {"step": 41220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41220, "total_transitions": 168837120, "num_steps_per_env": 1, "wm_loss": 0.417718768119812, "actor_loss": -8.71824836730957, "critic_loss": 0.05903713032603264, "reward": 0.0705799013376236, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25241124629974365, 0.16030293703079224, 0.25316527485847473], "policy_updates": 41120, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8031.332495444999, "contact_bce": 0.30944839119911194, "contact_force_loss": 0.032466672360897064, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.9993808269500732]} {"step": 41230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41230, "total_transitions": 168878080, "num_steps_per_env": 1, "wm_loss": 0.4235009551048279, "actor_loss": -8.722075462341309, "critic_loss": 0.02365225739777088, "reward": 0.07102229446172714, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2474054992198944, 0.1583690643310547, 0.2546098828315735], "policy_updates": 41130, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8034.842636725999, "contact_bce": 0.3138255178928375, "contact_force_loss": 0.0329248309135437, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.994992733001709]} {"step": 41240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41240, "total_transitions": 168919040, "num_steps_per_env": 1, "wm_loss": 0.4079129695892334, "actor_loss": -8.739453315734863, "critic_loss": 0.023175766691565514, "reward": 0.07075594365596771, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24850527942180634, 0.16129659116268158, 0.2570337951183319], "policy_updates": 41140, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8038.365342687, "contact_bce": 0.3110239803791046, "contact_force_loss": 0.032407455146312714, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.994992733001709]} {"step": 41250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41250, "total_transitions": 168960000, "num_steps_per_env": 1, "wm_loss": 0.4014912545681, "actor_loss": -8.757013320922852, "critic_loss": 0.017434248700737953, "reward": 0.07035036385059357, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2515890598297119, 0.15878967940807343, 0.26153337955474854], "policy_updates": 41150, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8041.886921118, "contact_bce": 0.30534207820892334, "contact_force_loss": 0.03229876980185509, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.994992733001709]} {"step": 41260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41260, "total_transitions": 169000960, "num_steps_per_env": 1, "wm_loss": 0.4242704510688782, "actor_loss": -8.762714385986328, "critic_loss": 0.022441642358899117, "reward": 0.07069781422615051, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24278691411018372, 0.15691855549812317, 0.25649771094322205], "policy_updates": 41160, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8045.4092212860005, "contact_bce": 0.3114470839500427, "contact_force_loss": 0.03280378878116608, "terrain_level_mean": 3.2099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.994992733001709]} {"step": 41270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41270, "total_transitions": 169041920, "num_steps_per_env": 1, "wm_loss": 0.42691537737846375, "actor_loss": -8.757333755493164, "critic_loss": 0.019219055771827698, "reward": 0.07078342884778976, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24099192023277283, 0.1558079570531845, 0.2562432587146759], "policy_updates": 41170, "skipped_updates": 0, "invalid_env_resets": 75, "elapsed_s": 8048.926315854999, "contact_bce": 0.3130030930042267, "contact_force_loss": 0.03208014741539955, "terrain_level_mean": 3.2099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9975907802581787, 0.9972911477088928, 2.994992733001709]} RECOVERY reset 1 invalid environments; first IDs=[2010] {"step": 41280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41280, "total_transitions": 169082880, "num_steps_per_env": 1, "wm_loss": 0.43219441175460815, "actor_loss": -8.746315002441406, "critic_loss": 0.024482065811753273, "reward": 0.07070872187614441, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24430988729000092, 0.15624889731407166, 0.2556516230106354], "policy_updates": 41180, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8052.453843238999, "contact_bce": 0.31834539771080017, "contact_force_loss": 0.0329941026866436, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9975907802581787, 0.9991310834884644, 2.994992733001709]} {"step": 41290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41290, "total_transitions": 169123840, "num_steps_per_env": 1, "wm_loss": 0.44313880801200867, "actor_loss": -8.76689338684082, "critic_loss": 0.025317499414086342, "reward": 0.07040487974882126, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24817055463790894, 0.15559373795986176, 0.256881982088089], "policy_updates": 41190, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8055.970275847999, "contact_bce": 0.3067336678504944, "contact_force_loss": 0.03309090435504913, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9959770441055298, 0.9991310834884644, 2.994992733001709]} {"step": 41300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41300, "total_transitions": 169164800, "num_steps_per_env": 1, "wm_loss": 0.4244728088378906, "actor_loss": -8.738910675048828, "critic_loss": 0.027184387668967247, "reward": 0.07034720480442047, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24798396229743958, 0.15730878710746765, 0.2550765573978424], "policy_updates": 41200, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8059.482771393, "contact_bce": 0.31135255098342896, "contact_force_loss": 0.032897915691137314, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9959770441055298, 0.9991310834884644, 2.994992733001709]} {"step": 41310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41310, "total_transitions": 169205760, "num_steps_per_env": 1, "wm_loss": 0.39211151003837585, "actor_loss": -8.708675384521484, "critic_loss": 0.027897754684090614, "reward": 0.07075310498476028, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24347536265850067, 0.15505461394786835, 0.2520052492618561], "policy_updates": 41210, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8062.992459447, "contact_bce": 0.31015944480895996, "contact_force_loss": 0.03203226998448372, "terrain_level_mean": 3.212158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9959770441055298, 0.9991310834884644, 2.994992733001709]} {"step": 41320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41320, "total_transitions": 169246720, "num_steps_per_env": 1, "wm_loss": 0.4240764081478119, "actor_loss": -8.758705139160156, "critic_loss": 0.02958594262599945, "reward": 0.0709059089422226, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2408454567193985, 0.15439078211784363, 0.251956969499588], "policy_updates": 41220, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8066.503166701, "contact_bce": 0.3133777678012848, "contact_force_loss": 0.032411184161901474, "terrain_level_mean": 3.212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9959770441055298, 0.9991310834884644, 2.994992733001709]} {"step": 41330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41330, "total_transitions": 169287680, "num_steps_per_env": 1, "wm_loss": 0.4244488477706909, "actor_loss": -8.747060775756836, "critic_loss": 0.02021506242454052, "reward": 0.07021700590848923, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24700993299484253, 0.15522995591163635, 0.25714051723480225], "policy_updates": 41230, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8070.015590366999, "contact_bce": 0.318247526884079, "contact_force_loss": 0.03349168226122856, "terrain_level_mean": 3.2138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994992733001709]} {"step": 41340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41340, "total_transitions": 169328640, "num_steps_per_env": 1, "wm_loss": 0.40697038173675537, "actor_loss": -8.696256637573242, "critic_loss": 0.029032697901129723, "reward": 0.07061158120632172, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24402932822704315, 0.15494391322135925, 0.2522689998149872], "policy_updates": 41240, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8073.532419962, "contact_bce": 0.3121809661388397, "contact_force_loss": 0.03244052454829216, "terrain_level_mean": 3.21240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994992733001709]} {"step": 41350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41350, "total_transitions": 169369600, "num_steps_per_env": 1, "wm_loss": 0.3925648629665375, "actor_loss": -8.728385925292969, "critic_loss": 0.03364355117082596, "reward": 0.07071042060852051, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24747468531131744, 0.154777392745018, 0.2556039094924927], "policy_updates": 41250, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8077.056935509, "contact_bce": 0.3077155351638794, "contact_force_loss": 0.03183482214808464, "terrain_level_mean": 3.21240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994992733001709]} {"step": 41360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41360, "total_transitions": 169410560, "num_steps_per_env": 1, "wm_loss": 0.4267455041408539, "actor_loss": -8.726783752441406, "critic_loss": 0.020925013348460197, "reward": 0.07014896720647812, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24778254330158234, 0.1577308475971222, 0.25858259201049805], "policy_updates": 41260, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8080.578178944, "contact_bce": 0.31832629442214966, "contact_force_loss": 0.03368862718343735, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994417667388916]} {"step": 41370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41370, "total_transitions": 169451520, "num_steps_per_env": 1, "wm_loss": 0.42057716846466064, "actor_loss": -8.717411994934082, "critic_loss": 0.026960372924804688, "reward": 0.07032639533281326, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24789933860301971, 0.15359239280223846, 0.25550660490989685], "policy_updates": 41270, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8084.095051604, "contact_bce": 0.3139539957046509, "contact_force_loss": 0.032354533672332764, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994417667388916]} {"step": 41380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41380, "total_transitions": 169492480, "num_steps_per_env": 1, "wm_loss": 0.42281144857406616, "actor_loss": -8.675640106201172, "critic_loss": 0.032049909234046936, "reward": 0.06991229206323624, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2515336275100708, 0.15321870148181915, 0.254578560590744], "policy_updates": 41280, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8087.609734409, "contact_bce": 0.3084918260574341, "contact_force_loss": 0.03200095146894455, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41390, "total_transitions": 169533440, "num_steps_per_env": 1, "wm_loss": 0.42745888233184814, "actor_loss": -8.725427627563477, "critic_loss": 0.028535768389701843, "reward": 0.07043381035327911, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2449706643819809, 0.15306220948696136, 0.25380739569664], "policy_updates": 41290, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8091.121201542, "contact_bce": 0.312102735042572, "contact_force_loss": 0.03180887922644615, "terrain_level_mean": 3.2099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41400, "total_transitions": 169574400, "num_steps_per_env": 1, "wm_loss": 0.4002401828765869, "actor_loss": -8.701021194458008, "critic_loss": 0.02859666384756565, "reward": 0.07089704275131226, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24418702721595764, 0.15376199781894684, 0.24777622520923615], "policy_updates": 41300, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8094.88698364, "contact_bce": 0.30962568521499634, "contact_force_loss": 0.03190963342785835, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41410, "total_transitions": 169615360, "num_steps_per_env": 1, "wm_loss": 0.4118083119392395, "actor_loss": -8.744466781616211, "critic_loss": 0.02233058586716652, "reward": 0.07099729031324387, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24970509111881256, 0.15640313923358917, 0.24986034631729126], "policy_updates": 41310, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8098.407834032, "contact_bce": 0.3117790222167969, "contact_force_loss": 0.032635267823934555, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41420, "total_transitions": 169656320, "num_steps_per_env": 1, "wm_loss": 0.42384833097457886, "actor_loss": -8.761680603027344, "critic_loss": 0.03153374046087265, "reward": 0.0707150250673294, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25291091203689575, 0.15788541734218597, 0.2546723484992981], "policy_updates": 41320, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8101.931491007, "contact_bce": 0.3189123272895813, "contact_force_loss": 0.03295653313398361, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41430, "total_transitions": 169697280, "num_steps_per_env": 1, "wm_loss": 0.4666023850440979, "actor_loss": -8.700279235839844, "critic_loss": 0.02237500436604023, "reward": 0.0703384056687355, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2548803389072418, 0.1554882973432541, 0.2595144212245941], "policy_updates": 41330, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8105.451819653, "contact_bce": 0.314753919839859, "contact_force_loss": 0.03272205591201782, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41440, "total_transitions": 169738240, "num_steps_per_env": 1, "wm_loss": 0.4232545793056488, "actor_loss": -8.71084976196289, "critic_loss": 0.025451377034187317, "reward": 0.07013145834207535, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2566364109516144, 0.15457937121391296, 0.2589515447616577], "policy_updates": 41340, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8108.971190984, "contact_bce": 0.3142832815647125, "contact_force_loss": 0.032422151416540146, "terrain_level_mean": 3.212646484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41450, "total_transitions": 169779200, "num_steps_per_env": 1, "wm_loss": 0.4158587157726288, "actor_loss": -8.712310791015625, "critic_loss": 0.023007458075881004, "reward": 0.07061287015676498, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25749197602272034, 0.15473800897598267, 0.25539636611938477], "policy_updates": 41350, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8112.497360102, "contact_bce": 0.30542227625846863, "contact_force_loss": 0.03235067427158356, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41460, "total_transitions": 169820160, "num_steps_per_env": 1, "wm_loss": 0.3982594609260559, "actor_loss": -8.74697494506836, "critic_loss": 0.021590976044535637, "reward": 0.07115747779607773, "falls": 4, "interval_steps": 10, "velocity_mae": [0.254000723361969, 0.15404166281223297, 0.25353294610977173], "policy_updates": 41360, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8116.017329345, "contact_bce": 0.3093424439430237, "contact_force_loss": 0.031799398362636566, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.999772310256958, 0.9991310834884644, 2.994767427444458]} {"step": 41470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41470, "total_transitions": 169861120, "num_steps_per_env": 1, "wm_loss": 0.4507072865962982, "actor_loss": -8.648787498474121, "critic_loss": 0.020923739299178123, "reward": 0.07124096900224686, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25136473774909973, 0.1525312215089798, 0.254099577665329], "policy_updates": 41370, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8119.533901489999, "contact_bce": 0.3196626901626587, "contact_force_loss": 0.03301220387220383, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.999772310256958, 0.9983094930648804, 2.994767427444458]} {"step": 41480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41480, "total_transitions": 169902080, "num_steps_per_env": 1, "wm_loss": 0.41534188389778137, "actor_loss": -8.702980041503906, "critic_loss": 0.02672114036977291, "reward": 0.07124769687652588, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2539761960506439, 0.15489640831947327, 0.25257909297943115], "policy_updates": 41380, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8123.0573954559995, "contact_bce": 0.30996108055114746, "contact_force_loss": 0.032455772161483765, "terrain_level_mean": 3.212646484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.999772310256958, 0.9983094930648804, 2.994767427444458]} {"step": 41490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41490, "total_transitions": 169943040, "num_steps_per_env": 1, "wm_loss": 0.40074703097343445, "actor_loss": -8.77598762512207, "critic_loss": 0.03074885718524456, "reward": 0.07093503326177597, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2507028877735138, 0.15605589747428894, 0.2534894049167633], "policy_updates": 41390, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8126.578711727999, "contact_bce": 0.3161497116088867, "contact_force_loss": 0.032373953610658646, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.999772310256958, 0.9983094930648804, 2.994767427444458]} {"step": 41500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41500, "total_transitions": 169984000, "num_steps_per_env": 1, "wm_loss": 0.4345950186252594, "actor_loss": -8.689282417297363, "critic_loss": 0.024396440014243126, "reward": 0.07119371742010117, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24573157727718353, 0.15619546175003052, 0.24648195505142212], "policy_updates": 41400, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8130.103556936, "contact_bce": 0.3129110038280487, "contact_force_loss": 0.03331978619098663, "terrain_level_mean": 3.214599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.999772310256958, 0.9983094930648804, 2.999338150024414]} {"step": 41510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41510, "total_transitions": 170024960, "num_steps_per_env": 1, "wm_loss": 0.40968599915504456, "actor_loss": -8.698132514953613, "critic_loss": 0.021990926936268806, "reward": 0.07125568389892578, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24980925023555756, 0.15526984632015228, 0.24756045639514923], "policy_updates": 41410, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8133.633043470999, "contact_bce": 0.31309226155281067, "contact_force_loss": 0.03253980353474617, "terrain_level_mean": 3.2158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.999772310256958, 0.9989751577377319, 2.999338150024414]} {"step": 41520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41520, "total_transitions": 170065920, "num_steps_per_env": 1, "wm_loss": 0.4143112897872925, "actor_loss": -8.68815803527832, "critic_loss": 0.03358977660536766, "reward": 0.0710805207490921, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24712519347667694, 0.15481671690940857, 0.25169822573661804], "policy_updates": 41420, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8137.150384366, "contact_bce": 0.31037670373916626, "contact_force_loss": 0.0320533849298954, "terrain_level_mean": 3.21435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9982577562332153, 0.9990153312683105, 2.999338150024414]} {"step": 41530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41530, "total_transitions": 170106880, "num_steps_per_env": 1, "wm_loss": 0.40295618772506714, "actor_loss": -8.714588165283203, "critic_loss": 0.02312139980494976, "reward": 0.07128188759088516, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24667862057685852, 0.15457351505756378, 0.24924558401107788], "policy_updates": 41430, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8140.664642810999, "contact_bce": 0.3118332624435425, "contact_force_loss": 0.03237579017877579, "terrain_level_mean": 3.2158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9982577562332153, 0.9990153312683105, 2.999338150024414]} {"step": 41540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41540, "total_transitions": 170147840, "num_steps_per_env": 1, "wm_loss": 0.38756847381591797, "actor_loss": -8.730369567871094, "critic_loss": 0.02075025625526905, "reward": 0.07139750570058823, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24528969824314117, 0.15341392159461975, 0.248752623796463], "policy_updates": 41440, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8144.161562844, "contact_bce": 0.3137228190898895, "contact_force_loss": 0.03172420710325241, "terrain_level_mean": 3.2158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9982577562332153, 0.9990153312683105, 2.999338150024414]} {"step": 41550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41550, "total_transitions": 170188800, "num_steps_per_env": 1, "wm_loss": 0.41005924344062805, "actor_loss": -8.763851165771484, "critic_loss": 0.024265846237540245, "reward": 0.07155922055244446, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24271290004253387, 0.15236105024814606, 0.24951019883155823], "policy_updates": 41450, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8147.669383355999, "contact_bce": 0.3139476180076599, "contact_force_loss": 0.03172343224287033, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9982577562332153, 0.9990153312683105, 2.999338150024414]} {"step": 41560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41560, "total_transitions": 170229760, "num_steps_per_env": 1, "wm_loss": 0.4101601541042328, "actor_loss": -8.7552490234375, "critic_loss": 0.027898335829377174, "reward": 0.07134213298559189, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24486887454986572, 0.15322937071323395, 0.24706058204174042], "policy_updates": 41460, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8151.1813857259995, "contact_bce": 0.31228962540626526, "contact_force_loss": 0.03320033848285675, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9979830980300903, 0.9990153312683105, 2.999338150024414]} {"step": 41570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41570, "total_transitions": 170270720, "num_steps_per_env": 1, "wm_loss": 0.4358728229999542, "actor_loss": -8.723861694335938, "critic_loss": 0.021995900198817253, "reward": 0.07146848738193512, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24861478805541992, 0.15511554479599, 0.24646145105361938], "policy_updates": 41470, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8154.699044570999, "contact_bce": 0.3162561357021332, "contact_force_loss": 0.03331490233540535, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9979830980300903, 0.9990153312683105, 2.999338150024414]} {"step": 41580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41580, "total_transitions": 170311680, "num_steps_per_env": 1, "wm_loss": 0.43637606501579285, "actor_loss": -8.712417602539062, "critic_loss": 0.035799797624349594, "reward": 0.07173987478017807, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2445915937423706, 0.1519404947757721, 0.24537412822246552], "policy_updates": 41480, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8158.474664028, "contact_bce": 0.3133935332298279, "contact_force_loss": 0.033819083124399185, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9979830980300903, 0.9990153312683105, 2.999338150024414]} {"step": 41590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41590, "total_transitions": 170352640, "num_steps_per_env": 1, "wm_loss": 0.38918575644493103, "actor_loss": -8.788545608520508, "critic_loss": 0.015456628985702991, "reward": 0.07182934135198593, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2404024451971054, 0.15011939406394958, 0.24750421941280365], "policy_updates": 41490, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8161.993429379999, "contact_bce": 0.3140052556991577, "contact_force_loss": 0.03154496103525162, "terrain_level_mean": 3.215087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9979830980300903, 0.9990153312683105, 2.999338150024414]} {"step": 41600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41600, "total_transitions": 170393600, "num_steps_per_env": 1, "wm_loss": 0.4281260073184967, "actor_loss": -8.712555885314941, "critic_loss": 0.028372740373015404, "reward": 0.07127309590578079, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24126437306404114, 0.15341293811798096, 0.2537972033023834], "policy_updates": 41500, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8165.5059148909995, "contact_bce": 0.32014521956443787, "contact_force_loss": 0.03214915841817856, "terrain_level_mean": 3.214599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9979830980300903, 0.9990153312683105, 2.999338150024414]} {"step": 41610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41610, "total_transitions": 170434560, "num_steps_per_env": 1, "wm_loss": 0.4445192217826843, "actor_loss": -8.806631088256836, "critic_loss": 0.02398056723177433, "reward": 0.0711655467748642, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2461274415254593, 0.15495023131370544, 0.256194144487381], "policy_updates": 41510, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8169.020080444, "contact_bce": 0.311864972114563, "contact_force_loss": 0.03282547742128372, "terrain_level_mean": 3.2158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9979830980300903, 0.999518871307373, 2.999338150024414]} {"step": 41620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41620, "total_transitions": 170475520, "num_steps_per_env": 1, "wm_loss": 0.42433491349220276, "actor_loss": -8.777724266052246, "critic_loss": 0.02337951958179474, "reward": 0.07114886492490768, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24653328955173492, 0.1537514626979828, 0.2561233937740326], "policy_updates": 41520, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8172.543560982999, "contact_bce": 0.31030604243278503, "contact_force_loss": 0.032469864934682846, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9979830980300903, 0.999518871307373, 2.999338150024414]} {"step": 41630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41630, "total_transitions": 170516480, "num_steps_per_env": 1, "wm_loss": 0.387738972902298, "actor_loss": -8.77681827545166, "critic_loss": 0.02015937864780426, "reward": 0.07105528563261032, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24683178961277008, 0.15315169095993042, 0.25272053480148315], "policy_updates": 41530, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8176.057874437999, "contact_bce": 0.3113986849784851, "contact_force_loss": 0.03104296699166298, "terrain_level_mean": 3.216064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9979830980300903, 0.999518871307373, 2.999338150024414]} {"step": 41640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41640, "total_transitions": 170557440, "num_steps_per_env": 1, "wm_loss": 0.47569242119789124, "actor_loss": -8.72119140625, "critic_loss": 0.024182621389627457, "reward": 0.07123055309057236, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24824154376983643, 0.15214145183563232, 0.2515685558319092], "policy_updates": 41540, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8179.580152346, "contact_bce": 0.3146892786026001, "contact_force_loss": 0.032087549567222595, "terrain_level_mean": 3.21630859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.998921513557434, 0.999518871307373, 2.999338150024414]} {"step": 41650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41650, "total_transitions": 170598400, "num_steps_per_env": 1, "wm_loss": 0.42635682225227356, "actor_loss": -8.71483325958252, "critic_loss": 0.022434934973716736, "reward": 0.07111969590187073, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2487175166606903, 0.15425631403923035, 0.2521877586841583], "policy_updates": 41550, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8183.093256929999, "contact_bce": 0.3136562407016754, "contact_force_loss": 0.03161827474832535, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.998921513557434, 0.999518871307373, 2.999338150024414]} {"step": 41660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41660, "total_transitions": 170639360, "num_steps_per_env": 1, "wm_loss": 0.4202410876750946, "actor_loss": -8.755615234375, "critic_loss": 0.024774301797151566, "reward": 0.07152184844017029, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2459801584482193, 0.15460169315338135, 0.25280627608299255], "policy_updates": 41560, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8186.616568082999, "contact_bce": 0.30602386593818665, "contact_force_loss": 0.03214016929268837, "terrain_level_mean": 3.215087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.998921513557434, 0.9998608827590942, 2.999338150024414]} {"step": 41670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41670, "total_transitions": 170680320, "num_steps_per_env": 1, "wm_loss": 0.4010903835296631, "actor_loss": -8.729732513427734, "critic_loss": 0.024126378819346428, "reward": 0.07132788747549057, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24867551028728485, 0.15640129148960114, 0.2561877369880676], "policy_updates": 41570, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8190.157527221999, "contact_bce": 0.3107449412345886, "contact_force_loss": 0.03152884170413017, "terrain_level_mean": 3.214599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.998921513557434, 0.9998608827590942, 2.999338150024414]} {"step": 41680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41680, "total_transitions": 170721280, "num_steps_per_env": 1, "wm_loss": 0.43120649456977844, "actor_loss": -8.786700248718262, "critic_loss": 0.02846313826739788, "reward": 0.07156720012426376, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24681323766708374, 0.1561041921377182, 0.25332313776016235], "policy_updates": 41580, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8193.68150192, "contact_bce": 0.31549254059791565, "contact_force_loss": 0.03259969875216484, "terrain_level_mean": 3.214111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.998921513557434, 0.9998608827590942, 2.999338150024414]} {"step": 41690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41690, "total_transitions": 170762240, "num_steps_per_env": 1, "wm_loss": 0.40749990940093994, "actor_loss": -8.787884712219238, "critic_loss": 0.024518150836229324, "reward": 0.07112492620944977, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24941396713256836, 0.1553509682416916, 0.2518042027950287], "policy_updates": 41590, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8197.194470572, "contact_bce": 0.3174704313278198, "contact_force_loss": 0.032946981489658356, "terrain_level_mean": 3.214599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.998921513557434, 0.9998608827590942, 2.9975099563598633]} {"step": 41700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41700, "total_transitions": 170803200, "num_steps_per_env": 1, "wm_loss": 0.4223269522190094, "actor_loss": -8.76144790649414, "critic_loss": 0.026155192404985428, "reward": 0.07113878428936005, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24847491085529327, 0.15458737313747406, 0.2498113512992859], "policy_updates": 41600, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8200.71560418, "contact_bce": 0.3130744397640228, "contact_force_loss": 0.03212132304906845, "terrain_level_mean": 3.21435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.998921513557434, 0.9998608827590942, 2.9975099563598633]} {"step": 41710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41710, "total_transitions": 170844160, "num_steps_per_env": 1, "wm_loss": 0.4402129352092743, "actor_loss": -8.772098541259766, "critic_loss": 0.030122060328722, "reward": 0.07113602757453918, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24366676807403564, 0.15509548783302307, 0.2465931624174118], "policy_updates": 41610, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8204.233311854001, "contact_bce": 0.31409943103790283, "contact_force_loss": 0.032447464764118195, "terrain_level_mean": 3.2138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.998921513557434, 0.999518871307373, 2.9975099563598633]} {"step": 41720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41720, "total_transitions": 170885120, "num_steps_per_env": 1, "wm_loss": 0.39755183458328247, "actor_loss": -8.748308181762695, "critic_loss": 0.02925175428390503, "reward": 0.07137149572372437, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24394658207893372, 0.15567177534103394, 0.24997001886367798], "policy_updates": 41620, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8207.767639851001, "contact_bce": 0.31128886342048645, "contact_force_loss": 0.03213003650307655, "terrain_level_mean": 3.2138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.998921513557434, 0.999518871307373, 2.9975099563598633]} {"step": 41730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41730, "total_transitions": 170926080, "num_steps_per_env": 1, "wm_loss": 0.4072616696357727, "actor_loss": -8.786581039428711, "critic_loss": 0.026838252320885658, "reward": 0.07124251872301102, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2483409196138382, 0.15655498206615448, 0.25428399443626404], "policy_updates": 41630, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8211.288499033, "contact_bce": 0.31042373180389404, "contact_force_loss": 0.03243616223335266, "terrain_level_mean": 3.2138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.998921513557434, 0.999518871307373, 2.9975099563598633]} {"step": 41740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41740, "total_transitions": 170967040, "num_steps_per_env": 1, "wm_loss": 0.4287622570991516, "actor_loss": -8.727296829223633, "critic_loss": 0.028326768428087234, "reward": 0.07128157466650009, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2505866587162018, 0.1539895087480545, 0.2521189749240875], "policy_updates": 41640, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8215.060693680001, "contact_bce": 0.3163355886936188, "contact_force_loss": 0.0322614386677742, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.998921513557434, 0.999518871307373, 2.9975099563598633]} {"step": 41750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41750, "total_transitions": 171008000, "num_steps_per_env": 1, "wm_loss": 0.42973023653030396, "actor_loss": -8.704071044921875, "critic_loss": 0.02616320364177227, "reward": 0.07137847691774368, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24901030957698822, 0.15254683792591095, 0.25602179765701294], "policy_updates": 41650, "skipped_updates": 0, "invalid_env_resets": 76, "elapsed_s": 8218.577739341, "contact_bce": 0.31452131271362305, "contact_force_loss": 0.03165213018655777, "terrain_level_mean": 3.215087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9970004558563232, 0.999518871307373, 2.9991729259490967]} RECOVERY reset 1 invalid environments; first IDs=[953] {"step": 41760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41760, "total_transitions": 171048960, "num_steps_per_env": 1, "wm_loss": 0.42476704716682434, "actor_loss": -8.745866775512695, "critic_loss": 0.029219061136245728, "reward": 0.07135727256536484, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24760055541992188, 0.15155528485774994, 0.25395357608795166], "policy_updates": 41660, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8222.111619528001, "contact_bce": 0.3129827380180359, "contact_force_loss": 0.03177875280380249, "terrain_level_mean": 3.214599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9970004558563232, 0.999518871307373, 2.9991729259490967]} {"step": 41770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41770, "total_transitions": 171089920, "num_steps_per_env": 1, "wm_loss": 0.4126253128051758, "actor_loss": -8.745339393615723, "critic_loss": 0.029935309663414955, "reward": 0.07136358320713043, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24588432908058167, 0.15228819847106934, 0.25458264350891113], "policy_updates": 41670, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8225.635171501, "contact_bce": 0.3129006028175354, "contact_force_loss": 0.03173673525452614, "terrain_level_mean": 3.214111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9991729259490967]} {"step": 41780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41780, "total_transitions": 171130880, "num_steps_per_env": 1, "wm_loss": 0.4008680284023285, "actor_loss": -8.719537734985352, "critic_loss": 0.02475162222981453, "reward": 0.07153987139463425, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24187009036540985, 0.1539262980222702, 0.25135117769241333], "policy_updates": 41680, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8229.152613965001, "contact_bce": 0.30931150913238525, "contact_force_loss": 0.03136836737394333, "terrain_level_mean": 3.212646484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9991729259490967]} {"step": 41790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41790, "total_transitions": 171171840, "num_steps_per_env": 1, "wm_loss": 0.41289961338043213, "actor_loss": -8.741231918334961, "critic_loss": 0.029658764600753784, "reward": 0.07081669569015503, "falls": 13, "interval_steps": 10, "velocity_mae": [0.24388745427131653, 0.15640240907669067, 0.2556215226650238], "policy_updates": 41690, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8232.682336720001, "contact_bce": 0.3089319169521332, "contact_force_loss": 0.03222346678376198, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9991729259490967]} {"step": 41800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41800, "total_transitions": 171212800, "num_steps_per_env": 1, "wm_loss": 0.3987188935279846, "actor_loss": -8.742925643920898, "critic_loss": 0.026184333488345146, "reward": 0.07060229033231735, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2469879537820816, 0.1567760407924652, 0.25616949796676636], "policy_updates": 41700, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8236.208320163001, "contact_bce": 0.31041163206100464, "contact_force_loss": 0.030945930629968643, "terrain_level_mean": 3.2099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41810, "total_transitions": 171253760, "num_steps_per_env": 1, "wm_loss": 0.41557803750038147, "actor_loss": -8.71234130859375, "critic_loss": 0.02953486144542694, "reward": 0.0706343799829483, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24917595088481903, 0.15515409409999847, 0.2534767687320709], "policy_updates": 41710, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8239.729788755001, "contact_bce": 0.32173535227775574, "contact_force_loss": 0.03307388722896576, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41820, "total_transitions": 171294720, "num_steps_per_env": 1, "wm_loss": 0.41694310307502747, "actor_loss": -8.7358980178833, "critic_loss": 0.026167631149291992, "reward": 0.07016420364379883, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25077319145202637, 0.15757565200328827, 0.2558084726333618], "policy_updates": 41720, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8243.25434467, "contact_bce": 0.3196064233779907, "contact_force_loss": 0.03350215032696724, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41830, "total_transitions": 171335680, "num_steps_per_env": 1, "wm_loss": 0.43098369240760803, "actor_loss": -8.80298900604248, "critic_loss": 0.02143389917910099, "reward": 0.07056158781051636, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24617983400821686, 0.15976493060588837, 0.25448113679885864], "policy_updates": 41730, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8246.775837426001, "contact_bce": 0.3111445903778076, "contact_force_loss": 0.03182796761393547, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41840, "total_transitions": 171376640, "num_steps_per_env": 1, "wm_loss": 0.42971426248550415, "actor_loss": -8.723001480102539, "critic_loss": 0.020898398011922836, "reward": 0.07055207341909409, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24811841547489166, 0.15848691761493683, 0.2523370385169983], "policy_updates": 41740, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8250.298708544, "contact_bce": 0.31581929326057434, "contact_force_loss": 0.03348814696073532, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41850, "total_transitions": 171417600, "num_steps_per_env": 1, "wm_loss": 0.41946935653686523, "actor_loss": -8.756185531616211, "critic_loss": 0.029171139001846313, "reward": 0.07061290740966797, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2526841163635254, 0.1560041308403015, 0.2541358470916748], "policy_updates": 41750, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8253.822911999001, "contact_bce": 0.3118348717689514, "contact_force_loss": 0.032390251755714417, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41860, "total_transitions": 171458560, "num_steps_per_env": 1, "wm_loss": 0.4238385260105133, "actor_loss": -8.7769775390625, "critic_loss": 0.02084164135158062, "reward": 0.070635125041008, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2511792778968811, 0.15523530542850494, 0.2527458369731903], "policy_updates": 41760, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8257.342547518001, "contact_bce": 0.3072986602783203, "contact_force_loss": 0.03174395486712456, "terrain_level_mean": 3.210693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41870, "total_transitions": 171499520, "num_steps_per_env": 1, "wm_loss": 0.39428895711898804, "actor_loss": -8.755317687988281, "critic_loss": 0.018660251051187515, "reward": 0.07077562063932419, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24899780750274658, 0.156401589512825, 0.25628411769866943], "policy_updates": 41770, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8261.117665953001, "contact_bce": 0.31232669949531555, "contact_force_loss": 0.03169848024845123, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41880, "total_transitions": 171540480, "num_steps_per_env": 1, "wm_loss": 0.42862552404403687, "actor_loss": -8.738941192626953, "critic_loss": 0.027572596445679665, "reward": 0.07064642012119293, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24701575934886932, 0.15674085915088654, 0.2513647675514221], "policy_updates": 41780, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8264.639903737001, "contact_bce": 0.31146422028541565, "contact_force_loss": 0.0324711948633194, "terrain_level_mean": 3.2099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41890, "total_transitions": 171581440, "num_steps_per_env": 1, "wm_loss": 0.3898106813430786, "actor_loss": -8.711790084838867, "critic_loss": 0.022214293479919434, "reward": 0.07111090421676636, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24380509555339813, 0.15773004293441772, 0.25337350368499756], "policy_updates": 41790, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8268.154263609, "contact_bce": 0.3041577935218811, "contact_force_loss": 0.03151234984397888, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41900, "total_transitions": 171622400, "num_steps_per_env": 1, "wm_loss": 0.38545164465904236, "actor_loss": -8.745361328125, "critic_loss": 0.029702801257371902, "reward": 0.0707007348537445, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24855205416679382, 0.15754848718643188, 0.2574903070926666], "policy_updates": 41800, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8271.669597338001, "contact_bce": 0.3117940425872803, "contact_force_loss": 0.03189272806048393, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9970004558563232, 0.9995315074920654, 2.9993436336517334]} {"step": 41910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41910, "total_transitions": 171663360, "num_steps_per_env": 1, "wm_loss": 0.4410523772239685, "actor_loss": -8.757745742797852, "critic_loss": 0.029682070016860962, "reward": 0.0702093169093132, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24949057400226593, 0.15597625076770782, 0.26006388664245605], "policy_updates": 41810, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8275.182199696, "contact_bce": 0.3113817572593689, "contact_force_loss": 0.03308503329753876, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9985193014144897, 0.9995315074920654, 2.9993436336517334]} {"step": 41920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41920, "total_transitions": 171704320, "num_steps_per_env": 1, "wm_loss": 0.41024649143218994, "actor_loss": -8.749689102172852, "critic_loss": 0.033181753009557724, "reward": 0.07036686688661575, "falls": 5, "interval_steps": 10, "velocity_mae": [0.250399112701416, 0.15590377151966095, 0.2538714110851288], "policy_updates": 41820, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8278.703399617001, "contact_bce": 0.31147658824920654, "contact_force_loss": 0.03210512548685074, "terrain_level_mean": 3.2099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9985193014144897, 0.9995315074920654, 2.9993436336517334]} {"step": 41930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41930, "total_transitions": 171745280, "num_steps_per_env": 1, "wm_loss": 0.41364145278930664, "actor_loss": -8.737052917480469, "critic_loss": 0.02695634961128235, "reward": 0.07017713040113449, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2510394752025604, 0.15612556040287018, 0.25581133365631104], "policy_updates": 41830, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8282.217310850001, "contact_bce": 0.3112926483154297, "contact_force_loss": 0.03282997012138367, "terrain_level_mean": 3.209228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.9985193014144897, 0.9995315074920654, 2.9993436336517334]} {"step": 41940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41940, "total_transitions": 171786240, "num_steps_per_env": 1, "wm_loss": 0.4215801954269409, "actor_loss": -8.67773723602295, "critic_loss": 0.03161464259028435, "reward": 0.07021472603082657, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2529025971889496, 0.1556965410709381, 0.25571000576019287], "policy_updates": 41840, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8285.734587074001, "contact_bce": 0.30757272243499756, "contact_force_loss": 0.03238091990351677, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9985193014144897, 0.9995315074920654, 2.9993436336517334]} {"step": 41950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41950, "total_transitions": 171827200, "num_steps_per_env": 1, "wm_loss": 0.404825896024704, "actor_loss": -8.763227462768555, "critic_loss": 0.022635774686932564, "reward": 0.07016803324222565, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2510651648044586, 0.15725599229335785, 0.25944268703460693], "policy_updates": 41850, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8289.260283623, "contact_bce": 0.3078591227531433, "contact_force_loss": 0.031199904158711433, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9985193014144897, 0.9995315074920654, 2.9993436336517334]} {"step": 41960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41960, "total_transitions": 171868160, "num_steps_per_env": 1, "wm_loss": 0.4160138666629791, "actor_loss": -8.741500854492188, "critic_loss": 0.01950235292315483, "reward": 0.06997054070234299, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2518934905529022, 0.15564538538455963, 0.2534012198448181], "policy_updates": 41860, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8292.78026166, "contact_bce": 0.31026941537857056, "contact_force_loss": 0.031847063452005386, "terrain_level_mean": 3.208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9914183616638184, 0.9995315074920654, 2.9993436336517334]} {"step": 41970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41970, "total_transitions": 171909120, "num_steps_per_env": 1, "wm_loss": 0.43406519293785095, "actor_loss": -8.694523811340332, "critic_loss": 0.03799647092819214, "reward": 0.07044486701488495, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2527579963207245, 0.15615175664424896, 0.2527567744255066], "policy_updates": 41870, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8296.297967937, "contact_bce": 0.3151091933250427, "contact_force_loss": 0.03326248750090599, "terrain_level_mean": 3.20947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9914183616638184, 0.9995315074920654, 2.9993436336517334]} {"step": 41980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41980, "total_transitions": 171950080, "num_steps_per_env": 1, "wm_loss": 0.41142773628234863, "actor_loss": -8.746099472045898, "critic_loss": 0.023571917787194252, "reward": 0.0708962231874466, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24997758865356445, 0.15415059030056, 0.25211918354034424], "policy_updates": 41880, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8300.072845206001, "contact_bce": 0.3125392198562622, "contact_force_loss": 0.03310051187872887, "terrain_level_mean": 3.209228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.993617296218872, 0.9995315074920654, 2.9998371601104736]} {"step": 41990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 41990, "total_transitions": 171991040, "num_steps_per_env": 1, "wm_loss": 0.41624367237091064, "actor_loss": -8.729705810546875, "critic_loss": 0.023811856284737587, "reward": 0.0711737871170044, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2472020387649536, 0.15218470990657806, 0.24955995380878448], "policy_updates": 41890, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8303.586110844, "contact_bce": 0.3072337210178375, "contact_force_loss": 0.03166433051228523, "terrain_level_mean": 3.208984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.993617296218872, 0.9994717240333557, 2.9998371601104736]} {"step": 42000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42000, "total_transitions": 172032000, "num_steps_per_env": 1, "wm_loss": 0.41641223430633545, "actor_loss": -8.714347839355469, "critic_loss": 0.026671096682548523, "reward": 0.07058573514223099, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24821211397647858, 0.15352965891361237, 0.25684118270874023], "policy_updates": 41900, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8307.100177855, "contact_bce": 0.3122079074382782, "contact_force_loss": 0.03327757865190506, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.993617296218872, 0.9994717240333557, 2.9998371601104736]} {"step": 42010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42010, "total_transitions": 172072960, "num_steps_per_env": 1, "wm_loss": 0.42052680253982544, "actor_loss": -8.692035675048828, "critic_loss": 0.027304334565997124, "reward": 0.07039061933755875, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24724318087100983, 0.15570151805877686, 0.2558833658695221], "policy_updates": 41910, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8310.645663875, "contact_bce": 0.3038494288921356, "contact_force_loss": 0.032579969614744186, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.993617296218872, 0.9994717240333557, 2.9998371601104736]} {"step": 42020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42020, "total_transitions": 172113920, "num_steps_per_env": 1, "wm_loss": 0.401266485452652, "actor_loss": -8.747793197631836, "critic_loss": 0.026856128126382828, "reward": 0.07054754346609116, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24939072132110596, 0.15514561533927917, 0.254211962223053], "policy_updates": 41920, "skipped_updates": 0, "invalid_env_resets": 77, "elapsed_s": 8314.171253974, "contact_bce": 0.3077287971973419, "contact_force_loss": 0.03196283057332039, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.993617296218872, 0.9994717240333557, 2.9998371601104736]} RECOVERY reset 1 invalid environments; first IDs=[2147] {"step": 42030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42030, "total_transitions": 172154880, "num_steps_per_env": 1, "wm_loss": 0.39420226216316223, "actor_loss": -8.76552963256836, "critic_loss": 0.025892911478877068, "reward": 0.07016391307115555, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25417542457580566, 0.15551884472370148, 0.2537221908569336], "policy_updates": 41930, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8317.701722222, "contact_bce": 0.30723950266838074, "contact_force_loss": 0.03223129361867905, "terrain_level_mean": 3.210693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.993617296218872, 0.9994717240333557, 2.9998371601104736]} {"step": 42040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42040, "total_transitions": 172195840, "num_steps_per_env": 1, "wm_loss": 0.436561644077301, "actor_loss": -8.739850044250488, "critic_loss": 0.022042585536837578, "reward": 0.0705912858247757, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2505711317062378, 0.15579983592033386, 0.25284039974212646], "policy_updates": 41940, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8321.228079916, "contact_bce": 0.3122267723083496, "contact_force_loss": 0.03278457745909691, "terrain_level_mean": 3.210693359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42050, "total_transitions": 172236800, "num_steps_per_env": 1, "wm_loss": 0.43541219830513, "actor_loss": -8.73765754699707, "critic_loss": 0.025057515129446983, "reward": 0.07053434103727341, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2502847909927368, 0.15367518365383148, 0.25270891189575195], "policy_updates": 41950, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8324.73596023, "contact_bce": 0.3158009350299835, "contact_force_loss": 0.032902561128139496, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42060, "total_transitions": 172277760, "num_steps_per_env": 1, "wm_loss": 0.4457719326019287, "actor_loss": -8.72036361694336, "critic_loss": 0.023950867354869843, "reward": 0.07108590751886368, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24426758289337158, 0.15233193337917328, 0.2509881556034088], "policy_updates": 41960, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8328.247165656001, "contact_bce": 0.31189998984336853, "contact_force_loss": 0.032512176781892776, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42070, "total_transitions": 172318720, "num_steps_per_env": 1, "wm_loss": 0.42661720514297485, "actor_loss": -8.751615524291992, "critic_loss": 0.023629803210496902, "reward": 0.07108185440301895, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24336712062358856, 0.15470866858959198, 0.25297313928604126], "policy_updates": 41970, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8331.762189673, "contact_bce": 0.31371355056762695, "contact_force_loss": 0.032169561833143234, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42080, "total_transitions": 172359680, "num_steps_per_env": 1, "wm_loss": 0.38561001420021057, "actor_loss": -8.675203323364258, "critic_loss": 0.035882510244846344, "reward": 0.07092050462961197, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24778662621974945, 0.15370473265647888, 0.25203728675842285], "policy_updates": 41980, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8335.259513362, "contact_bce": 0.3117162883281708, "contact_force_loss": 0.03235757723450661, "terrain_level_mean": 3.21142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42090, "total_transitions": 172400640, "num_steps_per_env": 1, "wm_loss": 0.40440061688423157, "actor_loss": -8.686572074890137, "critic_loss": 0.03143460676074028, "reward": 0.07089848816394806, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2500995695590973, 0.15463608503341675, 0.25388485193252563], "policy_updates": 41990, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8338.759067601, "contact_bce": 0.3078579902648926, "contact_force_loss": 0.032279785722494125, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42100, "total_transitions": 172441600, "num_steps_per_env": 1, "wm_loss": 0.41358765959739685, "actor_loss": -8.704179763793945, "critic_loss": 0.03216578811407089, "reward": 0.07115067541599274, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24577227234840393, 0.1556641310453415, 0.25056737661361694], "policy_updates": 42000, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8342.263745284, "contact_bce": 0.3134051263332367, "contact_force_loss": 0.031994424760341644, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42110, "total_transitions": 172482560, "num_steps_per_env": 1, "wm_loss": 0.4235525131225586, "actor_loss": -8.681130409240723, "critic_loss": 0.03275008872151375, "reward": 0.07150457799434662, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2447517365217209, 0.15377835929393768, 0.2471788078546524], "policy_updates": 42010, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8346.033970215001, "contact_bce": 0.31538674235343933, "contact_force_loss": 0.03236224502325058, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9988224506378174, 0.9999616146087646, 2.9998371601104736]} {"step": 42120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42120, "total_transitions": 172523520, "num_steps_per_env": 1, "wm_loss": 0.3955296277999878, "actor_loss": -8.74705696105957, "critic_loss": 0.02690737508237362, "reward": 0.07111610472202301, "falls": 5, "interval_steps": 10, "velocity_mae": [0.243937686085701, 0.15447254478931427, 0.24553915858268738], "policy_updates": 42020, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8349.554186253, "contact_bce": 0.309538871049881, "contact_force_loss": 0.032233886420726776, "terrain_level_mean": 3.21142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9998371601104736]} {"step": 42130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42130, "total_transitions": 172564480, "num_steps_per_env": 1, "wm_loss": 0.4193730354309082, "actor_loss": -8.749570846557617, "critic_loss": 0.029386093840003014, "reward": 0.07139936834573746, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24345305562019348, 0.15154317021369934, 0.2463778555393219], "policy_updates": 42030, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8353.070869145, "contact_bce": 0.31664350628852844, "contact_force_loss": 0.03313419222831726, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9998371601104736]} {"step": 42140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42140, "total_transitions": 172605440, "num_steps_per_env": 1, "wm_loss": 0.4134337902069092, "actor_loss": -8.775264739990234, "critic_loss": 0.030989274382591248, "reward": 0.07134183496236801, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2411397248506546, 0.1522052139043808, 0.2465040534734726], "policy_updates": 42040, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8356.569396744, "contact_bce": 0.307914674282074, "contact_force_loss": 0.0315854474902153, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9998371601104736]} {"step": 42150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42150, "total_transitions": 172646400, "num_steps_per_env": 1, "wm_loss": 0.4263826608657837, "actor_loss": -8.73857593536377, "critic_loss": 0.03300895169377327, "reward": 0.07092756032943726, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24903935194015503, 0.15493761003017426, 0.2552964985370636], "policy_updates": 42050, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8360.076192569, "contact_bce": 0.3141924738883972, "contact_force_loss": 0.03278186917304993, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9998371601104736]} {"step": 42160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42160, "total_transitions": 172687360, "num_steps_per_env": 1, "wm_loss": 0.4302233159542084, "actor_loss": -8.76812744140625, "critic_loss": 0.02281135693192482, "reward": 0.07080917805433273, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2516939640045166, 0.15539824962615967, 0.25734326243400574], "policy_updates": 42060, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8363.587401147, "contact_bce": 0.3151085674762726, "contact_force_loss": 0.03231034055352211, "terrain_level_mean": 3.212158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9998371601104736]} {"step": 42170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42170, "total_transitions": 172728320, "num_steps_per_env": 1, "wm_loss": 0.40604040026664734, "actor_loss": -8.703144073486328, "critic_loss": 0.03013141267001629, "reward": 0.07120388746261597, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25248613953590393, 0.1559888869524002, 0.2565324306488037], "policy_updates": 42070, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8367.083205552, "contact_bce": 0.3131358027458191, "contact_force_loss": 0.03241931274533272, "terrain_level_mean": 3.212158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9998371601104736]} {"step": 42180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42180, "total_transitions": 172769280, "num_steps_per_env": 1, "wm_loss": 0.41158348321914673, "actor_loss": -8.75208568572998, "critic_loss": 0.03192353993654251, "reward": 0.07125043123960495, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25312674045562744, 0.15603280067443848, 0.25445806980133057], "policy_updates": 42080, "skipped_updates": 0, "invalid_env_resets": 78, "elapsed_s": 8370.584815869, "contact_bce": 0.3067818284034729, "contact_force_loss": 0.03106953389942646, "terrain_level_mean": 3.21240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9998371601104736]} RECOVERY reset 1 invalid environments; first IDs=[1538] {"step": 42190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42190, "total_transitions": 172810240, "num_steps_per_env": 1, "wm_loss": 0.4038359522819519, "actor_loss": -8.720818519592285, "critic_loss": 0.028424590826034546, "reward": 0.0710546001791954, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25306227803230286, 0.15801022946834564, 0.2528957724571228], "policy_updates": 42090, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8374.099175882, "contact_bce": 0.3111191391944885, "contact_force_loss": 0.03203076124191284, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9986977577209473]} {"step": 42200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42200, "total_transitions": 172851200, "num_steps_per_env": 1, "wm_loss": 0.4087470471858978, "actor_loss": -8.733892440795898, "critic_loss": 0.030229581519961357, "reward": 0.07120257616043091, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24917156994342804, 0.155659019947052, 0.2497524470090866], "policy_updates": 42100, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8377.604625459, "contact_bce": 0.31136003136634827, "contact_force_loss": 0.03179354965686798, "terrain_level_mean": 3.213623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9986977577209473]} {"step": 42210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42210, "total_transitions": 172892160, "num_steps_per_env": 1, "wm_loss": 0.40664684772491455, "actor_loss": -8.765388488769531, "critic_loss": 0.021172497421503067, "reward": 0.07108136266469955, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24717481434345245, 0.15634745359420776, 0.2517199218273163], "policy_updates": 42110, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8381.113100802, "contact_bce": 0.313920795917511, "contact_force_loss": 0.031893279403448105, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9986977577209473]} {"step": 42220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42220, "total_transitions": 172933120, "num_steps_per_env": 1, "wm_loss": 0.43265560269355774, "actor_loss": -8.765499114990234, "critic_loss": 0.024911988526582718, "reward": 0.07117261737585068, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2468455582857132, 0.15842363238334656, 0.25492504239082336], "policy_updates": 42120, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8384.611074833001, "contact_bce": 0.3139990568161011, "contact_force_loss": 0.0327407568693161, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9990639686584473, 0.9999616146087646, 2.9986977577209473]} {"step": 42230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42230, "total_transitions": 172974080, "num_steps_per_env": 1, "wm_loss": 0.41212642192840576, "actor_loss": -8.745465278625488, "critic_loss": 0.02462664805352688, "reward": 0.07140770554542542, "falls": 11, "interval_steps": 10, "velocity_mae": [0.24604271352291107, 0.15639488399028778, 0.25508901476860046], "policy_updates": 42130, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8388.112456951001, "contact_bce": 0.30876800417900085, "contact_force_loss": 0.031441815197467804, "terrain_level_mean": 3.213623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9990639686584473, 0.999378502368927, 2.9986977577209473]} {"step": 42240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42240, "total_transitions": 173015040, "num_steps_per_env": 1, "wm_loss": 0.43387556076049805, "actor_loss": -8.70199966430664, "critic_loss": 0.03215212747454643, "reward": 0.0713159590959549, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2446736842393875, 0.15570631623268127, 0.2525181174278259], "policy_updates": 42140, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8391.629922956, "contact_bce": 0.3127764165401459, "contact_force_loss": 0.032634034752845764, "terrain_level_mean": 3.213623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9990639686584473, 0.999378502368927, 2.9986977577209473]} {"step": 42250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42250, "total_transitions": 173056000, "num_steps_per_env": 1, "wm_loss": 0.38090091943740845, "actor_loss": -8.701956748962402, "critic_loss": 0.02928978018462658, "reward": 0.07104179263114929, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24511906504631042, 0.15546512603759766, 0.24722009897232056], "policy_updates": 42150, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8395.141002377, "contact_bce": 0.30384114384651184, "contact_force_loss": 0.03157052770256996, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9990639686584473, 0.999378502368927, 2.9986977577209473]} {"step": 42260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42260, "total_transitions": 173096960, "num_steps_per_env": 1, "wm_loss": 0.41066405177116394, "actor_loss": -8.753650665283203, "critic_loss": 0.030547117814421654, "reward": 0.0712113007903099, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24316909909248352, 0.15410058200359344, 0.2476533055305481], "policy_updates": 42160, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8398.66316057, "contact_bce": 0.3099502623081207, "contact_force_loss": 0.03260643035173416, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9990639686584473, 0.999378502368927, 2.9986977577209473]} {"step": 42270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42270, "total_transitions": 173137920, "num_steps_per_env": 1, "wm_loss": 0.44863635301589966, "actor_loss": -8.71312141418457, "critic_loss": 0.03762331232428551, "reward": 0.07125328481197357, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24070218205451965, 0.15245667099952698, 0.24623025953769684], "policy_updates": 42170, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8402.191161251001, "contact_bce": 0.3165835738182068, "contact_force_loss": 0.03340887278318405, "terrain_level_mean": 3.213134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9990639686584473, 0.999378502368927, 2.9986977577209473]} {"step": 42280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42280, "total_transitions": 173178880, "num_steps_per_env": 1, "wm_loss": 0.4172433018684387, "actor_loss": -8.766693115234375, "critic_loss": 0.034967295825481415, "reward": 0.0710720643401146, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2405184954404831, 0.15226434171199799, 0.2505970001220703], "policy_updates": 42180, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8405.714131861001, "contact_bce": 0.3088054060935974, "contact_force_loss": 0.03207946941256523, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9979302883148193, 0.999378502368927, 2.9986977577209473]} {"step": 42290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42290, "total_transitions": 173219840, "num_steps_per_env": 1, "wm_loss": 0.42730534076690674, "actor_loss": -8.745922088623047, "critic_loss": 0.02189670316874981, "reward": 0.07118378579616547, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2477293163537979, 0.15413865447044373, 0.2520555555820465], "policy_updates": 42190, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8409.237801533001, "contact_bce": 0.3093768060207367, "contact_force_loss": 0.03246837854385376, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9979302883148193, 0.999378502368927, 2.9986977577209473]} {"step": 42300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42300, "total_transitions": 173260800, "num_steps_per_env": 1, "wm_loss": 0.4203183948993683, "actor_loss": -8.792242050170898, "critic_loss": 0.02868984453380108, "reward": 0.07145974785089493, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24890154600143433, 0.15335844457149506, 0.2516772150993347], "policy_updates": 42200, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8412.761671072001, "contact_bce": 0.31248608231544495, "contact_force_loss": 0.03246702626347542, "terrain_level_mean": 3.21435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9979302883148193, 0.999378502368927, 2.9986977577209473]} {"step": 42310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42310, "total_transitions": 173301760, "num_steps_per_env": 1, "wm_loss": 0.4030407667160034, "actor_loss": -8.71561050415039, "critic_loss": 0.027346450835466385, "reward": 0.07107599824666977, "falls": 8, "interval_steps": 10, "velocity_mae": [0.245235413312912, 0.15471622347831726, 0.2523353695869446], "policy_updates": 42210, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8416.28419638, "contact_bce": 0.31290730834007263, "contact_force_loss": 0.031750429421663284, "terrain_level_mean": 3.213134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9979302883148193, 0.999378502368927, 2.9986977577209473]} {"step": 42320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42320, "total_transitions": 173342720, "num_steps_per_env": 1, "wm_loss": 0.40329962968826294, "actor_loss": -8.789304733276367, "critic_loss": 0.028829405084252357, "reward": 0.07089611142873764, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24284763634204865, 0.15330441296100616, 0.2523626685142517], "policy_updates": 42220, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8419.802781031001, "contact_bce": 0.30665597319602966, "contact_force_loss": 0.031274907290935516, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9979302883148193, 0.999378502368927, 2.9986977577209473]} {"step": 42330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42330, "total_transitions": 173383680, "num_steps_per_env": 1, "wm_loss": 0.41439729928970337, "actor_loss": -8.730897903442383, "critic_loss": 0.03557892516255379, "reward": 0.07097143679857254, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24417206645011902, 0.15475629270076752, 0.25044235587120056], "policy_updates": 42230, "skipped_updates": 0, "invalid_env_resets": 79, "elapsed_s": 8423.321462271, "contact_bce": 0.3132053315639496, "contact_force_loss": 0.032244857400655746, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9979302883148193, 0.998052179813385, 2.998469829559326]} RECOVERY reset 1 invalid environments; first IDs=[1199] {"step": 42340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42340, "total_transitions": 173424640, "num_steps_per_env": 1, "wm_loss": 0.3991939127445221, "actor_loss": -8.740262985229492, "critic_loss": 0.03121362440288067, "reward": 0.07110830396413803, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24569131433963776, 0.1564706414937973, 0.2510046064853668], "policy_updates": 42240, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8426.844385187, "contact_bce": 0.3108189105987549, "contact_force_loss": 0.03138083219528198, "terrain_level_mean": 3.214111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9979302883148193, 0.998052179813385, 2.998469829559326]} {"step": 42350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42350, "total_transitions": 173465600, "num_steps_per_env": 1, "wm_loss": 0.39311444759368896, "actor_loss": -8.73161506652832, "critic_loss": 0.03042515553534031, "reward": 0.07095609605312347, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24370604753494263, 0.1552409827709198, 0.24977771937847137], "policy_updates": 42250, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8430.342207180001, "contact_bce": 0.3056270182132721, "contact_force_loss": 0.031940657645463943, "terrain_level_mean": 3.21435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9979302883148193, 0.998052179813385, 2.998469829559326]} {"step": 42360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42360, "total_transitions": 173506560, "num_steps_per_env": 1, "wm_loss": 0.4001622498035431, "actor_loss": -8.764884948730469, "critic_loss": 0.025078577920794487, "reward": 0.07080386579036713, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24530364573001862, 0.15620602667331696, 0.25789180397987366], "policy_updates": 42260, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8433.845050357, "contact_bce": 0.31531837582588196, "contact_force_loss": 0.032695598900318146, "terrain_level_mean": 3.2138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9979302883148193, 0.998052179813385, 2.998469829559326]} {"step": 42370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42370, "total_transitions": 173547520, "num_steps_per_env": 1, "wm_loss": 0.4234860837459564, "actor_loss": -8.718550682067871, "critic_loss": 0.046280957758426666, "reward": 0.0701403096318245, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24655821919441223, 0.1595924347639084, 0.25933128595352173], "policy_updates": 42270, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8437.360992896001, "contact_bce": 0.31143060326576233, "contact_force_loss": 0.03208586573600769, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998469829559326]} {"step": 42380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42380, "total_transitions": 173588480, "num_steps_per_env": 1, "wm_loss": 0.39491596817970276, "actor_loss": -8.761640548706055, "critic_loss": 0.02509169839322567, "reward": 0.07012554258108139, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24391397833824158, 0.15759438276290894, 0.254090815782547], "policy_updates": 42280, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8440.871188775001, "contact_bce": 0.3078402876853943, "contact_force_loss": 0.03132902458310127, "terrain_level_mean": 3.2138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998469829559326]} {"step": 42390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42390, "total_transitions": 173629440, "num_steps_per_env": 1, "wm_loss": 0.42460209131240845, "actor_loss": -8.699357986450195, "critic_loss": 0.035868752747774124, "reward": 0.07035136222839355, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2433518022298813, 0.15436597168445587, 0.25409382581710815], "policy_updates": 42290, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8444.383078252, "contact_bce": 0.3084436357021332, "contact_force_loss": 0.03268178924918175, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998469829559326]} {"step": 42400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42400, "total_transitions": 173670400, "num_steps_per_env": 1, "wm_loss": 0.42183977365493774, "actor_loss": -8.758110046386719, "critic_loss": 0.03543471172451973, "reward": 0.07077736407518387, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24471056461334229, 0.15755413472652435, 0.2528589963912964], "policy_updates": 42300, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8447.898785151001, "contact_bce": 0.3111492395401001, "contact_force_loss": 0.03212694451212883, "terrain_level_mean": 3.21533203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998469829559326]} {"step": 42410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42410, "total_transitions": 173711360, "num_steps_per_env": 1, "wm_loss": 0.4236202836036682, "actor_loss": -8.728433609008789, "critic_loss": 0.02039848081767559, "reward": 0.0710824728012085, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2443392276763916, 0.1569383293390274, 0.2557765245437622], "policy_updates": 42310, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8451.421275653001, "contact_bce": 0.3114239573478699, "contact_force_loss": 0.03224659711122513, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998469829559326]} {"step": 42420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42420, "total_transitions": 173752320, "num_steps_per_env": 1, "wm_loss": 0.3907450735569, "actor_loss": -8.723001480102539, "critic_loss": 0.03692495450377464, "reward": 0.0711095854640007, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2438305765390396, 0.15656642615795135, 0.2555900514125824], "policy_updates": 42320, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8454.920985375, "contact_bce": 0.31683674454689026, "contact_force_loss": 0.03193828463554382, "terrain_level_mean": 3.215087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9979302883148193, 0.9997895956039429, 2.998469829559326]} {"step": 42430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42430, "total_transitions": 173793280, "num_steps_per_env": 1, "wm_loss": 0.4137180745601654, "actor_loss": -8.75771713256836, "critic_loss": 0.025898901745676994, "reward": 0.07084022462368011, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24407878518104553, 0.15600204467773438, 0.25365957617759705], "policy_updates": 42330, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8458.414928088001, "contact_bce": 0.3134795129299164, "contact_force_loss": 0.032549288123846054, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9979302883148193, 0.9997895956039429, 2.998469829559326]} {"step": 42440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42440, "total_transitions": 173834240, "num_steps_per_env": 1, "wm_loss": 0.40785908699035645, "actor_loss": -8.710217475891113, "critic_loss": 0.033712003380060196, "reward": 0.07042913138866425, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2460106760263443, 0.15922041237354279, 0.2529152035713196], "policy_updates": 42340, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8461.923623332, "contact_bce": 0.31107097864151, "contact_force_loss": 0.03195773810148239, "terrain_level_mean": 3.215087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9979302883148193, 0.9997895956039429, 2.998469829559326]} {"step": 42450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42450, "total_transitions": 173875200, "num_steps_per_env": 1, "wm_loss": 0.41463783383369446, "actor_loss": -8.69869613647461, "critic_loss": 0.03414003178477287, "reward": 0.07016988843679428, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2451329082250595, 0.1617422252893448, 0.25850990414619446], "policy_updates": 42350, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8465.424413006, "contact_bce": 0.3108794391155243, "contact_force_loss": 0.03161408752202988, "terrain_level_mean": 3.214599609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9979302883148193, 0.9997895956039429, 2.998469829559326]} {"step": 42460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42460, "total_transitions": 173916160, "num_steps_per_env": 1, "wm_loss": 0.3887999653816223, "actor_loss": -8.708255767822266, "critic_loss": 0.023828113451600075, "reward": 0.0703597217798233, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24137453734874725, 0.16208961606025696, 0.25819116830825806], "policy_updates": 42360, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8468.929527211001, "contact_bce": 0.30674684047698975, "contact_force_loss": 0.031041208654642105, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998283863067627]} {"step": 42470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42470, "total_transitions": 173957120, "num_steps_per_env": 1, "wm_loss": 0.4720640480518341, "actor_loss": -8.769842147827148, "critic_loss": 0.033960144966840744, "reward": 0.0708613395690918, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24028456211090088, 0.16024760901927948, 0.25072380900382996], "policy_updates": 42370, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8472.439476582, "contact_bce": 0.3136414885520935, "contact_force_loss": 0.032636310905218124, "terrain_level_mean": 3.214111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998283863067627]} {"step": 42480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42480, "total_transitions": 173998080, "num_steps_per_env": 1, "wm_loss": 0.4132275879383087, "actor_loss": -8.738479614257812, "critic_loss": 0.026831144466996193, "reward": 0.07083376497030258, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24174143373966217, 0.1607917696237564, 0.25483012199401855], "policy_updates": 42380, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8475.959679988, "contact_bce": 0.3119477331638336, "contact_force_loss": 0.03267800062894821, "terrain_level_mean": 3.212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998283863067627]} {"step": 42490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42490, "total_transitions": 174039040, "num_steps_per_env": 1, "wm_loss": 0.4371374845504761, "actor_loss": -8.71046257019043, "critic_loss": 0.0313836894929409, "reward": 0.07038668543100357, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24899673461914062, 0.1592886596918106, 0.25513166189193726], "policy_updates": 42390, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8479.482549324, "contact_bce": 0.31106510758399963, "contact_force_loss": 0.033093445003032684, "terrain_level_mean": 3.212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9979302883148193, 0.9993060827255249, 2.998283863067627]} {"step": 42500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42500, "total_transitions": 174080000, "num_steps_per_env": 1, "wm_loss": 0.4174734354019165, "actor_loss": -8.756718635559082, "critic_loss": 0.024718737229704857, "reward": 0.07073567807674408, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2442817986011505, 0.15768124163150787, 0.2517951428890228], "policy_updates": 42400, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8482.999459593, "contact_bce": 0.3124086558818817, "contact_force_loss": 0.032227322459220886, "terrain_level_mean": 3.212158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9993155002593994, 0.9993060827255249, 2.998283863067627]} {"step": 42510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42510, "total_transitions": 174120960, "num_steps_per_env": 1, "wm_loss": 0.4197138845920563, "actor_loss": -8.75892448425293, "critic_loss": 0.029215550050139427, "reward": 0.0711754709482193, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2394728809595108, 0.15873654186725616, 0.2515808939933777], "policy_updates": 42410, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8486.549981635, "contact_bce": 0.3144345283508301, "contact_force_loss": 0.032628435641527176, "terrain_level_mean": 3.21240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9993155002593994, 0.9993060827255249, 2.998283863067627]} {"step": 42520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42520, "total_transitions": 174161920, "num_steps_per_env": 1, "wm_loss": 0.383124977350235, "actor_loss": -8.730159759521484, "critic_loss": 0.019178662449121475, "reward": 0.07110802084207535, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24381065368652344, 0.15585722029209137, 0.2527574300765991], "policy_updates": 42420, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8490.062074176001, "contact_bce": 0.3081042468547821, "contact_force_loss": 0.03150473162531853, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9993155002593994, 0.9993060827255249, 2.998283863067627]} {"step": 42530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42530, "total_transitions": 174202880, "num_steps_per_env": 1, "wm_loss": 0.4457714855670929, "actor_loss": -8.753702163696289, "critic_loss": 0.029554856941103935, "reward": 0.07075085490942001, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25254303216934204, 0.1551736444234848, 0.25010865926742554], "policy_updates": 42430, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8493.562746158, "contact_bce": 0.3127204477787018, "contact_force_loss": 0.03310045599937439, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36181640625, "command_abs_max": [1.9993155002593994, 0.9993060827255249, 2.998283863067627]} {"step": 42540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42540, "total_transitions": 174243840, "num_steps_per_env": 1, "wm_loss": 0.4187457859516144, "actor_loss": -8.72227954864502, "critic_loss": 0.027885574847459793, "reward": 0.07009955495595932, "falls": 3, "interval_steps": 10, "velocity_mae": [0.256696492433548, 0.15519732236862183, 0.25715604424476624], "policy_updates": 42440, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8497.315887368, "contact_bce": 0.3141718804836273, "contact_force_loss": 0.0323629193007946, "terrain_level_mean": 3.212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359375, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.998283863067627]} {"step": 42550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42550, "total_transitions": 174284800, "num_steps_per_env": 1, "wm_loss": 0.41347870230674744, "actor_loss": -8.741100311279297, "critic_loss": 0.027280230075120926, "reward": 0.0701860710978508, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2504902482032776, 0.15576285123825073, 0.253445029258728], "policy_updates": 42450, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8500.818445083001, "contact_bce": 0.3155771493911743, "contact_force_loss": 0.03245745599269867, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.998283863067627]} {"step": 42560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42560, "total_transitions": 174325760, "num_steps_per_env": 1, "wm_loss": 0.4346732199192047, "actor_loss": -8.762153625488281, "critic_loss": 0.03406945988535881, "reward": 0.07058949768543243, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2501921057701111, 0.15806087851524353, 0.2530549466609955], "policy_updates": 42460, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8504.325297733001, "contact_bce": 0.307706743478775, "contact_force_loss": 0.032300449907779694, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357666015625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.998283863067627]} {"step": 42570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42570, "total_transitions": 174366720, "num_steps_per_env": 1, "wm_loss": 0.41507688164711, "actor_loss": -8.7734956741333, "critic_loss": 0.024105481803417206, "reward": 0.07067520916461945, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24877679347991943, 0.15948975086212158, 0.2537754774093628], "policy_updates": 42470, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8507.830976546, "contact_bce": 0.31268924474716187, "contact_force_loss": 0.032213274389505386, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.984786033630371]} {"step": 42580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42580, "total_transitions": 174407680, "num_steps_per_env": 1, "wm_loss": 0.4238402247428894, "actor_loss": -8.736242294311523, "critic_loss": 0.024634918197989464, "reward": 0.07120548188686371, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2457234114408493, 0.15630073845386505, 0.2513873875141144], "policy_updates": 42480, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8511.350591814, "contact_bce": 0.3124575912952423, "contact_force_loss": 0.032418299466371536, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.984786033630371]} {"step": 42590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42590, "total_transitions": 174448640, "num_steps_per_env": 1, "wm_loss": 0.4539772570133209, "actor_loss": -8.715171813964844, "critic_loss": 0.030542923137545586, "reward": 0.07131541520357132, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24490037560462952, 0.15589112043380737, 0.25569236278533936], "policy_updates": 42490, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8514.861601561, "contact_bce": 0.31332114338874817, "contact_force_loss": 0.033187709748744965, "terrain_level_mean": 3.21142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} {"step": 42600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42600, "total_transitions": 174489600, "num_steps_per_env": 1, "wm_loss": 0.41338592767715454, "actor_loss": -8.743509292602539, "critic_loss": 0.030859170481562614, "reward": 0.07083168625831604, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24325665831565857, 0.15665341913700104, 0.26087716221809387], "policy_updates": 42500, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8518.356059202, "contact_bce": 0.3147830069065094, "contact_force_loss": 0.03180891275405884, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} {"step": 42610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42610, "total_transitions": 174530560, "num_steps_per_env": 1, "wm_loss": 0.4010603129863739, "actor_loss": -8.683629035949707, "critic_loss": 0.04298888519406319, "reward": 0.0705508440732956, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2451898157596588, 0.1592174470424652, 0.2565678656101227], "policy_updates": 42510, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8521.861949072001, "contact_bce": 0.3093123733997345, "contact_force_loss": 0.03192153573036194, "terrain_level_mean": 3.211181640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355712890625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} {"step": 42620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42620, "total_transitions": 174571520, "num_steps_per_env": 1, "wm_loss": 0.4214990437030792, "actor_loss": -8.762505531311035, "critic_loss": 0.025743532925844193, "reward": 0.07067812234163284, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24881413578987122, 0.15785031020641327, 0.2532351613044739], "policy_updates": 42520, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8525.361983741, "contact_bce": 0.31370770931243896, "contact_force_loss": 0.0326845720410347, "terrain_level_mean": 3.21142578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} {"step": 42630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42630, "total_transitions": 174612480, "num_steps_per_env": 1, "wm_loss": 0.4742105305194855, "actor_loss": -8.748199462890625, "critic_loss": 0.023437971249222755, "reward": 0.07069361954927444, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24876777827739716, 0.16123390197753906, 0.2561744451522827], "policy_updates": 42530, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8528.859563098, "contact_bce": 0.3095105290412903, "contact_force_loss": 0.032170623540878296, "terrain_level_mean": 3.21044921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} {"step": 42640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42640, "total_transitions": 174653440, "num_steps_per_env": 1, "wm_loss": 0.41992995142936707, "actor_loss": -8.754081726074219, "critic_loss": 0.028552761301398277, "reward": 0.0713149756193161, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24735480546951294, 0.1573108583688736, 0.2530551552772522], "policy_updates": 42540, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8532.361291717001, "contact_bce": 0.31027206778526306, "contact_force_loss": 0.03140668198466301, "terrain_level_mean": 3.210205078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} {"step": 42650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42650, "total_transitions": 174694400, "num_steps_per_env": 1, "wm_loss": 0.414374977350235, "actor_loss": -8.741079330444336, "critic_loss": 0.031007541343569756, "reward": 0.07139952480792999, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2436753809452057, 0.1527852714061737, 0.252016544342041], "policy_updates": 42550, "skipped_updates": 0, "invalid_env_resets": 80, "elapsed_s": 8535.868180006, "contact_bce": 0.3147064447402954, "contact_force_loss": 0.0319514125585556, "terrain_level_mean": 3.2109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} RECOVERY reset 1 invalid environments; first IDs=[702] {"step": 42660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42660, "total_transitions": 174735360, "num_steps_per_env": 1, "wm_loss": 0.39784127473831177, "actor_loss": -8.736478805541992, "critic_loss": 0.031144047155976295, "reward": 0.07134091854095459, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24104376137256622, 0.1538100242614746, 0.2506577968597412], "policy_updates": 42560, "skipped_updates": 0, "invalid_env_resets": 81, "elapsed_s": 8539.393634881, "contact_bce": 0.3111092448234558, "contact_force_loss": 0.031026916578412056, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} {"step": 42670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42670, "total_transitions": 174776320, "num_steps_per_env": 1, "wm_loss": 0.42463287711143494, "actor_loss": -8.70716667175293, "critic_loss": 0.028261912986636162, "reward": 0.07128720730543137, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24076442420482635, 0.15464968979358673, 0.2508034110069275], "policy_updates": 42570, "skipped_updates": 0, "invalid_env_resets": 81, "elapsed_s": 8542.91155877, "contact_bce": 0.31506770849227905, "contact_force_loss": 0.032959647476673126, "terrain_level_mean": 3.211669921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9883780479431152]} RECOVERY reset 1 invalid environments; first IDs=[1323] {"step": 42680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42680, "total_transitions": 174817280, "num_steps_per_env": 1, "wm_loss": 0.4071383476257324, "actor_loss": -8.742505073547363, "critic_loss": 0.027441060170531273, "reward": 0.07138680666685104, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23948916792869568, 0.1545814424753189, 0.25131919980049133], "policy_updates": 42580, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8546.441263064, "contact_bce": 0.31041720509529114, "contact_force_loss": 0.03242836892604828, "terrain_level_mean": 3.2119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960598945617676]} {"step": 42690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42690, "total_transitions": 174858240, "num_steps_per_env": 1, "wm_loss": 0.384287565946579, "actor_loss": -8.684991836547852, "critic_loss": 0.024480370804667473, "reward": 0.07158327102661133, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24083571135997772, 0.1533702313899994, 0.24899990856647491], "policy_updates": 42590, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8549.958154263, "contact_bce": 0.3087966740131378, "contact_force_loss": 0.031433023512363434, "terrain_level_mean": 3.212890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960598945617676]} {"step": 42700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42700, "total_transitions": 174899200, "num_steps_per_env": 1, "wm_loss": 0.40005677938461304, "actor_loss": -8.776002883911133, "critic_loss": 0.029879247769713402, "reward": 0.07148116081953049, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24702203273773193, 0.15498127043247223, 0.2523616552352905], "policy_updates": 42600, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8553.477618066001, "contact_bce": 0.3092149496078491, "contact_force_loss": 0.03220691904425621, "terrain_level_mean": 3.213623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960598945617676]} {"step": 42710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42710, "total_transitions": 174940160, "num_steps_per_env": 1, "wm_loss": 0.41225048899650574, "actor_loss": -8.75631332397461, "critic_loss": 0.025552311912178993, "reward": 0.07129058986902237, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24854488670825958, 0.15870347619056702, 0.25131160020828247], "policy_updates": 42610, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8557.005634653, "contact_bce": 0.30712100863456726, "contact_force_loss": 0.03207463398575783, "terrain_level_mean": 3.21533203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960598945617676]} {"step": 42720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42720, "total_transitions": 174981120, "num_steps_per_env": 1, "wm_loss": 0.39834389090538025, "actor_loss": -8.78536319732666, "critic_loss": 0.036417268216609955, "reward": 0.07143580168485641, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24817192554473877, 0.1565275937318802, 0.2501365840435028], "policy_updates": 42620, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8560.523098384001, "contact_bce": 0.3094947040081024, "contact_force_loss": 0.03244670107960701, "terrain_level_mean": 3.21533203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960598945617676]} {"step": 42730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42730, "total_transitions": 175022080, "num_steps_per_env": 1, "wm_loss": 0.44825804233551025, "actor_loss": -8.71072769165039, "critic_loss": 0.025287112221121788, "reward": 0.07100404053926468, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2494651973247528, 0.15485058724880219, 0.25219857692718506], "policy_updates": 42630, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8564.038202639, "contact_bce": 0.31276261806488037, "contact_force_loss": 0.03247324377298355, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960741996765137]} {"step": 42740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42740, "total_transitions": 175063040, "num_steps_per_env": 1, "wm_loss": 0.44464266300201416, "actor_loss": -8.730772018432617, "critic_loss": 0.024309102445840836, "reward": 0.07072167098522186, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2500099241733551, 0.15558837354183197, 0.25432851910591125], "policy_updates": 42640, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8567.555116056, "contact_bce": 0.31576594710350037, "contact_force_loss": 0.03229092061519623, "terrain_level_mean": 3.21533203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960741996765137]} {"step": 42750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42750, "total_transitions": 175104000, "num_steps_per_env": 1, "wm_loss": 0.43540701270103455, "actor_loss": -8.752706527709961, "critic_loss": 0.0304498802870512, "reward": 0.07123406231403351, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25138401985168457, 0.1560559868812561, 0.24999624490737915], "policy_updates": 42650, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8571.075676935001, "contact_bce": 0.3126012980937958, "contact_force_loss": 0.03214573860168457, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960741996765137]} {"step": 42760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42760, "total_transitions": 175144960, "num_steps_per_env": 1, "wm_loss": 0.42837968468666077, "actor_loss": -8.730948448181152, "critic_loss": 0.023798508569598198, "reward": 0.07141990959644318, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24751542508602142, 0.15460820496082306, 0.2503356635570526], "policy_updates": 42660, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8574.589630389, "contact_bce": 0.3109094202518463, "contact_force_loss": 0.03269946947693825, "terrain_level_mean": 3.215087890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960741996765137]} {"step": 42770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42770, "total_transitions": 175185920, "num_steps_per_env": 1, "wm_loss": 0.41441553831100464, "actor_loss": -8.754834175109863, "critic_loss": 0.03445642068982124, "reward": 0.07107234746217728, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24297276139259338, 0.1548413336277008, 0.2520774304866791], "policy_updates": 42670, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8578.104185045, "contact_bce": 0.31590452790260315, "contact_force_loss": 0.032135121524333954, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960741996765137]} {"step": 42780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42780, "total_transitions": 175226880, "num_steps_per_env": 1, "wm_loss": 0.4009527862071991, "actor_loss": -8.775012969970703, "critic_loss": 0.02829854004085064, "reward": 0.07133246213197708, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24361078441143036, 0.15611617267131805, 0.24665293097496033], "policy_updates": 42680, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8581.628165151, "contact_bce": 0.3128868043422699, "contact_force_loss": 0.03178659826517105, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960741996765137]} {"step": 42790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42790, "total_transitions": 175267840, "num_steps_per_env": 1, "wm_loss": 0.41992661356925964, "actor_loss": -8.700576782226562, "critic_loss": 0.0242014117538929, "reward": 0.07148408144712448, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2480759620666504, 0.15615221858024597, 0.2470412254333496], "policy_updates": 42690, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8585.154429229, "contact_bce": 0.3149127662181854, "contact_force_loss": 0.031989701092243195, "terrain_level_mean": 3.2158203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960741996765137]} {"step": 42800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42800, "total_transitions": 175308800, "num_steps_per_env": 1, "wm_loss": 0.41331371665000916, "actor_loss": -8.695241928100586, "critic_loss": 0.023681102320551872, "reward": 0.07031222432851791, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24815064668655396, 0.15884912014007568, 0.25584861636161804], "policy_updates": 42700, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8588.676052517001, "contact_bce": 0.3103732466697693, "contact_force_loss": 0.032412782311439514, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960598945617676]} {"step": 42810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42810, "total_transitions": 175349760, "num_steps_per_env": 1, "wm_loss": 0.4300660192966461, "actor_loss": -8.721684455871582, "critic_loss": 0.02014971151947975, "reward": 0.07009842246770859, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25122228264808655, 0.16037222743034363, 0.2565685212612152], "policy_updates": 42710, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8592.190463166, "contact_bce": 0.31674084067344666, "contact_force_loss": 0.032645054161548615, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9993155002593994, 0.9976108074188232, 2.9960598945617676]} {"step": 42820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42820, "total_transitions": 175390720, "num_steps_per_env": 1, "wm_loss": 0.4144534170627594, "actor_loss": -8.75930404663086, "critic_loss": 0.02148579992353916, "reward": 0.07007399946451187, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24778269231319427, 0.1580614149570465, 0.2584078907966614], "policy_updates": 42720, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8595.697873125, "contact_bce": 0.3136962950229645, "contact_force_loss": 0.03291245549917221, "terrain_level_mean": 3.213134765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9993155002593994, 0.9950138330459595, 2.9960598945617676]} {"step": 42830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42830, "total_transitions": 175431680, "num_steps_per_env": 1, "wm_loss": 0.4182000458240509, "actor_loss": -8.720569610595703, "critic_loss": 0.0242506992071867, "reward": 0.07005427032709122, "falls": 6, "interval_steps": 10, "velocity_mae": [0.247902050614357, 0.15793566405773163, 0.25524285435676575], "policy_updates": 42730, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8599.217101271, "contact_bce": 0.31307461857795715, "contact_force_loss": 0.0324128232896328, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9993155002593994, 0.9950138330459595, 2.9960598945617676]} {"step": 42840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42840, "total_transitions": 175472640, "num_steps_per_env": 1, "wm_loss": 0.4048576354980469, "actor_loss": -8.724456787109375, "critic_loss": 0.03479989245533943, "reward": 0.07026704400777817, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25054073333740234, 0.15880322456359863, 0.2568117082118988], "policy_updates": 42740, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8602.731806688, "contact_bce": 0.31548359990119934, "contact_force_loss": 0.0325775183737278, "terrain_level_mean": 3.213623046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9993155002593994, 0.9995535612106323, 2.9960598945617676]} {"step": 42850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42850, "total_transitions": 175513600, "num_steps_per_env": 1, "wm_loss": 0.40456056594848633, "actor_loss": -8.733749389648438, "critic_loss": 0.0258534736931324, "reward": 0.0702660083770752, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24966585636138916, 0.16074207425117493, 0.256896048784256], "policy_updates": 42750, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8606.255791213001, "contact_bce": 0.3105384409427643, "contact_force_loss": 0.031824301928281784, "terrain_level_mean": 3.21337890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9993155002593994, 0.9995535612106323, 2.9960598945617676]} {"step": 42860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42860, "total_transitions": 175554560, "num_steps_per_env": 1, "wm_loss": 0.40599292516708374, "actor_loss": -8.725424766540527, "critic_loss": 0.030880583450198174, "reward": 0.06976281106472015, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25490960478782654, 0.16081763803958893, 0.2539210319519043], "policy_updates": 42760, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8609.775225787, "contact_bce": 0.3125227391719818, "contact_force_loss": 0.032362200319767, "terrain_level_mean": 3.2138671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9993155002593994, 0.9995535612106323, 2.9960598945617676]} {"step": 42870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42870, "total_transitions": 175595520, "num_steps_per_env": 1, "wm_loss": 0.40386348962783813, "actor_loss": -8.734796524047852, "critic_loss": 0.02460356615483761, "reward": 0.07034461945295334, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2525169253349304, 0.15695038437843323, 0.25503358244895935], "policy_updates": 42770, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8613.278478652, "contact_bce": 0.3095533549785614, "contact_force_loss": 0.0314110703766346, "terrain_level_mean": 3.21435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9993155002593994, 0.9995535612106323, 2.9960598945617676]} {"step": 42880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42880, "total_transitions": 175636480, "num_steps_per_env": 1, "wm_loss": 0.4214513599872589, "actor_loss": -8.7234468460083, "critic_loss": 0.03120466135442257, "reward": 0.07080408185720444, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24620039761066437, 0.15456673502922058, 0.2500268816947937], "policy_updates": 42780, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8616.785067931001, "contact_bce": 0.3121027648448944, "contact_force_loss": 0.03155459463596344, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42890, "total_transitions": 175677440, "num_steps_per_env": 1, "wm_loss": 0.3947145342826843, "actor_loss": -8.760623931884766, "critic_loss": 0.02799983136355877, "reward": 0.07097315043210983, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24595777690410614, 0.15163418650627136, 0.25019434094429016], "policy_updates": 42790, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8620.293043601001, "contact_bce": 0.31274789571762085, "contact_force_loss": 0.032591380178928375, "terrain_level_mean": 3.214111328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42900, "total_transitions": 175718400, "num_steps_per_env": 1, "wm_loss": 0.4134826958179474, "actor_loss": -8.739450454711914, "critic_loss": 0.025514263659715652, "reward": 0.07088153809309006, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24677208065986633, 0.15119591355323792, 0.25168663263320923], "policy_updates": 42800, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8623.813683133001, "contact_bce": 0.3119528591632843, "contact_force_loss": 0.03247317671775818, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42910, "total_transitions": 175759360, "num_steps_per_env": 1, "wm_loss": 0.43733322620391846, "actor_loss": -8.697949409484863, "critic_loss": 0.02871301770210266, "reward": 0.07096462696790695, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24513736367225647, 0.15550577640533447, 0.2519757151603699], "policy_updates": 42810, "skipped_updates": 0, "invalid_env_resets": 82, "elapsed_s": 8627.321203174, "contact_bce": 0.3167893588542938, "contact_force_loss": 0.03269481658935547, "terrain_level_mean": 3.21533203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} RECOVERY reset 1 invalid environments; first IDs=[1323] {"step": 42920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42920, "total_transitions": 175800320, "num_steps_per_env": 1, "wm_loss": 0.4495968520641327, "actor_loss": -8.739799499511719, "critic_loss": 0.028375452384352684, "reward": 0.0705745741724968, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24850139021873474, 0.15974029898643494, 0.257686972618103], "policy_updates": 42820, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8630.844954811, "contact_bce": 0.3118801414966583, "contact_force_loss": 0.032731793820858, "terrain_level_mean": 3.21484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42930, "total_transitions": 175841280, "num_steps_per_env": 1, "wm_loss": 0.4430776834487915, "actor_loss": -8.712786674499512, "critic_loss": 0.023949025198817253, "reward": 0.07075632363557816, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25190258026123047, 0.1599140167236328, 0.2550487816333771], "policy_updates": 42830, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8634.364236177, "contact_bce": 0.3122153878211975, "contact_force_loss": 0.03239273279905319, "terrain_level_mean": 3.216064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42940, "total_transitions": 175882240, "num_steps_per_env": 1, "wm_loss": 0.40575361251831055, "actor_loss": -8.720203399658203, "critic_loss": 0.029510999098420143, "reward": 0.0704483687877655, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2509656250476837, 0.16107337176799774, 0.2534864544868469], "policy_updates": 42840, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8637.868709923001, "contact_bce": 0.3110675811767578, "contact_force_loss": 0.03215735778212547, "terrain_level_mean": 3.216552734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42950, "total_transitions": 175923200, "num_steps_per_env": 1, "wm_loss": 0.3949001431465149, "actor_loss": -8.725215911865234, "critic_loss": 0.02458006702363491, "reward": 0.07039214670658112, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24792709946632385, 0.15866388380527496, 0.24966253340244293], "policy_updates": 42850, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8641.379330848, "contact_bce": 0.30873796343803406, "contact_force_loss": 0.03191455826163292, "terrain_level_mean": 3.218017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42960, "total_transitions": 175964160, "num_steps_per_env": 1, "wm_loss": 0.41464462876319885, "actor_loss": -8.692901611328125, "critic_loss": 0.025752639397978783, "reward": 0.06997528672218323, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24916236102581024, 0.1608297973871231, 0.2548532783985138], "policy_updates": 42860, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8644.893530839001, "contact_bce": 0.30987003445625305, "contact_force_loss": 0.0321764200925827, "terrain_level_mean": 3.218505859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.998136043548584, 0.9995535612106323, 2.9960598945617676]} {"step": 42970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42970, "total_transitions": 176005120, "num_steps_per_env": 1, "wm_loss": 0.3972451686859131, "actor_loss": -8.719219207763672, "critic_loss": 0.02827092446386814, "reward": 0.07000222057104111, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24908079206943512, 0.15926943719387054, 0.255366712808609], "policy_updates": 42870, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8648.409247361, "contact_bce": 0.3130998909473419, "contact_force_loss": 0.03153500705957413, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.998671531677246, 0.9995535612106323, 2.9960598945617676]} {"step": 42980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42980, "total_transitions": 176046080, "num_steps_per_env": 1, "wm_loss": 0.39782190322875977, "actor_loss": -8.719684600830078, "critic_loss": 0.02237619087100029, "reward": 0.07073405385017395, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24509786069393158, 0.15832355618476868, 0.25225549936294556], "policy_updates": 42880, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8651.929122834, "contact_bce": 0.313610702753067, "contact_force_loss": 0.03124784119427204, "terrain_level_mean": 3.218017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.998671531677246, 0.9995535612106323, 2.9960598945617676]} {"step": 42990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 42990, "total_transitions": 176087040, "num_steps_per_env": 1, "wm_loss": 0.42895859479904175, "actor_loss": -8.697779655456543, "critic_loss": 0.038450270891189575, "reward": 0.07105061411857605, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24189263582229614, 0.1558978259563446, 0.25173670053482056], "policy_updates": 42890, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8655.445202706, "contact_bce": 0.31340107321739197, "contact_force_loss": 0.03206104412674904, "terrain_level_mean": 3.21826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.998671531677246, 0.9995535612106323, 2.9960598945617676]} {"step": 43000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43000, "total_transitions": 176128000, "num_steps_per_env": 1, "wm_loss": 0.4286274015903473, "actor_loss": -8.707052230834961, "critic_loss": 0.025918930768966675, "reward": 0.0708705261349678, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2484075129032135, 0.1538899838924408, 0.25541990995407104], "policy_updates": 42900, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8658.975080611, "contact_bce": 0.3145711421966553, "contact_force_loss": 0.032865386456251144, "terrain_level_mean": 3.2197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.9960598945617676]} {"step": 43010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43010, "total_transitions": 176168960, "num_steps_per_env": 1, "wm_loss": 0.428137868642807, "actor_loss": -8.701150894165039, "critic_loss": 0.02197985351085663, "reward": 0.07071929425001144, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25171586871147156, 0.15425439178943634, 0.2519696056842804], "policy_updates": 42910, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8662.525123213001, "contact_bce": 0.31338223814964294, "contact_force_loss": 0.03211505711078644, "terrain_level_mean": 3.220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.9960598945617676]} {"step": 43020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43020, "total_transitions": 176209920, "num_steps_per_env": 1, "wm_loss": 0.4119202792644501, "actor_loss": -8.710884094238281, "critic_loss": 0.028580958023667336, "reward": 0.07084779441356659, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25235673785209656, 0.15509827435016632, 0.2495182454586029], "policy_updates": 42920, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8666.03465494, "contact_bce": 0.3110012114048004, "contact_force_loss": 0.03218457102775574, "terrain_level_mean": 3.219482421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.9960598945617676]} {"step": 43030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43030, "total_transitions": 176250880, "num_steps_per_env": 1, "wm_loss": 0.424495667219162, "actor_loss": -8.734565734863281, "critic_loss": 0.02623807266354561, "reward": 0.07116269320249557, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24750079214572906, 0.15608906745910645, 0.25196003913879395], "policy_updates": 42930, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8669.783339581001, "contact_bce": 0.31151100993156433, "contact_force_loss": 0.03137851879000664, "terrain_level_mean": 3.220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} {"step": 43040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43040, "total_transitions": 176291840, "num_steps_per_env": 1, "wm_loss": 0.42118021845817566, "actor_loss": -8.719032287597656, "critic_loss": 0.028500396758317947, "reward": 0.07076989114284515, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2504761517047882, 0.15406915545463562, 0.25508835911750793], "policy_updates": 42940, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8673.282393039, "contact_bce": 0.3131002187728882, "contact_force_loss": 0.03189298138022423, "terrain_level_mean": 3.219970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} {"step": 43050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43050, "total_transitions": 176332800, "num_steps_per_env": 1, "wm_loss": 0.4056920111179352, "actor_loss": -8.753228187561035, "critic_loss": 0.022564446553587914, "reward": 0.07077551633119583, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25278109312057495, 0.15284138917922974, 0.2514636516571045], "policy_updates": 42950, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8676.778222394001, "contact_bce": 0.3131645619869232, "contact_force_loss": 0.03350229188799858, "terrain_level_mean": 3.22021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} {"step": 43060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43060, "total_transitions": 176373760, "num_steps_per_env": 1, "wm_loss": 0.4310479462146759, "actor_loss": -8.73294448852539, "critic_loss": 0.025314508005976677, "reward": 0.07071968913078308, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2506971061229706, 0.15122562646865845, 0.2511298954486847], "policy_updates": 42960, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8680.275996864, "contact_bce": 0.31055885553359985, "contact_force_loss": 0.03317190706729889, "terrain_level_mean": 3.22021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} {"step": 43070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43070, "total_transitions": 176414720, "num_steps_per_env": 1, "wm_loss": 0.4058241844177246, "actor_loss": -8.680535316467285, "critic_loss": 0.02902657352387905, "reward": 0.07115182280540466, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24700233340263367, 0.14863084256649017, 0.2494106888771057], "policy_updates": 42970, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8683.776875014, "contact_bce": 0.31070104241371155, "contact_force_loss": 0.0322016105055809, "terrain_level_mean": 3.22119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} {"step": 43080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43080, "total_transitions": 176455680, "num_steps_per_env": 1, "wm_loss": 0.3959822654724121, "actor_loss": -8.724649429321289, "critic_loss": 0.02784162200987339, "reward": 0.07086871564388275, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2511269152164459, 0.1507047414779663, 0.2517496943473816], "policy_updates": 42980, "skipped_updates": 0, "invalid_env_resets": 83, "elapsed_s": 8687.273840313, "contact_bce": 0.311799019575119, "contact_force_loss": 0.031398434191942215, "terrain_level_mean": 3.22265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} RECOVERY reset 1 invalid environments; first IDs=[1181] {"step": 43090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43090, "total_transitions": 176496640, "num_steps_per_env": 1, "wm_loss": 0.39046168327331543, "actor_loss": -8.773472785949707, "critic_loss": 0.01913035847246647, "reward": 0.07094510644674301, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2504626214504242, 0.1514941155910492, 0.25101742148399353], "policy_updates": 42990, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8690.793062264, "contact_bce": 0.30506381392478943, "contact_force_loss": 0.03094864822924137, "terrain_level_mean": 3.222900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} {"step": 43100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43100, "total_transitions": 176537600, "num_steps_per_env": 1, "wm_loss": 0.40702128410339355, "actor_loss": -8.726741790771484, "critic_loss": 0.02985435724258423, "reward": 0.07103268057107925, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24877700209617615, 0.15256331861019135, 0.2509814202785492], "policy_updates": 43000, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8694.300982958, "contact_bce": 0.31037479639053345, "contact_force_loss": 0.03186047822237015, "terrain_level_mean": 3.2216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3583984375, "command_abs_max": [1.9991984367370605, 0.9995535612106323, 2.998591423034668]} {"step": 43110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43110, "total_transitions": 176578560, "num_steps_per_env": 1, "wm_loss": 0.4095899760723114, "actor_loss": -8.688666343688965, "critic_loss": 0.03212772309780121, "reward": 0.07122509926557541, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25085508823394775, 0.15369874238967896, 0.2534506320953369], "policy_updates": 43010, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8697.802780415, "contact_bce": 0.30764368176460266, "contact_force_loss": 0.0322277769446373, "terrain_level_mean": 3.221923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9991984367370605, 0.9991111159324646, 2.9997706413269043]} {"step": 43120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43120, "total_transitions": 176619520, "num_steps_per_env": 1, "wm_loss": 0.39545533061027527, "actor_loss": -8.72137451171875, "critic_loss": 0.03498021885752678, "reward": 0.07047093659639359, "falls": 1, "interval_steps": 10, "velocity_mae": [0.254968523979187, 0.15523914992809296, 0.2564918100833893], "policy_updates": 43020, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8701.304020219, "contact_bce": 0.3050864338874817, "contact_force_loss": 0.03079153224825859, "terrain_level_mean": 3.222900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43130, "total_transitions": 176660480, "num_steps_per_env": 1, "wm_loss": 0.39706113934516907, "actor_loss": -8.73185920715332, "critic_loss": 0.025476723909378052, "reward": 0.07024644315242767, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2551542818546295, 0.15417692065238953, 0.2533766031265259], "policy_updates": 43030, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8704.801452166, "contact_bce": 0.3068268299102783, "contact_force_loss": 0.031892552971839905, "terrain_level_mean": 3.223876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43140, "total_transitions": 176701440, "num_steps_per_env": 1, "wm_loss": 0.39680972695350647, "actor_loss": -8.702250480651855, "critic_loss": 0.030933335423469543, "reward": 0.07021176069974899, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2576201856136322, 0.15484420955181122, 0.25453993678092957], "policy_updates": 43040, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8708.301469608, "contact_bce": 0.3109114468097687, "contact_force_loss": 0.03217587247490883, "terrain_level_mean": 3.223876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43150, "total_transitions": 176742400, "num_steps_per_env": 1, "wm_loss": 0.3938905596733093, "actor_loss": -8.762343406677246, "critic_loss": 0.02174392156302929, "reward": 0.07085198909044266, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25687140226364136, 0.15478478372097015, 0.24866245687007904], "policy_updates": 43050, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8711.818717899001, "contact_bce": 0.31047844886779785, "contact_force_loss": 0.03132310137152672, "terrain_level_mean": 3.224365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355712890625, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43160, "total_transitions": 176783360, "num_steps_per_env": 1, "wm_loss": 0.43137916922569275, "actor_loss": -8.705787658691406, "critic_loss": 0.029417533427476883, "reward": 0.07114458829164505, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25915995240211487, 0.15685778856277466, 0.2545987367630005], "policy_updates": 43060, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8715.338194162001, "contact_bce": 0.3087979257106781, "contact_force_loss": 0.03276059404015541, "terrain_level_mean": 3.224853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43170, "total_transitions": 176824320, "num_steps_per_env": 1, "wm_loss": 0.40781036019325256, "actor_loss": -8.721351623535156, "critic_loss": 0.033905014395713806, "reward": 0.07092837244272232, "falls": 10, "interval_steps": 10, "velocity_mae": [0.25887924432754517, 0.1573798656463623, 0.2512616515159607], "policy_updates": 43070, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8718.861867414, "contact_bce": 0.3114442229270935, "contact_force_loss": 0.03170973062515259, "terrain_level_mean": 3.22412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357421875, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43180, "total_transitions": 176865280, "num_steps_per_env": 1, "wm_loss": 0.40073007345199585, "actor_loss": -8.674993515014648, "critic_loss": 0.033297665417194366, "reward": 0.07097673416137695, "falls": 5, "interval_steps": 10, "velocity_mae": [0.256389319896698, 0.1575261354446411, 0.2484705150127411], "policy_updates": 43080, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8722.385415652001, "contact_bce": 0.3135194182395935, "contact_force_loss": 0.032499026507139206, "terrain_level_mean": 3.22412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43190, "total_transitions": 176906240, "num_steps_per_env": 1, "wm_loss": 0.39870136976242065, "actor_loss": -8.692139625549316, "critic_loss": 0.02352060005068779, "reward": 0.07116913050413132, "falls": 1, "interval_steps": 10, "velocity_mae": [0.25752514600753784, 0.1576976329088211, 0.24950215220451355], "policy_updates": 43090, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8725.911797479, "contact_bce": 0.3141220808029175, "contact_force_loss": 0.03164678066968918, "terrain_level_mean": 3.225341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43200, "total_transitions": 176947200, "num_steps_per_env": 1, "wm_loss": 0.4011440575122833, "actor_loss": -8.730134963989258, "critic_loss": 0.028031086549162865, "reward": 0.07077287882566452, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25808703899383545, 0.1582174003124237, 0.253781795501709], "policy_updates": 43100, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8729.425798509, "contact_bce": 0.3132611811161041, "contact_force_loss": 0.032897450029850006, "terrain_level_mean": 3.224365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_043200.mp4 {"step": 43210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43210, "total_transitions": 176988160, "num_steps_per_env": 1, "wm_loss": 0.4132770001888275, "actor_loss": -8.666780471801758, "critic_loss": 0.03199424222111702, "reward": 0.0709516778588295, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2538517415523529, 0.155303955078125, 0.2530147135257721], "policy_updates": 43110, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8738.707954391, "contact_bce": 0.3148389160633087, "contact_force_loss": 0.03210320323705673, "terrain_level_mean": 3.22314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43220, "total_transitions": 177029120, "num_steps_per_env": 1, "wm_loss": 0.4399918019771576, "actor_loss": -8.680144309997559, "critic_loss": 0.029575306922197342, "reward": 0.07129932940006256, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2516559064388275, 0.155596062541008, 0.2491263896226883], "policy_updates": 43120, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8742.207380249001, "contact_bce": 0.31712058186531067, "contact_force_loss": 0.033115554600954056, "terrain_level_mean": 3.22412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43230, "total_transitions": 177070080, "num_steps_per_env": 1, "wm_loss": 0.40115484595298767, "actor_loss": -8.724984169006348, "critic_loss": 0.027233770117163658, "reward": 0.07105356454849243, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2478727400302887, 0.15760022401809692, 0.2552449703216553], "policy_updates": 43130, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8745.706631716, "contact_bce": 0.3132324814796448, "contact_force_loss": 0.0327371284365654, "terrain_level_mean": 3.224853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43240, "total_transitions": 177111040, "num_steps_per_env": 1, "wm_loss": 0.38496631383895874, "actor_loss": -8.687166213989258, "critic_loss": 0.019311055541038513, "reward": 0.07069694250822067, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25276675820350647, 0.15880420804023743, 0.25578227639198303], "policy_updates": 43140, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8749.211501955, "contact_bce": 0.3073646128177643, "contact_force_loss": 0.03234945237636566, "terrain_level_mean": 3.224853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43250, "total_transitions": 177152000, "num_steps_per_env": 1, "wm_loss": 0.39606767892837524, "actor_loss": -8.676258087158203, "critic_loss": 0.028276218101382256, "reward": 0.07041740417480469, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25657087564468384, 0.1601225733757019, 0.26111987233161926], "policy_updates": 43150, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8752.717075731001, "contact_bce": 0.30779120326042175, "contact_force_loss": 0.03230739012360573, "terrain_level_mean": 3.22412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43260, "total_transitions": 177192960, "num_steps_per_env": 1, "wm_loss": 0.42488494515419006, "actor_loss": -8.754165649414062, "critic_loss": 0.021045660600066185, "reward": 0.07029827684164047, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2593620717525482, 0.1599458009004593, 0.2552380859851837], "policy_updates": 43160, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8756.224949021, "contact_bce": 0.31942570209503174, "contact_force_loss": 0.03302298113703728, "terrain_level_mean": 3.22509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.999918818473816, 0.9991111159324646, 2.9997706413269043]} {"step": 43270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43270, "total_transitions": 177233920, "num_steps_per_env": 1, "wm_loss": 0.398372620344162, "actor_loss": -8.704360961914062, "critic_loss": 0.02882557548582554, "reward": 0.07034563273191452, "falls": 5, "interval_steps": 10, "velocity_mae": [0.26625770330429077, 0.16003641486167908, 0.25582027435302734], "policy_updates": 43170, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8759.727413582, "contact_bce": 0.3114527463912964, "contact_force_loss": 0.031917497515678406, "terrain_level_mean": 3.224853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43280, "total_transitions": 177274880, "num_steps_per_env": 1, "wm_loss": 0.41665002703666687, "actor_loss": -8.694979667663574, "critic_loss": 0.026017939671874046, "reward": 0.07059141248464584, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2648676037788391, 0.1619611233472824, 0.2591586410999298], "policy_updates": 43180, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8763.22671716, "contact_bce": 0.31499725580215454, "contact_force_loss": 0.03211415931582451, "terrain_level_mean": 3.2255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43290, "total_transitions": 177315840, "num_steps_per_env": 1, "wm_loss": 0.44284167885780334, "actor_loss": -8.662019729614258, "critic_loss": 0.03434879705309868, "reward": 0.07082685083150864, "falls": 9, "interval_steps": 10, "velocity_mae": [0.26062625646591187, 0.16110192239284515, 0.2537961006164551], "policy_updates": 43190, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8766.724458055001, "contact_bce": 0.3137260675430298, "contact_force_loss": 0.03242575004696846, "terrain_level_mean": 3.225341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43300, "total_transitions": 177356800, "num_steps_per_env": 1, "wm_loss": 0.4255412220954895, "actor_loss": -8.684041976928711, "critic_loss": 0.029038483276963234, "reward": 0.07084252685308456, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25681042671203613, 0.15878231823444366, 0.2554619610309601], "policy_updates": 43200, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8770.219786965, "contact_bce": 0.31819212436676025, "contact_force_loss": 0.03258642926812172, "terrain_level_mean": 3.224365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43310, "total_transitions": 177397760, "num_steps_per_env": 1, "wm_loss": 0.39421728253364563, "actor_loss": -8.6378755569458, "critic_loss": 0.028513675555586815, "reward": 0.07104766368865967, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2507432699203491, 0.1592034101486206, 0.25457999110221863], "policy_updates": 43210, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8773.715508057001, "contact_bce": 0.3051990866661072, "contact_force_loss": 0.030810974538326263, "terrain_level_mean": 3.223876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43320, "total_transitions": 177438720, "num_steps_per_env": 1, "wm_loss": 0.4208069145679474, "actor_loss": -8.705039024353027, "critic_loss": 0.030426055192947388, "reward": 0.07119915634393692, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25136515498161316, 0.1578165590763092, 0.2527344822883606], "policy_updates": 43220, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8777.213169237, "contact_bce": 0.3181685507297516, "contact_force_loss": 0.033931758254766464, "terrain_level_mean": 3.22314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43330, "total_transitions": 177479680, "num_steps_per_env": 1, "wm_loss": 0.41385164856910706, "actor_loss": -8.700614929199219, "critic_loss": 0.02867664210498333, "reward": 0.07133033871650696, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2524186670780182, 0.1555079072713852, 0.24871490895748138], "policy_updates": 43230, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8780.707981803, "contact_bce": 0.31050097942352295, "contact_force_loss": 0.03247956931591034, "terrain_level_mean": 3.22216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43340, "total_transitions": 177520640, "num_steps_per_env": 1, "wm_loss": 0.4292767345905304, "actor_loss": -8.723411560058594, "critic_loss": 0.03648291900753975, "reward": 0.07118245214223862, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25370895862579346, 0.15681301057338715, 0.2478107064962387], "policy_updates": 43240, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8784.209054094, "contact_bce": 0.31465643644332886, "contact_force_loss": 0.032799918204545975, "terrain_level_mean": 3.222412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43350, "total_transitions": 177561600, "num_steps_per_env": 1, "wm_loss": 0.43574225902557373, "actor_loss": -8.750242233276367, "critic_loss": 0.02502943016588688, "reward": 0.07101486623287201, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24930092692375183, 0.16116979718208313, 0.2515791952610016], "policy_updates": 43250, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8787.714171032001, "contact_bce": 0.3159807324409485, "contact_force_loss": 0.03359588608145714, "terrain_level_mean": 3.222412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43360, "total_transitions": 177602560, "num_steps_per_env": 1, "wm_loss": 0.3952910006046295, "actor_loss": -8.706581115722656, "critic_loss": 0.03424838185310364, "reward": 0.07064523547887802, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2493833601474762, 0.16168460249900818, 0.2516656219959259], "policy_updates": 43260, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8791.221673452, "contact_bce": 0.3110884428024292, "contact_force_loss": 0.03243006393313408, "terrain_level_mean": 3.221923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43370, "total_transitions": 177643520, "num_steps_per_env": 1, "wm_loss": 0.4240153729915619, "actor_loss": -8.701950073242188, "critic_loss": 0.02939453162252903, "reward": 0.07065830379724503, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25341126322746277, 0.16195504367351532, 0.25623372197151184], "policy_updates": 43270, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8794.726734822001, "contact_bce": 0.3150334656238556, "contact_force_loss": 0.032301388680934906, "terrain_level_mean": 3.22216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.999918818473816, 0.9984347820281982, 2.9997706413269043]} {"step": 43380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43380, "total_transitions": 177684480, "num_steps_per_env": 1, "wm_loss": 0.4262126088142395, "actor_loss": -8.64332389831543, "critic_loss": 0.03932220861315727, "reward": 0.07073714584112167, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2548193335533142, 0.16343863308429718, 0.2579203248023987], "policy_updates": 43280, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8798.239326462, "contact_bce": 0.31169041991233826, "contact_force_loss": 0.03311244398355484, "terrain_level_mean": 3.222900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9976407289505005, 0.9984347820281982, 2.9997706413269043]} {"step": 43390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43390, "total_transitions": 177725440, "num_steps_per_env": 1, "wm_loss": 0.4152378737926483, "actor_loss": -8.691764831542969, "critic_loss": 0.03638751432299614, "reward": 0.07088441401720047, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2517901062965393, 0.1600528508424759, 0.25718215107917786], "policy_updates": 43290, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8801.75191285, "contact_bce": 0.31105837225914, "contact_force_loss": 0.0324416421353817, "terrain_level_mean": 3.223388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9976407289505005, 0.9984347820281982, 2.9997706413269043]} {"step": 43400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43400, "total_transitions": 177766400, "num_steps_per_env": 1, "wm_loss": 0.43736663460731506, "actor_loss": -8.696504592895508, "critic_loss": 0.02646510675549507, "reward": 0.0711820051074028, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2493506222963333, 0.15825779736042023, 0.25562793016433716], "policy_updates": 43300, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8805.257405021, "contact_bce": 0.31948360800743103, "contact_force_loss": 0.032736849039793015, "terrain_level_mean": 3.22216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9976407289505005, 0.9984347820281982, 2.9997706413269043]} {"step": 43410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43410, "total_transitions": 177807360, "num_steps_per_env": 1, "wm_loss": 0.4026525020599365, "actor_loss": -8.726861000061035, "critic_loss": 0.021787026897072792, "reward": 0.07173290103673935, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24502111971378326, 0.154378741979599, 0.25047990679740906], "policy_updates": 43310, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8808.755236047, "contact_bce": 0.3114679157733917, "contact_force_loss": 0.0320260152220726, "terrain_level_mean": 3.220458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9976407289505005, 0.9984347820281982, 2.9997706413269043]} {"step": 43420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43420, "total_transitions": 177848320, "num_steps_per_env": 1, "wm_loss": 0.40754732489585876, "actor_loss": -8.703932762145996, "critic_loss": 0.024726107716560364, "reward": 0.07168491184711456, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24656721949577332, 0.15535172820091248, 0.251706600189209], "policy_updates": 43320, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8812.265889834001, "contact_bce": 0.3131139576435089, "contact_force_loss": 0.03279867395758629, "terrain_level_mean": 3.220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9976407289505005, 0.9940043091773987, 2.9997706413269043]} {"step": 43430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43430, "total_transitions": 177889280, "num_steps_per_env": 1, "wm_loss": 0.4498306214809418, "actor_loss": -8.713594436645508, "critic_loss": 0.028283655643463135, "reward": 0.07136788219213486, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2515382766723633, 0.15761932730674744, 0.25400325655937195], "policy_updates": 43330, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8815.755687802, "contact_bce": 0.31626927852630615, "contact_force_loss": 0.03265812620520592, "terrain_level_mean": 3.22119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9976407289505005, 0.9940043091773987, 2.9997706413269043]} {"step": 43440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43440, "total_transitions": 177930240, "num_steps_per_env": 1, "wm_loss": 0.41021889448165894, "actor_loss": -8.676586151123047, "critic_loss": 0.07402845472097397, "reward": 0.07145211845636368, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24945957958698273, 0.15727730095386505, 0.2531988322734833], "policy_updates": 43340, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8819.247990073001, "contact_bce": 0.3157303035259247, "contact_force_loss": 0.03343639895319939, "terrain_level_mean": 3.2216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9986841678619385, 0.9940043091773987, 2.9997706413269043]} {"step": 43450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43450, "total_transitions": 177971200, "num_steps_per_env": 1, "wm_loss": 0.4274871349334717, "actor_loss": -8.689801216125488, "critic_loss": 0.02584998868405819, "reward": 0.07103720307350159, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25126540660858154, 0.15800054371356964, 0.2546049654483795], "policy_updates": 43350, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8822.733423153, "contact_bce": 0.30913621187210083, "contact_force_loss": 0.03261673077940941, "terrain_level_mean": 3.222412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9986841678619385, 0.9999210834503174, 2.994699001312256]} {"step": 43460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43460, "total_transitions": 178012160, "num_steps_per_env": 1, "wm_loss": 0.4164445400238037, "actor_loss": -8.713415145874023, "critic_loss": 0.02867601253092289, "reward": 0.07068478316068649, "falls": 5, "interval_steps": 10, "velocity_mae": [0.251289427280426, 0.15533052384853363, 0.25449374318122864], "policy_updates": 43360, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8826.222518686001, "contact_bce": 0.3145870566368103, "contact_force_loss": 0.033072393387556076, "terrain_level_mean": 3.2236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9986841678619385, 0.9999210834503174, 2.993551015853882]} {"step": 43470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43470, "total_transitions": 178053120, "num_steps_per_env": 1, "wm_loss": 0.4223588705062866, "actor_loss": -8.664916038513184, "critic_loss": 0.02870124951004982, "reward": 0.07081299275159836, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24880336225032806, 0.15630000829696655, 0.2556937038898468], "policy_updates": 43370, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8829.715522894001, "contact_bce": 0.3159691095352173, "contact_force_loss": 0.03227725625038147, "terrain_level_mean": 3.22314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9986841678619385, 0.9999210834503174, 2.993551015853882]} {"step": 43480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43480, "total_transitions": 178094080, "num_steps_per_env": 1, "wm_loss": 0.39921024441719055, "actor_loss": -8.706154823303223, "critic_loss": 0.02885640226304531, "reward": 0.07080341130495071, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24842193722724915, 0.15768836438655853, 0.25603070855140686], "policy_updates": 43380, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8833.212682039, "contact_bce": 0.3126857876777649, "contact_force_loss": 0.03165748342871666, "terrain_level_mean": 3.22314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9986841678619385, 0.9999210834503174, 2.993551015853882]} {"step": 43490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43490, "total_transitions": 178135040, "num_steps_per_env": 1, "wm_loss": 0.42383092641830444, "actor_loss": -8.695308685302734, "critic_loss": 0.02537834458053112, "reward": 0.07059033215045929, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24601860344409943, 0.15984533727169037, 0.2571337819099426], "policy_updates": 43390, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8836.708553811, "contact_bce": 0.3173060119152069, "contact_force_loss": 0.032626472413539886, "terrain_level_mean": 3.2236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.998660087585449]} {"step": 43500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43500, "total_transitions": 178176000, "num_steps_per_env": 1, "wm_loss": 0.4229763448238373, "actor_loss": -8.70189380645752, "critic_loss": 0.023198377341032028, "reward": 0.06975799798965454, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2508075535297394, 0.16033516824245453, 0.25641554594039917], "policy_updates": 43400, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8840.201722787, "contact_bce": 0.3179512321949005, "contact_force_loss": 0.03256447613239288, "terrain_level_mean": 3.22314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.998660087585449]} {"step": 43510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43510, "total_transitions": 178216960, "num_steps_per_env": 1, "wm_loss": 0.43991878628730774, "actor_loss": -8.766976356506348, "critic_loss": 0.025417853146791458, "reward": 0.07036429643630981, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2518952488899231, 0.16222532093524933, 0.2587207853794098], "policy_updates": 43410, "skipped_updates": 0, "invalid_env_resets": 84, "elapsed_s": 8843.741714661, "contact_bce": 0.316558837890625, "contact_force_loss": 0.03305275738239288, "terrain_level_mean": 3.2236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.998660087585449]} RECOVERY reset 1 invalid environments; first IDs=[1462] {"step": 43520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43520, "total_transitions": 178257920, "num_steps_per_env": 1, "wm_loss": 0.41203612089157104, "actor_loss": -8.682456970214844, "critic_loss": 0.03636600077152252, "reward": 0.06985845416784286, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2563445270061493, 0.16122695803642273, 0.2613377869129181], "policy_updates": 43420, "skipped_updates": 0, "invalid_env_resets": 85, "elapsed_s": 8847.528960009, "contact_bce": 0.3109132945537567, "contact_force_loss": 0.03237247094511986, "terrain_level_mean": 3.224365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.998660087585449]} {"step": 43530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43530, "total_transitions": 178298880, "num_steps_per_env": 1, "wm_loss": 0.4138011932373047, "actor_loss": -8.665243148803711, "critic_loss": 0.034613270312547684, "reward": 0.06978707760572433, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25645068287849426, 0.1618933379650116, 0.25909629464149475], "policy_updates": 43430, "skipped_updates": 0, "invalid_env_resets": 85, "elapsed_s": 8851.050190419, "contact_bce": 0.3114670217037201, "contact_force_loss": 0.03179985284805298, "terrain_level_mean": 3.22509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.998660087585449]} {"step": 43540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43540, "total_transitions": 178339840, "num_steps_per_env": 1, "wm_loss": 0.4292815029621124, "actor_loss": -8.666762351989746, "critic_loss": 0.02839619480073452, "reward": 0.0700840875506401, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25506630539894104, 0.1606714427471161, 0.2595002055168152], "policy_updates": 43440, "skipped_updates": 0, "invalid_env_resets": 85, "elapsed_s": 8854.569419610001, "contact_bce": 0.31174391508102417, "contact_force_loss": 0.03215821832418442, "terrain_level_mean": 3.225830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.998660087585449]} {"step": 43550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43550, "total_transitions": 178380800, "num_steps_per_env": 1, "wm_loss": 0.4038936495780945, "actor_loss": -8.726934432983398, "critic_loss": 0.028704410418868065, "reward": 0.06990260630846024, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2563747465610504, 0.1593269556760788, 0.2598363161087036], "policy_updates": 43450, "skipped_updates": 0, "invalid_env_resets": 85, "elapsed_s": 8858.074176157, "contact_bce": 0.3105173110961914, "contact_force_loss": 0.03240146487951279, "terrain_level_mean": 3.227783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43560, "total_transitions": 178421760, "num_steps_per_env": 1, "wm_loss": 0.4128919541835785, "actor_loss": -8.674538612365723, "critic_loss": 0.040402788668870926, "reward": 0.06969687342643738, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2531372606754303, 0.16115933656692505, 0.2517921030521393], "policy_updates": 43460, "skipped_updates": 0, "invalid_env_resets": 85, "elapsed_s": 8861.599657829001, "contact_bce": 0.3127174377441406, "contact_force_loss": 0.032166022807359695, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} RECOVERY reset 1 invalid environments; first IDs=[1314] {"step": 43570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43570, "total_transitions": 178462720, "num_steps_per_env": 1, "wm_loss": 0.423512727022171, "actor_loss": -8.703863143920898, "critic_loss": 0.02389548346400261, "reward": 0.06983204931020737, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24792976677417755, 0.1600310057401657, 0.25084835290908813], "policy_updates": 43470, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8865.122713802, "contact_bce": 0.3170105516910553, "contact_force_loss": 0.03264982998371124, "terrain_level_mean": 3.228759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43580, "total_transitions": 178503680, "num_steps_per_env": 1, "wm_loss": 0.4108228087425232, "actor_loss": -8.71786880493164, "critic_loss": 0.020292172208428383, "reward": 0.07022816687822342, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2452862709760666, 0.1597166508436203, 0.25442537665367126], "policy_updates": 43480, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8868.620053576, "contact_bce": 0.311908483505249, "contact_force_loss": 0.032147057354450226, "terrain_level_mean": 3.228271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43590, "total_transitions": 178544640, "num_steps_per_env": 1, "wm_loss": 0.4093983769416809, "actor_loss": -8.701698303222656, "critic_loss": 0.027488797903060913, "reward": 0.070330910384655, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2454897165298462, 0.15855717658996582, 0.2524436116218567], "policy_updates": 43490, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8872.147544781, "contact_bce": 0.31590962409973145, "contact_force_loss": 0.032543107867240906, "terrain_level_mean": 3.228271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43600, "total_transitions": 178585600, "num_steps_per_env": 1, "wm_loss": 0.4074201285839081, "actor_loss": -8.71633529663086, "critic_loss": 0.03065558709204197, "reward": 0.07051386684179306, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2440996766090393, 0.1598798930644989, 0.24951769411563873], "policy_updates": 43500, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8875.670708491001, "contact_bce": 0.31123727560043335, "contact_force_loss": 0.03215935453772545, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43610, "total_transitions": 178626560, "num_steps_per_env": 1, "wm_loss": 0.4243827760219574, "actor_loss": -8.7159423828125, "critic_loss": 0.0330062173306942, "reward": 0.07051918655633926, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24441103637218475, 0.15868856012821198, 0.2530200183391571], "policy_updates": 43510, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8879.19566797, "contact_bce": 0.3128884732723236, "contact_force_loss": 0.03289947286248207, "terrain_level_mean": 3.227783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43620, "total_transitions": 178667520, "num_steps_per_env": 1, "wm_loss": 0.43239960074424744, "actor_loss": -8.778501510620117, "critic_loss": 0.03533051535487175, "reward": 0.07049194723367691, "falls": 12, "interval_steps": 10, "velocity_mae": [0.2440403699874878, 0.15832766890525818, 0.25594815611839294], "policy_updates": 43520, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8882.714188059, "contact_bce": 0.3200069069862366, "contact_force_loss": 0.032822806388139725, "terrain_level_mean": 3.22705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43630, "total_transitions": 178708480, "num_steps_per_env": 1, "wm_loss": 0.4340061843395233, "actor_loss": -8.654403686523438, "critic_loss": 0.024322977289557457, "reward": 0.07085707038640976, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2458460032939911, 0.1562352478504181, 0.25286170840263367], "policy_updates": 43530, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8886.233486104, "contact_bce": 0.31060633063316345, "contact_force_loss": 0.03234928473830223, "terrain_level_mean": 3.225830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43640, "total_transitions": 178749440, "num_steps_per_env": 1, "wm_loss": 0.43261322379112244, "actor_loss": -8.730125427246094, "critic_loss": 0.030655687674880028, "reward": 0.0712137445807457, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24623657763004303, 0.15422114729881287, 0.2532539963722229], "policy_updates": 43540, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8889.743942776, "contact_bce": 0.30823397636413574, "contact_force_loss": 0.03320501372218132, "terrain_level_mean": 3.22607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43650, "total_transitions": 178790400, "num_steps_per_env": 1, "wm_loss": 0.4284260869026184, "actor_loss": -8.686057090759277, "critic_loss": 0.039697498083114624, "reward": 0.07090896368026733, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24341264367103577, 0.1542951613664627, 0.2512827515602112], "policy_updates": 43550, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8893.263749762, "contact_bce": 0.3097648620605469, "contact_force_loss": 0.03289815038442612, "terrain_level_mean": 3.22607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43660, "total_transitions": 178831360, "num_steps_per_env": 1, "wm_loss": 0.42399948835372925, "actor_loss": -8.732748031616211, "critic_loss": 0.027026468887925148, "reward": 0.07089436799287796, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24678631126880646, 0.1569431573152542, 0.2521283030509949], "policy_updates": 43560, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8896.774554315001, "contact_bce": 0.3122802674770355, "contact_force_loss": 0.032755617052316666, "terrain_level_mean": 3.22607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43670, "total_transitions": 178872320, "num_steps_per_env": 1, "wm_loss": 0.42278891801834106, "actor_loss": -8.690971374511719, "critic_loss": 0.024861864745616913, "reward": 0.07048589736223221, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2511810064315796, 0.15872912108898163, 0.2573885917663574], "policy_updates": 43570, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8900.283390459, "contact_bce": 0.30978840589523315, "contact_force_loss": 0.03221302852034569, "terrain_level_mean": 3.227294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43680, "total_transitions": 178913280, "num_steps_per_env": 1, "wm_loss": 0.44593319296836853, "actor_loss": -8.733738899230957, "critic_loss": 0.02966327778995037, "reward": 0.07053154706954956, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24984188377857208, 0.15888391435146332, 0.2585499882698059], "policy_updates": 43580, "skipped_updates": 0, "invalid_env_resets": 86, "elapsed_s": 8903.797589916001, "contact_bce": 0.32337144017219543, "contact_force_loss": 0.033828988671302795, "terrain_level_mean": 3.2265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} RECOVERY reset 1 invalid environments; first IDs=[1146] {"step": 43690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43690, "total_transitions": 178954240, "num_steps_per_env": 1, "wm_loss": 0.4136486053466797, "actor_loss": -8.69104290008545, "critic_loss": 0.03325005993247032, "reward": 0.07037714868783951, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24837945401668549, 0.15890778601169586, 0.2537969946861267], "policy_updates": 43590, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8907.313209858, "contact_bce": 0.3141571879386902, "contact_force_loss": 0.032700520008802414, "terrain_level_mean": 3.226806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43700, "total_transitions": 178995200, "num_steps_per_env": 1, "wm_loss": 0.4060792624950409, "actor_loss": -8.759190559387207, "critic_loss": 0.03178355097770691, "reward": 0.0703703835606575, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25047168135643005, 0.15846367180347443, 0.25591614842414856], "policy_updates": 43600, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8910.828933345001, "contact_bce": 0.3084844946861267, "contact_force_loss": 0.03249331936240196, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43710, "total_transitions": 179036160, "num_steps_per_env": 1, "wm_loss": 0.41094619035720825, "actor_loss": -8.763886451721191, "critic_loss": 0.027710333466529846, "reward": 0.07031505554914474, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2528010606765747, 0.15968482196331024, 0.2539201080799103], "policy_updates": 43610, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8914.340929532, "contact_bce": 0.3131667971611023, "contact_force_loss": 0.03140386939048767, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43720, "total_transitions": 179077120, "num_steps_per_env": 1, "wm_loss": 0.4564192593097687, "actor_loss": -8.656904220581055, "critic_loss": 0.02862248197197914, "reward": 0.07022345811128616, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25453874468803406, 0.15936416387557983, 0.25401443243026733], "policy_updates": 43620, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8917.839445062, "contact_bce": 0.3162129819393158, "contact_force_loss": 0.03355482593178749, "terrain_level_mean": 3.227783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43730, "total_transitions": 179118080, "num_steps_per_env": 1, "wm_loss": 0.424848735332489, "actor_loss": -8.700937271118164, "critic_loss": 0.03425898030400276, "reward": 0.07016351819038391, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2526516020298004, 0.1566644012928009, 0.25450363755226135], "policy_updates": 43630, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8921.338876335001, "contact_bce": 0.31293991208076477, "contact_force_loss": 0.03317713364958763, "terrain_level_mean": 3.228271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332275390625, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43740, "total_transitions": 179159040, "num_steps_per_env": 1, "wm_loss": 0.42183762788772583, "actor_loss": -8.693638801574707, "critic_loss": 0.02478603832423687, "reward": 0.07053013890981674, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24777711927890778, 0.15519975125789642, 0.25446075201034546], "policy_updates": 43640, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8924.838402802001, "contact_bce": 0.30869370698928833, "contact_force_loss": 0.03226166218519211, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43750, "total_transitions": 179200000, "num_steps_per_env": 1, "wm_loss": 0.3956768810749054, "actor_loss": -8.724281311035156, "critic_loss": 0.03693161532282829, "reward": 0.0706729143857956, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24564354121685028, 0.15517738461494446, 0.2536187469959259], "policy_updates": 43650, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8928.334740126, "contact_bce": 0.3124673068523407, "contact_force_loss": 0.03299667686223984, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9993221759796143, 0.9999210834503174, 2.9959335327148438]} {"step": 43760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43760, "total_transitions": 179240960, "num_steps_per_env": 1, "wm_loss": 0.4468328356742859, "actor_loss": -8.717050552368164, "critic_loss": 0.026426726952195168, "reward": 0.0703658014535904, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24529260396957397, 0.15662144124507904, 0.2590847611427307], "policy_updates": 43660, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8931.839399675, "contact_bce": 0.3228456377983093, "contact_force_loss": 0.033249761909246445, "terrain_level_mean": 3.228759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9968852996826172, 0.9999210834503174, 2.9954988956451416]} {"step": 43770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43770, "total_transitions": 179281920, "num_steps_per_env": 1, "wm_loss": 0.3818638324737549, "actor_loss": -8.72983169555664, "critic_loss": 0.02364562451839447, "reward": 0.07011283934116364, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24426987767219543, 0.15855616331100464, 0.25912198424339294], "policy_updates": 43670, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8935.476773071001, "contact_bce": 0.30876702070236206, "contact_force_loss": 0.03144814074039459, "terrain_level_mean": 3.22900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9971445798873901, 0.9999210834503174, 2.9954988956451416]} {"step": 43780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43780, "total_transitions": 179322880, "num_steps_per_env": 1, "wm_loss": 0.4016621708869934, "actor_loss": -8.689050674438477, "critic_loss": 0.03598867356777191, "reward": 0.07019752264022827, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24504952132701874, 0.15991124510765076, 0.2599546015262604], "policy_updates": 43680, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8938.977344264, "contact_bce": 0.31275326013565063, "contact_force_loss": 0.03285110369324684, "terrain_level_mean": 3.230712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9971445798873901, 0.9999210834503174, 2.9954988956451416]} {"step": 43790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43790, "total_transitions": 179363840, "num_steps_per_env": 1, "wm_loss": 0.41784781217575073, "actor_loss": -8.679862976074219, "critic_loss": 0.03417472168803215, "reward": 0.07034111022949219, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24661137163639069, 0.16029025614261627, 0.2612624168395996], "policy_updates": 43690, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8942.476157077, "contact_bce": 0.3092954158782959, "contact_force_loss": 0.03215749189257622, "terrain_level_mean": 3.229736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333740234375, "command_abs_max": [1.9971445798873901, 0.9999210834503174, 2.9954988956451416]} {"step": 43800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43800, "total_transitions": 179404800, "num_steps_per_env": 1, "wm_loss": 0.4093993306159973, "actor_loss": -8.713447570800781, "critic_loss": 0.03141583502292633, "reward": 0.07075516134500504, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24808548390865326, 0.15961094200611115, 0.25966641306877136], "policy_updates": 43700, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8945.975793526, "contact_bce": 0.3116046190261841, "contact_force_loss": 0.03231210634112358, "terrain_level_mean": 3.23046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9971445798873901, 0.9999210834503174, 2.997798204421997]} {"step": 43810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43810, "total_transitions": 179445760, "num_steps_per_env": 1, "wm_loss": 0.4081318974494934, "actor_loss": -8.725973129272461, "critic_loss": 0.03028283827006817, "reward": 0.07065214961767197, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24945230782032013, 0.15978600084781647, 0.2579846978187561], "policy_updates": 43710, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8949.476450153, "contact_bce": 0.30412524938583374, "contact_force_loss": 0.03118186630308628, "terrain_level_mean": 3.2314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43820, "total_transitions": 179486720, "num_steps_per_env": 1, "wm_loss": 0.41912931203842163, "actor_loss": -8.707944869995117, "critic_loss": 0.028653264045715332, "reward": 0.07057048380374908, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2489997297525406, 0.15715444087982178, 0.2587500810623169], "policy_updates": 43720, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8952.978306023, "contact_bce": 0.31124094128608704, "contact_force_loss": 0.03228900954127312, "terrain_level_mean": 3.23046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43830, "total_transitions": 179527680, "num_steps_per_env": 1, "wm_loss": 0.43426135182380676, "actor_loss": -8.750052452087402, "critic_loss": 0.027965625748038292, "reward": 0.07045146822929382, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2533407211303711, 0.15733714401721954, 0.25768691301345825], "policy_updates": 43730, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8956.482529253, "contact_bce": 0.3050168454647064, "contact_force_loss": 0.03192906081676483, "terrain_level_mean": 3.228759765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43840, "total_transitions": 179568640, "num_steps_per_env": 1, "wm_loss": 0.4280340373516083, "actor_loss": -8.637939453125, "critic_loss": 0.039008159190416336, "reward": 0.07082989066839218, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25463810563087463, 0.15555138885974884, 0.2583996057510376], "policy_updates": 43740, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8960.001391471, "contact_bce": 0.31791073083877563, "contact_force_loss": 0.03290923312306404, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43850, "total_transitions": 179609600, "num_steps_per_env": 1, "wm_loss": 0.41471245884895325, "actor_loss": -8.698806762695312, "critic_loss": 0.02123497799038887, "reward": 0.07064617425203323, "falls": 5, "interval_steps": 10, "velocity_mae": [0.253115177154541, 0.1563420444726944, 0.25943219661712646], "policy_updates": 43750, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8963.509398154001, "contact_bce": 0.3138217628002167, "contact_force_loss": 0.03188862279057503, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43860, "total_transitions": 179650560, "num_steps_per_env": 1, "wm_loss": 0.4109486937522888, "actor_loss": -8.72434139251709, "critic_loss": 0.029862672090530396, "reward": 0.07092644274234772, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25100240111351013, 0.15974894165992737, 0.25837215781211853], "policy_updates": 43760, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8967.017420288, "contact_bce": 0.3151979446411133, "contact_force_loss": 0.03252853453159332, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43870, "total_transitions": 179691520, "num_steps_per_env": 1, "wm_loss": 0.43185845017433167, "actor_loss": -8.715404510498047, "critic_loss": 0.03479977324604988, "reward": 0.070458322763443, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2514755427837372, 0.15860611200332642, 0.2601342499256134], "policy_updates": 43770, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8970.527414185, "contact_bce": 0.3155854642391205, "contact_force_loss": 0.03241625055670738, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43880, "total_transitions": 179732480, "num_steps_per_env": 1, "wm_loss": 0.4333551824092865, "actor_loss": -8.743478775024414, "critic_loss": 0.02553669922053814, "reward": 0.0702461451292038, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2535122334957123, 0.159222811460495, 0.255827397108078], "policy_updates": 43780, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8974.039723394, "contact_bce": 0.31356844305992126, "contact_force_loss": 0.03284924104809761, "terrain_level_mean": 3.2275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9971445798873901, 0.9987987875938416, 2.997798204421997]} {"step": 43890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43890, "total_transitions": 179773440, "num_steps_per_env": 1, "wm_loss": 0.40888354182243347, "actor_loss": -8.713730812072754, "critic_loss": 0.03769313171505928, "reward": 0.07038360834121704, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24909810721874237, 0.1600225865840912, 0.25496840476989746], "policy_updates": 43790, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8977.551291916001, "contact_bce": 0.31651467084884644, "contact_force_loss": 0.03311629965901375, "terrain_level_mean": 3.22705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328125, "command_abs_max": [1.9985287189483643, 0.9984923601150513, 2.997798204421997]} {"step": 43900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43900, "total_transitions": 179814400, "num_steps_per_env": 1, "wm_loss": 0.39648860692977905, "actor_loss": -8.680639266967773, "critic_loss": 0.02946721576154232, "reward": 0.07091325521469116, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24728327989578247, 0.16010843217372894, 0.25332579016685486], "policy_updates": 43800, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8981.06918563, "contact_bce": 0.3100607395172119, "contact_force_loss": 0.031137868762016296, "terrain_level_mean": 3.227294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.9985287189483643, 0.9984923601150513, 2.997798204421997]} {"step": 43910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43910, "total_transitions": 179855360, "num_steps_per_env": 1, "wm_loss": 0.4313598573207855, "actor_loss": -8.675092697143555, "critic_loss": 0.04038766399025917, "reward": 0.07094862312078476, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24716047942638397, 0.1588338017463684, 0.255723237991333], "policy_updates": 43810, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8984.579731549, "contact_bce": 0.3156644403934479, "contact_force_loss": 0.03280576691031456, "terrain_level_mean": 3.226806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9985287189483643, 0.9984923601150513, 2.997798204421997]} {"step": 43920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43920, "total_transitions": 179896320, "num_steps_per_env": 1, "wm_loss": 0.4174750745296478, "actor_loss": -8.684293746948242, "critic_loss": 0.03432757407426834, "reward": 0.07089117169380188, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24992330372333527, 0.16219843924045563, 0.2574117183685303], "policy_updates": 43820, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8988.094098595, "contact_bce": 0.3108992576599121, "contact_force_loss": 0.031999822705984116, "terrain_level_mean": 3.226806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9990733861923218, 0.9984923601150513, 2.997798204421997]} {"step": 43930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43930, "total_transitions": 179937280, "num_steps_per_env": 1, "wm_loss": 0.409203439950943, "actor_loss": -8.708820343017578, "critic_loss": 0.03367294743657112, "reward": 0.0705810934305191, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2498476654291153, 0.16180865466594696, 0.2617005705833435], "policy_updates": 43830, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8991.598517013, "contact_bce": 0.3147701621055603, "contact_force_loss": 0.032207317650318146, "terrain_level_mean": 3.227294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3310546875, "command_abs_max": [1.9990733861923218, 0.9991410970687866, 2.997798204421997]} {"step": 43940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43940, "total_transitions": 179978240, "num_steps_per_env": 1, "wm_loss": 0.4093708395957947, "actor_loss": -8.666656494140625, "critic_loss": 0.03332702815532684, "reward": 0.0701245591044426, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25264790654182434, 0.16163887083530426, 0.26062747836112976], "policy_updates": 43840, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8995.098640499, "contact_bce": 0.3136145770549774, "contact_force_loss": 0.03228916972875595, "terrain_level_mean": 3.226318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.997798204421997]} {"step": 43950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43950, "total_transitions": 180019200, "num_steps_per_env": 1, "wm_loss": 0.42760294675827026, "actor_loss": -8.719694137573242, "critic_loss": 0.03097023069858551, "reward": 0.06994161009788513, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2534732222557068, 0.1580057591199875, 0.26499637961387634], "policy_updates": 43850, "skipped_updates": 0, "invalid_env_resets": 87, "elapsed_s": 8998.609458579, "contact_bce": 0.31015700101852417, "contact_force_loss": 0.03292544186115265, "terrain_level_mean": 3.2255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.997798204421997]} RECOVERY reset 1 invalid environments; first IDs=[742] {"step": 43960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43960, "total_transitions": 180060160, "num_steps_per_env": 1, "wm_loss": 0.40956589579582214, "actor_loss": -8.692537307739258, "critic_loss": 0.03459827974438667, "reward": 0.07060591131448746, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2528979778289795, 0.15768039226531982, 0.26039862632751465], "policy_updates": 43860, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9002.128122853, "contact_bce": 0.31120312213897705, "contact_force_loss": 0.03188125789165497, "terrain_level_mean": 3.224853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.997798204421997]} {"step": 43970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43970, "total_transitions": 180101120, "num_steps_per_env": 1, "wm_loss": 0.437923401594162, "actor_loss": -8.695320129394531, "critic_loss": 0.02860129438340664, "reward": 0.07101502269506454, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2501254081726074, 0.15547971427440643, 0.2519444525241852], "policy_updates": 43870, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9005.618143198, "contact_bce": 0.31262022256851196, "contact_force_loss": 0.03222518786787987, "terrain_level_mean": 3.225341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.997798204421997]} {"step": 43980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43980, "total_transitions": 180142080, "num_steps_per_env": 1, "wm_loss": 0.4440280795097351, "actor_loss": -8.728641510009766, "critic_loss": 0.026433158665895462, "reward": 0.07118921726942062, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2424650937318802, 0.15443070232868195, 0.25392040610313416], "policy_updates": 43880, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9009.123566177, "contact_bce": 0.3210250735282898, "contact_force_loss": 0.03318645805120468, "terrain_level_mean": 3.224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 43990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 43990, "total_transitions": 180183040, "num_steps_per_env": 1, "wm_loss": 0.4013584852218628, "actor_loss": -8.759434700012207, "critic_loss": 0.03047885000705719, "reward": 0.07075487822294235, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24489375948905945, 0.15598618984222412, 0.25352492928504944], "policy_updates": 43890, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9012.649889442, "contact_bce": 0.3136790692806244, "contact_force_loss": 0.03304797410964966, "terrain_level_mean": 3.224365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44000, "total_transitions": 180224000, "num_steps_per_env": 1, "wm_loss": 0.43076127767562866, "actor_loss": -8.717708587646484, "critic_loss": 0.03697234392166138, "reward": 0.07092194259166718, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2443331480026245, 0.15614672005176544, 0.25385400652885437], "policy_updates": 43900, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9016.171047724001, "contact_bce": 0.31094205379486084, "contact_force_loss": 0.032495927065610886, "terrain_level_mean": 3.224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44010, "total_transitions": 180264960, "num_steps_per_env": 1, "wm_loss": 0.43569478392601013, "actor_loss": -8.690359115600586, "critic_loss": 0.032625894993543625, "reward": 0.0711607038974762, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24206766486167908, 0.15404152870178223, 0.2506820261478424], "policy_updates": 43910, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9019.724245523, "contact_bce": 0.3122626543045044, "contact_force_loss": 0.0327882282435894, "terrain_level_mean": 3.22509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3291015625, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44020, "total_transitions": 180305920, "num_steps_per_env": 1, "wm_loss": 0.4108053743839264, "actor_loss": -8.679073333740234, "critic_loss": 0.03533225879073143, "reward": 0.07114405184984207, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24000847339630127, 0.15458334982395172, 0.24568507075309753], "policy_updates": 43920, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9023.502099997, "contact_bce": 0.31167474389076233, "contact_force_loss": 0.03275209665298462, "terrain_level_mean": 3.225830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330322265625, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44030, "total_transitions": 180346880, "num_steps_per_env": 1, "wm_loss": 0.41270074248313904, "actor_loss": -8.768664360046387, "critic_loss": 0.029321247711777687, "reward": 0.07080058008432388, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2384089231491089, 0.15526598691940308, 0.25027623772621155], "policy_updates": 43930, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9027.022744376001, "contact_bce": 0.31713366508483887, "contact_force_loss": 0.03273008391261101, "terrain_level_mean": 3.225341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44040, "total_transitions": 180387840, "num_steps_per_env": 1, "wm_loss": 0.4045741856098175, "actor_loss": -8.727972030639648, "critic_loss": 0.022854004055261612, "reward": 0.07116731256246567, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2372363954782486, 0.15469440817832947, 0.2521206736564636], "policy_updates": 43940, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9030.542457875, "contact_bce": 0.3161192536354065, "contact_force_loss": 0.03239445760846138, "terrain_level_mean": 3.225341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44050, "total_transitions": 180428800, "num_steps_per_env": 1, "wm_loss": 0.42194339632987976, "actor_loss": -8.709296226501465, "critic_loss": 0.01956341229379177, "reward": 0.07086058706045151, "falls": 11, "interval_steps": 10, "velocity_mae": [0.23814360797405243, 0.15707950294017792, 0.25527167320251465], "policy_updates": 43950, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9034.061861067, "contact_bce": 0.3141534626483917, "contact_force_loss": 0.033263254910707474, "terrain_level_mean": 3.224365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44060, "total_transitions": 180469760, "num_steps_per_env": 1, "wm_loss": 0.400799036026001, "actor_loss": -8.737509727478027, "critic_loss": 0.02648370899260044, "reward": 0.07076885551214218, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24050311744213104, 0.15770386159420013, 0.2525007128715515], "policy_updates": 43960, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9037.581153111001, "contact_bce": 0.3137262463569641, "contact_force_loss": 0.032642923295497894, "terrain_level_mean": 3.2255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9997413158416748, 0.9991410970687866, 2.9994373321533203]} {"step": 44070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44070, "total_transitions": 180510720, "num_steps_per_env": 1, "wm_loss": 0.42527270317077637, "actor_loss": -8.775136947631836, "critic_loss": 0.027317721396684647, "reward": 0.07093708217144012, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24319909512996674, 0.1566011607646942, 0.25076475739479065], "policy_updates": 43970, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9041.100279075, "contact_bce": 0.30810126662254333, "contact_force_loss": 0.032111894339323044, "terrain_level_mean": 3.2255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44080, "total_transitions": 180551680, "num_steps_per_env": 1, "wm_loss": 0.40829038619995117, "actor_loss": -8.737974166870117, "critic_loss": 0.03496778756380081, "reward": 0.07124917954206467, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2414923459291458, 0.1552979201078415, 0.251475065946579], "policy_updates": 43980, "skipped_updates": 0, "invalid_env_resets": 88, "elapsed_s": 9044.626003708001, "contact_bce": 0.30949410796165466, "contact_force_loss": 0.0328766405582428, "terrain_level_mean": 3.2255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} RECOVERY reset 1 invalid environments; first IDs=[983] {"step": 44090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44090, "total_transitions": 180592640, "num_steps_per_env": 1, "wm_loss": 0.3877731263637543, "actor_loss": -8.706125259399414, "critic_loss": 0.02750704064965248, "reward": 0.07141584157943726, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2389044314622879, 0.1540423035621643, 0.2507765591144562], "policy_updates": 43990, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9048.169873581, "contact_bce": 0.3098829686641693, "contact_force_loss": 0.03217571973800659, "terrain_level_mean": 3.224853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44100, "total_transitions": 180633600, "num_steps_per_env": 1, "wm_loss": 0.4018207788467407, "actor_loss": -8.741997718811035, "critic_loss": 0.03722608461976051, "reward": 0.07174263894557953, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23458325862884521, 0.15279068052768707, 0.25262102484703064], "policy_updates": 44000, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9051.700179633, "contact_bce": 0.31392115354537964, "contact_force_loss": 0.03201085329055786, "terrain_level_mean": 3.224853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44110, "total_transitions": 180674560, "num_steps_per_env": 1, "wm_loss": 0.40716904401779175, "actor_loss": -8.770647048950195, "critic_loss": 0.03873768821358681, "reward": 0.07130813598632812, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23835694789886475, 0.15433119237422943, 0.2532557249069214], "policy_updates": 44010, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9055.208887174, "contact_bce": 0.3161379396915436, "contact_force_loss": 0.03190886974334717, "terrain_level_mean": 3.22509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44120, "total_transitions": 180715520, "num_steps_per_env": 1, "wm_loss": 0.4079439342021942, "actor_loss": -8.711248397827148, "critic_loss": 0.04144644737243652, "reward": 0.07100459933280945, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24091647565364838, 0.154618501663208, 0.2522195875644684], "policy_updates": 44020, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9058.729536841001, "contact_bce": 0.3137853741645813, "contact_force_loss": 0.032492510974407196, "terrain_level_mean": 3.2255859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44130, "total_transitions": 180756480, "num_steps_per_env": 1, "wm_loss": 0.40923362970352173, "actor_loss": -8.695845603942871, "critic_loss": 0.04238468408584595, "reward": 0.07137367874383926, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23619765043258667, 0.155466228723526, 0.25019916892051697], "policy_updates": 44030, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9062.249315446, "contact_bce": 0.3144063651561737, "contact_force_loss": 0.03269100934267044, "terrain_level_mean": 3.225830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44140, "total_transitions": 180797440, "num_steps_per_env": 1, "wm_loss": 0.4354668855667114, "actor_loss": -8.786026000976562, "critic_loss": 0.018992954865098, "reward": 0.07124124467372894, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2374974489212036, 0.15454570949077606, 0.25141528248786926], "policy_updates": 44040, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9065.772256251, "contact_bce": 0.31571024656295776, "contact_force_loss": 0.03230489417910576, "terrain_level_mean": 3.22607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44150, "total_transitions": 180838400, "num_steps_per_env": 1, "wm_loss": 0.4126238226890564, "actor_loss": -8.72365665435791, "critic_loss": 0.026550037786364555, "reward": 0.07115080952644348, "falls": 4, "interval_steps": 10, "velocity_mae": [0.237845316529274, 0.15331409871578217, 0.24966782331466675], "policy_updates": 44050, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9069.28014755, "contact_bce": 0.3137204945087433, "contact_force_loss": 0.03287115693092346, "terrain_level_mean": 3.22607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9997413158416748, 0.9994792938232422, 2.9994373321533203]} {"step": 44160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44160, "total_transitions": 180879360, "num_steps_per_env": 1, "wm_loss": 0.43578606843948364, "actor_loss": -8.723976135253906, "critic_loss": 0.030666504055261612, "reward": 0.07078364491462708, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2381986379623413, 0.1534900665283203, 0.2474893033504486], "policy_updates": 44060, "skipped_updates": 0, "invalid_env_resets": 89, "elapsed_s": 9072.782718433, "contact_bce": 0.31180551648139954, "contact_force_loss": 0.032358407974243164, "terrain_level_mean": 3.2265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9985287189483643, 0.9994792938232422, 2.9994373321533203]} RECOVERY reset 1 invalid environments; first IDs=[2111] {"step": 44170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44170, "total_transitions": 180920320, "num_steps_per_env": 1, "wm_loss": 0.4179695248603821, "actor_loss": -8.772525787353516, "critic_loss": 0.025940490886569023, "reward": 0.07050012797117233, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24271798133850098, 0.15236175060272217, 0.254706472158432], "policy_updates": 44070, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9076.313080650001, "contact_bce": 0.3111495077610016, "contact_force_loss": 0.03199019655585289, "terrain_level_mean": 3.22705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9985287189483643, 0.9994792938232422, 2.9994373321533203]} {"step": 44180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44180, "total_transitions": 180961280, "num_steps_per_env": 1, "wm_loss": 0.41729819774627686, "actor_loss": -8.754745483398438, "critic_loss": 0.022753922268748283, "reward": 0.07053040713071823, "falls": 0, "interval_steps": 10, "velocity_mae": [0.24236337840557098, 0.15356320142745972, 0.2535214424133301], "policy_updates": 44080, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9079.827692505001, "contact_bce": 0.3080524206161499, "contact_force_loss": 0.032540787011384964, "terrain_level_mean": 3.22900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9985287189483643, 0.9994792938232422, 2.9994373321533203]} {"step": 44190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44190, "total_transitions": 181002240, "num_steps_per_env": 1, "wm_loss": 0.4170096218585968, "actor_loss": -8.75555419921875, "critic_loss": 0.02906123176217079, "reward": 0.07036907225847244, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24383993446826935, 0.15783347189426422, 0.2539726495742798], "policy_updates": 44090, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9083.343904978, "contact_bce": 0.3161158561706543, "contact_force_loss": 0.03297913819551468, "terrain_level_mean": 3.2275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9985287189483643, 0.9994792938232422, 2.9994373321533203]} {"step": 44200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44200, "total_transitions": 181043200, "num_steps_per_env": 1, "wm_loss": 0.44067639112472534, "actor_loss": -8.715864181518555, "critic_loss": 0.029102398082613945, "reward": 0.07049573957920074, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24309733510017395, 0.1557735651731491, 0.24863861501216888], "policy_updates": 44100, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9086.857275638, "contact_bce": 0.3130481541156769, "contact_force_loss": 0.032912880182266235, "terrain_level_mean": 3.22705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9985287189483643, 0.9994792938232422, 2.9994373321533203]} {"step": 44210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44210, "total_transitions": 181084160, "num_steps_per_env": 1, "wm_loss": 0.39521315693855286, "actor_loss": -8.749055862426758, "critic_loss": 0.023188592866063118, "reward": 0.07124241441488266, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24220305681228638, 0.15545617043972015, 0.24889451265335083], "policy_updates": 44110, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9090.375540245, "contact_bce": 0.31000685691833496, "contact_force_loss": 0.03246264532208443, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9985287189483643, 0.9994792938232422, 2.9994373321533203]} {"step": 44220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44220, "total_transitions": 181125120, "num_steps_per_env": 1, "wm_loss": 0.4215342104434967, "actor_loss": -8.751642227172852, "critic_loss": 0.025468552485108376, "reward": 0.07095532864332199, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24262696504592896, 0.15481877326965332, 0.24887770414352417], "policy_updates": 44120, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9093.903550605, "contact_bce": 0.31159085035324097, "contact_force_loss": 0.03207674250006676, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44230, "total_transitions": 181166080, "num_steps_per_env": 1, "wm_loss": 0.3982439339160919, "actor_loss": -8.737845420837402, "critic_loss": 0.027369225397706032, "reward": 0.07043247669935226, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24087676405906677, 0.15459442138671875, 0.2539246678352356], "policy_updates": 44130, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9097.416061075, "contact_bce": 0.31114864349365234, "contact_force_loss": 0.031398795545101166, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44240, "total_transitions": 181207040, "num_steps_per_env": 1, "wm_loss": 0.3927272856235504, "actor_loss": -8.729490280151367, "critic_loss": 0.02799607627093792, "reward": 0.07034899294376373, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2425578534603119, 0.15676556527614594, 0.25387299060821533], "policy_updates": 44140, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9100.931341491001, "contact_bce": 0.3089159429073334, "contact_force_loss": 0.03185456246137619, "terrain_level_mean": 3.22900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44250, "total_transitions": 181248000, "num_steps_per_env": 1, "wm_loss": 0.39600637555122375, "actor_loss": -8.728170394897461, "critic_loss": 0.02086586132645607, "reward": 0.070309117436409, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24296322464942932, 0.15981939435005188, 0.25111648440361023], "policy_updates": 44150, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9104.446993256, "contact_bce": 0.30946630239486694, "contact_force_loss": 0.031043946743011475, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44260, "total_transitions": 181288960, "num_steps_per_env": 1, "wm_loss": 0.4321015179157257, "actor_loss": -8.715221405029297, "critic_loss": 0.027439702302217484, "reward": 0.07034406065940857, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24114148318767548, 0.1584579199552536, 0.2499476820230484], "policy_updates": 44160, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9107.96217781, "contact_bce": 0.3118252754211426, "contact_force_loss": 0.03244685381650925, "terrain_level_mean": 3.227294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44270, "total_transitions": 181329920, "num_steps_per_env": 1, "wm_loss": 0.3898182809352875, "actor_loss": -8.75003433227539, "critic_loss": 0.034901637583971024, "reward": 0.07061191648244858, "falls": 6, "interval_steps": 10, "velocity_mae": [0.243937686085701, 0.15555943548679352, 0.24676242470741272], "policy_updates": 44170, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9111.478108777, "contact_bce": 0.3091239035129547, "contact_force_loss": 0.030957190319895744, "terrain_level_mean": 3.22705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44280, "total_transitions": 181370880, "num_steps_per_env": 1, "wm_loss": 0.4315910041332245, "actor_loss": -8.762845039367676, "critic_loss": 0.035049501806497574, "reward": 0.07036679983139038, "falls": 11, "interval_steps": 10, "velocity_mae": [0.2448975294828415, 0.15663541853427887, 0.2470221370458603], "policy_updates": 44180, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9114.988125888001, "contact_bce": 0.3140915334224701, "contact_force_loss": 0.0325494259595871, "terrain_level_mean": 3.2265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44290, "total_transitions": 181411840, "num_steps_per_env": 1, "wm_loss": 0.39505258202552795, "actor_loss": -8.743624687194824, "critic_loss": 0.041476424783468246, "reward": 0.07065000385046005, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2462276965379715, 0.156992569565773, 0.24664978682994843], "policy_updates": 44190, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9118.499290328, "contact_bce": 0.3120167851448059, "contact_force_loss": 0.03203968331217766, "terrain_level_mean": 3.225830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44300, "total_transitions": 181452800, "num_steps_per_env": 1, "wm_loss": 0.4258146584033966, "actor_loss": -8.693706512451172, "critic_loss": 0.03805987164378166, "reward": 0.07037972658872604, "falls": 5, "interval_steps": 10, "velocity_mae": [0.246766597032547, 0.15637555718421936, 0.24809502065181732], "policy_updates": 44200, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9122.014436002, "contact_bce": 0.31498050689697266, "contact_force_loss": 0.03265468403697014, "terrain_level_mean": 3.225830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44310, "total_transitions": 181493760, "num_steps_per_env": 1, "wm_loss": 0.4312531650066376, "actor_loss": -8.781623840332031, "critic_loss": 0.028496015816926956, "reward": 0.07072560489177704, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2430468648672104, 0.15560650825500488, 0.24972417950630188], "policy_updates": 44210, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9125.518293217001, "contact_bce": 0.31453344225883484, "contact_force_loss": 0.03249755874276161, "terrain_level_mean": 3.226318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9990177154541016, 0.9994792938232422, 2.9994373321533203]} {"step": 44320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44320, "total_transitions": 181534720, "num_steps_per_env": 1, "wm_loss": 0.41956520080566406, "actor_loss": -8.7612943649292, "critic_loss": 0.027151448652148247, "reward": 0.07087500393390656, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2416129857301712, 0.1576463282108307, 0.2525644600391388], "policy_updates": 44220, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9129.028918007001, "contact_bce": 0.31050387024879456, "contact_force_loss": 0.03265367075800896, "terrain_level_mean": 3.225830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9994373321533203]} {"step": 44330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44330, "total_transitions": 181575680, "num_steps_per_env": 1, "wm_loss": 0.37977099418640137, "actor_loss": -8.713418006896973, "critic_loss": 0.024535182863473892, "reward": 0.07115911692380905, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24149051308631897, 0.15736788511276245, 0.25210094451904297], "policy_updates": 44230, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9132.545612825, "contact_bce": 0.313043475151062, "contact_force_loss": 0.03150121867656708, "terrain_level_mean": 3.22412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9994373321533203]} {"step": 44340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44340, "total_transitions": 181616640, "num_steps_per_env": 1, "wm_loss": 0.42634764313697815, "actor_loss": -8.702713966369629, "critic_loss": 0.040003497153520584, "reward": 0.07110490649938583, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23790407180786133, 0.1545305997133255, 0.248580664396286], "policy_updates": 44240, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9136.052749807, "contact_bce": 0.31069833040237427, "contact_force_loss": 0.03211584314703941, "terrain_level_mean": 3.2236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9994373321533203]} {"step": 44350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44350, "total_transitions": 181657600, "num_steps_per_env": 1, "wm_loss": 0.4012727737426758, "actor_loss": -8.719792366027832, "critic_loss": 0.024910233914852142, "reward": 0.07084526121616364, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24166227877140045, 0.15416550636291504, 0.25293490290641785], "policy_updates": 44250, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9139.563917504001, "contact_bce": 0.3136349022388458, "contact_force_loss": 0.031870417296886444, "terrain_level_mean": 3.223388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9994373321533203]} {"step": 44360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44360, "total_transitions": 181698560, "num_steps_per_env": 1, "wm_loss": 0.4046032726764679, "actor_loss": -8.676295280456543, "critic_loss": 0.028172096237540245, "reward": 0.07125531882047653, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24163293838500977, 0.15441153943538666, 0.2518153488636017], "policy_updates": 44260, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9143.088571064001, "contact_bce": 0.31513455510139465, "contact_force_loss": 0.03174813464283943, "terrain_level_mean": 3.222900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9974777698516846]} {"step": 44370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44370, "total_transitions": 181739520, "num_steps_per_env": 1, "wm_loss": 0.43532800674438477, "actor_loss": -8.743568420410156, "critic_loss": 0.026850074529647827, "reward": 0.0712682232260704, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2438620775938034, 0.15598267316818237, 0.2510281503200531], "policy_updates": 44270, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9146.602148565, "contact_bce": 0.3212791085243225, "contact_force_loss": 0.03286247327923775, "terrain_level_mean": 3.223876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9985809326171875]} {"step": 44380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44380, "total_transitions": 181780480, "num_steps_per_env": 1, "wm_loss": 0.3949185609817505, "actor_loss": -8.732850074768066, "critic_loss": 0.030365372076630592, "reward": 0.0710710808634758, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2431209236383438, 0.15561440587043762, 0.24948959052562714], "policy_updates": 44280, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9150.114915891001, "contact_bce": 0.3108532726764679, "contact_force_loss": 0.03192305937409401, "terrain_level_mean": 3.2216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335693359375, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9985809326171875]} {"step": 44390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44390, "total_transitions": 181821440, "num_steps_per_env": 1, "wm_loss": 0.3946250379085541, "actor_loss": -8.795663833618164, "critic_loss": 0.028048187494277954, "reward": 0.07112892717123032, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24268269538879395, 0.1542285531759262, 0.25398778915405273], "policy_updates": 44290, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9153.635966727, "contact_bce": 0.3111461102962494, "contact_force_loss": 0.03189387172460556, "terrain_level_mean": 3.22119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9985809326171875]} {"step": 44400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44400, "total_transitions": 181862400, "num_steps_per_env": 1, "wm_loss": 0.41603919863700867, "actor_loss": -8.71557903289795, "critic_loss": 0.03463578224182129, "reward": 0.07117974758148193, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24497251212596893, 0.15389494597911835, 0.25223931670188904], "policy_updates": 44300, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9157.160664875, "contact_bce": 0.3137435019016266, "contact_force_loss": 0.032042767852544785, "terrain_level_mean": 3.22216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9985809326171875]} {"step": 44410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44410, "total_transitions": 181903360, "num_steps_per_env": 1, "wm_loss": 0.43064171075820923, "actor_loss": -8.734034538269043, "critic_loss": 0.026784224435687065, "reward": 0.07122445851564407, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24501933157444, 0.153294637799263, 0.2468567192554474], "policy_updates": 44310, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9160.678675609, "contact_bce": 0.3188683092594147, "contact_force_loss": 0.032989609986543655, "terrain_level_mean": 3.22119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32958984375, "command_abs_max": [1.9990177154541016, 0.9989019632339478, 2.9985809326171875]} {"step": 44420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44420, "total_transitions": 181944320, "num_steps_per_env": 1, "wm_loss": 0.4163616895675659, "actor_loss": -8.757187843322754, "critic_loss": 0.027229411527514458, "reward": 0.07121863961219788, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24371787905693054, 0.15126436948776245, 0.2481410801410675], "policy_updates": 44320, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9164.189729038, "contact_bce": 0.3205420672893524, "contact_force_loss": 0.033431194722652435, "terrain_level_mean": 3.2216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32861328125, "command_abs_max": [1.9967858791351318, 0.9989019632339478, 2.9985809326171875]} {"step": 44430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44430, "total_transitions": 181985280, "num_steps_per_env": 1, "wm_loss": 0.4196886420249939, "actor_loss": -8.719985961914062, "critic_loss": 0.026413092389702797, "reward": 0.07092822343111038, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24264869093894958, 0.15324290096759796, 0.24973958730697632], "policy_updates": 44330, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9167.703005388, "contact_bce": 0.31244632601737976, "contact_force_loss": 0.03255530446767807, "terrain_level_mean": 3.22216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32666015625, "command_abs_max": [1.9967858791351318, 0.9989019632339478, 2.9985809326171875]} {"step": 44440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44440, "total_transitions": 182026240, "num_steps_per_env": 1, "wm_loss": 0.41490307450294495, "actor_loss": -8.747772216796875, "critic_loss": 0.02456795796751976, "reward": 0.07105936855077744, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24460369348526, 0.1524030864238739, 0.25015220046043396], "policy_updates": 44340, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9171.226188346001, "contact_bce": 0.31391042470932007, "contact_force_loss": 0.03143005073070526, "terrain_level_mean": 3.22216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32861328125, "command_abs_max": [1.9999840259552002, 0.9989019632339478, 2.9985809326171875]} {"step": 44450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44450, "total_transitions": 182067200, "num_steps_per_env": 1, "wm_loss": 0.39087262749671936, "actor_loss": -8.730855941772461, "critic_loss": 0.025883439928293228, "reward": 0.07122083753347397, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24580083787441254, 0.15203924477100372, 0.2501969635486603], "policy_updates": 44350, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9174.743328746, "contact_bce": 0.3104553818702698, "contact_force_loss": 0.031031498685479164, "terrain_level_mean": 3.222900390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9999840259552002, 0.9989019632339478, 2.9985809326171875]} {"step": 44460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44460, "total_transitions": 182108160, "num_steps_per_env": 1, "wm_loss": 0.4164707064628601, "actor_loss": -8.750543594360352, "critic_loss": 0.02113049104809761, "reward": 0.07096917927265167, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24526099860668182, 0.15411624312400818, 0.25391924381256104], "policy_updates": 44360, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9178.264402939001, "contact_bce": 0.3130946457386017, "contact_force_loss": 0.03200691193342209, "terrain_level_mean": 3.222412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328369140625, "command_abs_max": [1.9999840259552002, 0.9989019632339478, 2.9985809326171875]} {"step": 44470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44470, "total_transitions": 182149120, "num_steps_per_env": 1, "wm_loss": 0.39484110474586487, "actor_loss": -8.75318717956543, "critic_loss": 0.01845799759030342, "reward": 0.07126379013061523, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2431911677122116, 0.15476971864700317, 0.2538425326347351], "policy_updates": 44370, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9181.789741315, "contact_bce": 0.31095412373542786, "contact_force_loss": 0.03229344263672829, "terrain_level_mean": 3.22265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.325439453125, "command_abs_max": [1.9999840259552002, 0.9989019632339478, 2.9985809326171875]} {"step": 44480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44480, "total_transitions": 182190080, "num_steps_per_env": 1, "wm_loss": 0.38775521516799927, "actor_loss": -8.754127502441406, "critic_loss": 0.029330480843782425, "reward": 0.07085908204317093, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24289704859256744, 0.15902215242385864, 0.2591603398323059], "policy_updates": 44380, "skipped_updates": 0, "invalid_env_resets": 90, "elapsed_s": 9185.309302629, "contact_bce": 0.30241841077804565, "contact_force_loss": 0.030950484797358513, "terrain_level_mean": 3.221923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32373046875, "command_abs_max": [1.9999840259552002, 0.9990919828414917, 2.9985809326171875]} RECOVERY reset 1 invalid environments; first IDs=[2260] {"step": 44490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44490, "total_transitions": 182231040, "num_steps_per_env": 1, "wm_loss": 0.40097928047180176, "actor_loss": -8.696916580200195, "critic_loss": 0.028872424736618996, "reward": 0.0704929530620575, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24587193131446838, 0.1632148176431656, 0.257962167263031], "policy_updates": 44390, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9188.838419383, "contact_bce": 0.315520316362381, "contact_force_loss": 0.0324399471282959, "terrain_level_mean": 3.220947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32763671875, "command_abs_max": [1.9999840259552002, 0.9990919828414917, 2.9985809326171875]} {"step": 44500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44500, "total_transitions": 182272000, "num_steps_per_env": 1, "wm_loss": 0.3931882679462433, "actor_loss": -8.747193336486816, "critic_loss": 0.025953639298677444, "reward": 0.07052095979452133, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2479407638311386, 0.16387516260147095, 0.2546389698982239], "policy_updates": 44400, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9192.365381448, "contact_bce": 0.3097638189792633, "contact_force_loss": 0.03188825398683548, "terrain_level_mean": 3.2216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9999840259552002, 0.9990919828414917, 2.9985809326171875]} {"step": 44510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44510, "total_transitions": 182312960, "num_steps_per_env": 1, "wm_loss": 0.4109368324279785, "actor_loss": -8.711954116821289, "critic_loss": 0.021597785875201225, "reward": 0.07050034403800964, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24791668355464935, 0.15996935963630676, 0.2513461709022522], "policy_updates": 44410, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9195.908863214001, "contact_bce": 0.3095962703227997, "contact_force_loss": 0.03170853108167648, "terrain_level_mean": 3.220947265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.328125, "command_abs_max": [1.9999840259552002, 0.9990919828414917, 2.9985809326171875]} {"step": 44520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44520, "total_transitions": 182353920, "num_steps_per_env": 1, "wm_loss": 0.4315825402736664, "actor_loss": -8.721541404724121, "critic_loss": 0.03377973660826683, "reward": 0.07019292563199997, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24740110337734222, 0.1610356867313385, 0.25699982047080994], "policy_updates": 44420, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9199.664397055001, "contact_bce": 0.31506413221359253, "contact_force_loss": 0.03268996626138687, "terrain_level_mean": 3.22119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9999840259552002, 0.9990919828414917, 2.9985809326171875]} {"step": 44530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44530, "total_transitions": 182394880, "num_steps_per_env": 1, "wm_loss": 0.4323081374168396, "actor_loss": -8.730405807495117, "critic_loss": 0.02401210181415081, "reward": 0.0701177716255188, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2446081042289734, 0.1629536747932434, 0.2543681859970093], "policy_updates": 44430, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9203.176599216, "contact_bce": 0.3138141632080078, "contact_force_loss": 0.032464902848005295, "terrain_level_mean": 3.219970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33056640625, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44540, "total_transitions": 182435840, "num_steps_per_env": 1, "wm_loss": 0.4197779893875122, "actor_loss": -8.73457145690918, "critic_loss": 0.03052464686334133, "reward": 0.07014252990484238, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2471916377544403, 0.1649283915758133, 0.256687730550766], "policy_updates": 44440, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9206.688884515, "contact_bce": 0.311969131231308, "contact_force_loss": 0.03229600191116333, "terrain_level_mean": 3.22021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44550, "total_transitions": 182476800, "num_steps_per_env": 1, "wm_loss": 0.40295180678367615, "actor_loss": -8.719039916992188, "critic_loss": 0.028629157692193985, "reward": 0.07027417421340942, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24907660484313965, 0.162566140294075, 0.2552487552165985], "policy_updates": 44450, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9210.212491038, "contact_bce": 0.31694117188453674, "contact_force_loss": 0.0313698910176754, "terrain_level_mean": 3.219482421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332275390625, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44560, "total_transitions": 182517760, "num_steps_per_env": 1, "wm_loss": 0.4295805096626282, "actor_loss": -8.712728500366211, "critic_loss": 0.03863173723220825, "reward": 0.07027602940797806, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2515276074409485, 0.1611577570438385, 0.25750574469566345], "policy_updates": 44460, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9213.736488710001, "contact_bce": 0.31247568130493164, "contact_force_loss": 0.03229270875453949, "terrain_level_mean": 3.22021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44570, "total_transitions": 182558720, "num_steps_per_env": 1, "wm_loss": 0.41836926341056824, "actor_loss": -8.71639633178711, "critic_loss": 0.022730428725481033, "reward": 0.07021687924861908, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2500232756137848, 0.16106626391410828, 0.2597046494483948], "policy_updates": 44470, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9217.252624408, "contact_bce": 0.31158071756362915, "contact_force_loss": 0.031825415790081024, "terrain_level_mean": 3.219970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329345703125, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44580, "total_transitions": 182599680, "num_steps_per_env": 1, "wm_loss": 0.42628681659698486, "actor_loss": -8.714155197143555, "critic_loss": 0.022929614409804344, "reward": 0.0698198601603508, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2512931525707245, 0.16303877532482147, 0.25541210174560547], "policy_updates": 44480, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9220.769549184, "contact_bce": 0.31565728783607483, "contact_force_loss": 0.03311804682016373, "terrain_level_mean": 3.21875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3291015625, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44590, "total_transitions": 182640640, "num_steps_per_env": 1, "wm_loss": 0.4566039741039276, "actor_loss": -8.765521049499512, "critic_loss": 0.022000020369887352, "reward": 0.070386603474617, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24807628989219666, 0.15975555777549744, 0.25247126817703247], "policy_updates": 44490, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9224.291552184, "contact_bce": 0.31265926361083984, "contact_force_loss": 0.03244879096746445, "terrain_level_mean": 3.219482421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44600, "total_transitions": 182681600, "num_steps_per_env": 1, "wm_loss": 0.39368534088134766, "actor_loss": -8.786352157592773, "critic_loss": 0.025323599576950073, "reward": 0.07063426822423935, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2439950406551361, 0.160172238945961, 0.24883459508419037], "policy_updates": 44500, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9227.808724513001, "contact_bce": 0.3073000907897949, "contact_force_loss": 0.0317201130092144, "terrain_level_mean": 3.218505859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44610, "total_transitions": 182722560, "num_steps_per_env": 1, "wm_loss": 0.4159100353717804, "actor_loss": -8.71119499206543, "critic_loss": 0.0316518135368824, "reward": 0.07057397812604904, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24578402936458588, 0.15866850316524506, 0.24995164573192596], "policy_updates": 44510, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9231.329741623, "contact_bce": 0.30341145396232605, "contact_force_loss": 0.03180603310465813, "terrain_level_mean": 3.218017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44620, "total_transitions": 182763520, "num_steps_per_env": 1, "wm_loss": 0.44398900866508484, "actor_loss": -8.754281044006348, "critic_loss": 0.021040335297584534, "reward": 0.07073139399290085, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24668337404727936, 0.15748868882656097, 0.2532946467399597], "policy_updates": 44520, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9234.836742028001, "contact_bce": 0.30874329805374146, "contact_force_loss": 0.03270554170012474, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.9999840259552002, 0.9991061687469482, 2.9985809326171875]} {"step": 44630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44630, "total_transitions": 182804480, "num_steps_per_env": 1, "wm_loss": 0.40355369448661804, "actor_loss": -8.769542694091797, "critic_loss": 0.01678994856774807, "reward": 0.07081611454486847, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24499687552452087, 0.15368646383285522, 0.2544459104537964], "policy_updates": 44530, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9238.342510363, "contact_bce": 0.3168501555919647, "contact_force_loss": 0.03238128498196602, "terrain_level_mean": 3.217529296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3330078125, "command_abs_max": [1.9991309642791748, 0.9991061687469482, 2.9985809326171875]} {"step": 44640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44640, "total_transitions": 182845440, "num_steps_per_env": 1, "wm_loss": 0.4163011610507965, "actor_loss": -8.760998725891113, "critic_loss": 0.023148471489548683, "reward": 0.07071524113416672, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24952132999897003, 0.15268515050411224, 0.25217199325561523], "policy_updates": 44540, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9241.860164789001, "contact_bce": 0.31281882524490356, "contact_force_loss": 0.03231174126267433, "terrain_level_mean": 3.217041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330322265625, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.9985809326171875]} {"step": 44650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44650, "total_transitions": 182886400, "num_steps_per_env": 1, "wm_loss": 0.40131521224975586, "actor_loss": -8.755586624145508, "critic_loss": 0.028113622218370438, "reward": 0.07095946371555328, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24953992664813995, 0.15227290987968445, 0.25422707200050354], "policy_updates": 44550, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9245.380777856, "contact_bce": 0.30912142992019653, "contact_force_loss": 0.03196094557642937, "terrain_level_mean": 3.216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333740234375, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.9985809326171875]} {"step": 44660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44660, "total_transitions": 182927360, "num_steps_per_env": 1, "wm_loss": 0.4056413769721985, "actor_loss": -8.694807052612305, "critic_loss": 0.034051116555929184, "reward": 0.07112351804971695, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24902474880218506, 0.15239644050598145, 0.24716196954250336], "policy_updates": 44560, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9248.902870002, "contact_bce": 0.31174442172050476, "contact_force_loss": 0.03246481716632843, "terrain_level_mean": 3.21728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334716796875, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.9985809326171875]} {"step": 44670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44670, "total_transitions": 182968320, "num_steps_per_env": 1, "wm_loss": 0.40848907828330994, "actor_loss": -8.669891357421875, "critic_loss": 0.02437443844974041, "reward": 0.07109462469816208, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24822290241718292, 0.15261593461036682, 0.25219762325286865], "policy_updates": 44570, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9252.417078036, "contact_bce": 0.30622225999832153, "contact_force_loss": 0.03188611939549446, "terrain_level_mean": 3.21728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.999098777770996]} {"step": 44680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44680, "total_transitions": 183009280, "num_steps_per_env": 1, "wm_loss": 0.40910935401916504, "actor_loss": -8.705850601196289, "critic_loss": 0.02628333307802677, "reward": 0.07103484123945236, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24551448225975037, 0.15566414594650269, 0.24894310534000397], "policy_updates": 44580, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9255.930338716, "contact_bce": 0.31127089262008667, "contact_force_loss": 0.03187860921025276, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44690, "total_transitions": 183050240, "num_steps_per_env": 1, "wm_loss": 0.4063570201396942, "actor_loss": -8.730284690856934, "critic_loss": 0.02455388940870762, "reward": 0.07124107331037521, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24211962521076202, 0.15479008853435516, 0.24655218422412872], "policy_updates": 44590, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9259.452832874, "contact_bce": 0.3122507929801941, "contact_force_loss": 0.032333943992853165, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44700, "total_transitions": 183091200, "num_steps_per_env": 1, "wm_loss": 0.4068935513496399, "actor_loss": -8.75387954711914, "critic_loss": 0.028178973123431206, "reward": 0.07059527188539505, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2461676448583603, 0.1535978764295578, 0.24807576835155487], "policy_updates": 44600, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9262.962098018, "contact_bce": 0.30894070863723755, "contact_force_loss": 0.03154125064611435, "terrain_level_mean": 3.21826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44710, "total_transitions": 183132160, "num_steps_per_env": 1, "wm_loss": 0.37794017791748047, "actor_loss": -8.671281814575195, "critic_loss": 0.032465290278196335, "reward": 0.07014142721891403, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25002622604370117, 0.1534772664308548, 0.25240275263786316], "policy_updates": 44610, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9266.468820029, "contact_bce": 0.30374786257743835, "contact_force_loss": 0.03062654472887516, "terrain_level_mean": 3.218994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44720, "total_transitions": 183173120, "num_steps_per_env": 1, "wm_loss": 0.40607401728630066, "actor_loss": -8.766886711120605, "critic_loss": 0.027103031054139137, "reward": 0.07003200054168701, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24843484163284302, 0.15714791417121887, 0.25504210591316223], "policy_updates": 44620, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9269.980175282, "contact_bce": 0.3146081566810608, "contact_force_loss": 0.032753437757492065, "terrain_level_mean": 3.21923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44730, "total_transitions": 183214080, "num_steps_per_env": 1, "wm_loss": 0.3915296792984009, "actor_loss": -8.72811222076416, "critic_loss": 0.02348681353032589, "reward": 0.07045181095600128, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2472066581249237, 0.15660175681114197, 0.25448867678642273], "policy_updates": 44630, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9273.492743247001, "contact_bce": 0.3140975832939148, "contact_force_loss": 0.032021619379520416, "terrain_level_mean": 3.21923828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44740, "total_transitions": 183255040, "num_steps_per_env": 1, "wm_loss": 0.41019463539123535, "actor_loss": -8.714197158813477, "critic_loss": 0.02619985304772854, "reward": 0.07065053284168243, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24564602971076965, 0.1556260734796524, 0.2557068467140198], "policy_updates": 44640, "skipped_updates": 0, "invalid_env_resets": 91, "elapsed_s": 9277.00595832, "contact_bce": 0.31347164511680603, "contact_force_loss": 0.032530833035707474, "terrain_level_mean": 3.2197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} RECOVERY reset 1 invalid environments; first IDs=[1780] {"step": 44750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44750, "total_transitions": 183296000, "num_steps_per_env": 1, "wm_loss": 0.3913959860801697, "actor_loss": -8.708828926086426, "critic_loss": 0.0317213349044323, "reward": 0.07071708887815475, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24792331457138062, 0.15764375030994415, 0.2587696611881256], "policy_updates": 44650, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9280.527407862, "contact_bce": 0.31334376335144043, "contact_force_loss": 0.03134097903966904, "terrain_level_mean": 3.219970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44760, "total_transitions": 183336960, "num_steps_per_env": 1, "wm_loss": 0.4285285770893097, "actor_loss": -8.675252914428711, "critic_loss": 0.03577614948153496, "reward": 0.0701909214258194, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25607362389564514, 0.1576010286808014, 0.25748753547668457], "policy_updates": 44660, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9284.039333337001, "contact_bce": 0.3082914352416992, "contact_force_loss": 0.032857220619916916, "terrain_level_mean": 3.220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44770, "total_transitions": 183377920, "num_steps_per_env": 1, "wm_loss": 0.4015437960624695, "actor_loss": -8.781457901000977, "critic_loss": 0.03140537440776825, "reward": 0.06994672864675522, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2578733265399933, 0.1589457243680954, 0.2575490176677704], "policy_updates": 44670, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9287.545079654, "contact_bce": 0.3130233585834503, "contact_force_loss": 0.03200070559978485, "terrain_level_mean": 3.22021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44780, "total_transitions": 183418880, "num_steps_per_env": 1, "wm_loss": 0.3988548219203949, "actor_loss": -8.735282897949219, "critic_loss": 0.022657332941889763, "reward": 0.0705437883734703, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2560277581214905, 0.15722723305225372, 0.25061479210853577], "policy_updates": 44680, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9291.060398859001, "contact_bce": 0.31091901659965515, "contact_force_loss": 0.03190835192799568, "terrain_level_mean": 3.220458984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44790, "total_transitions": 183459840, "num_steps_per_env": 1, "wm_loss": 0.38853219151496887, "actor_loss": -8.72819709777832, "critic_loss": 0.028196385130286217, "reward": 0.0702497735619545, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25552821159362793, 0.156660258769989, 0.2560865581035614], "policy_updates": 44690, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9294.571211906, "contact_bce": 0.30799105763435364, "contact_force_loss": 0.03133818507194519, "terrain_level_mean": 3.22021484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44800, "total_transitions": 183500800, "num_steps_per_env": 1, "wm_loss": 0.435416579246521, "actor_loss": -8.722289085388184, "critic_loss": 0.03621537238359451, "reward": 0.07013756781816483, "falls": 11, "interval_steps": 10, "velocity_mae": [0.2549211084842682, 0.15647593140602112, 0.25451475381851196], "policy_updates": 44700, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9298.071099248, "contact_bce": 0.31565263867378235, "contact_force_loss": 0.03319113701581955, "terrain_level_mean": 3.21826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.999692440032959, 0.9995216131210327, 2.999098777770996]} {"step": 44810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44810, "total_transitions": 183541760, "num_steps_per_env": 1, "wm_loss": 0.4202764332294464, "actor_loss": -8.732498168945312, "critic_loss": 0.025260254740715027, "reward": 0.07063143700361252, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25153204798698425, 0.1566614806652069, 0.2539251148700714], "policy_updates": 44710, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9301.575465281001, "contact_bce": 0.31591665744781494, "contact_force_loss": 0.032897334545850754, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.999098777770996]} {"step": 44820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44820, "total_transitions": 183582720, "num_steps_per_env": 1, "wm_loss": 0.3958032429218292, "actor_loss": -8.716239929199219, "critic_loss": 0.03291062265634537, "reward": 0.07082585245370865, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2509573698043823, 0.15458720922470093, 0.25157272815704346], "policy_updates": 44720, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9305.079406838, "contact_bce": 0.30467408895492554, "contact_force_loss": 0.03183335065841675, "terrain_level_mean": 3.216552734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.9979143142700195]} {"step": 44830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44830, "total_transitions": 183623680, "num_steps_per_env": 1, "wm_loss": 0.4222736656665802, "actor_loss": -8.683245658874512, "critic_loss": 0.030788147822022438, "reward": 0.07097189873456955, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24865758419036865, 0.15401579439640045, 0.251453697681427], "policy_updates": 44730, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9308.59009343, "contact_bce": 0.31668519973754883, "contact_force_loss": 0.03319597989320755, "terrain_level_mean": 3.216064453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.9945759773254395]} {"step": 44840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44840, "total_transitions": 183664640, "num_steps_per_env": 1, "wm_loss": 0.3992551863193512, "actor_loss": -8.741677284240723, "critic_loss": 0.028994133695960045, "reward": 0.07133799046278, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24601085484027863, 0.1556895226240158, 0.2493492066860199], "policy_updates": 44740, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9312.09996538, "contact_bce": 0.3162494897842407, "contact_force_loss": 0.03313564136624336, "terrain_level_mean": 3.215576171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.9945759773254395]} {"step": 44850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44850, "total_transitions": 183705600, "num_steps_per_env": 1, "wm_loss": 0.425424724817276, "actor_loss": -8.703115463256836, "critic_loss": 0.02750452235341072, "reward": 0.07157454639673233, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24560967087745667, 0.1535295844078064, 0.24574899673461914], "policy_updates": 44750, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9315.612502006, "contact_bce": 0.31277406215667725, "contact_force_loss": 0.0317782387137413, "terrain_level_mean": 3.217041015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.999692440032959, 0.9991061687469482, 2.9945759773254395]} {"step": 44860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44860, "total_transitions": 183746560, "num_steps_per_env": 1, "wm_loss": 0.3829323649406433, "actor_loss": -8.752727508544922, "critic_loss": 0.019423363730311394, "reward": 0.07128513604402542, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24781987071037292, 0.15530484914779663, 0.24781973659992218], "policy_updates": 44760, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9319.121912199, "contact_bce": 0.31536731123924255, "contact_force_loss": 0.03206354379653931, "terrain_level_mean": 3.216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.999692440032959, 0.9993091821670532, 2.9945759773254395]} {"step": 44870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44870, "total_transitions": 183787520, "num_steps_per_env": 1, "wm_loss": 0.40868866443634033, "actor_loss": -8.719243049621582, "critic_loss": 0.03367042541503906, "reward": 0.07138027995824814, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2468048632144928, 0.15681950747966766, 0.25049567222595215], "policy_updates": 44770, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9322.622627651, "contact_bce": 0.31284642219543457, "contact_force_loss": 0.032472677528858185, "terrain_level_mean": 3.217529296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.999692440032959, 0.9993091821670532, 2.9945759773254395]} {"step": 44880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44880, "total_transitions": 183828480, "num_steps_per_env": 1, "wm_loss": 0.41060951352119446, "actor_loss": -8.718852043151855, "critic_loss": 0.029108544811606407, "reward": 0.07154293358325958, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24351271986961365, 0.15569862723350525, 0.2506161034107208], "policy_updates": 44780, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9326.128787761001, "contact_bce": 0.30909907817840576, "contact_force_loss": 0.032201990485191345, "terrain_level_mean": 3.21826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.999692440032959, 0.9993091821670532, 2.9927961826324463]} {"step": 44890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44890, "total_transitions": 183869440, "num_steps_per_env": 1, "wm_loss": 0.39291518926620483, "actor_loss": -8.712965965270996, "critic_loss": 0.03744278475642204, "reward": 0.07110481709241867, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24652138352394104, 0.15070952475070953, 0.2516792118549347], "policy_updates": 44790, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9329.638181874001, "contact_bce": 0.30992600321769714, "contact_force_loss": 0.031771790236234665, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.999692440032959, 0.9993091821670532, 2.9927961826324463]} {"step": 44900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44900, "total_transitions": 183910400, "num_steps_per_env": 1, "wm_loss": 0.43123480677604675, "actor_loss": -8.63115406036377, "critic_loss": 0.03433351218700409, "reward": 0.07111065089702606, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24982741475105286, 0.1498999148607254, 0.2513309717178345], "policy_updates": 44800, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9333.151879492001, "contact_bce": 0.3084036409854889, "contact_force_loss": 0.0320887416601181, "terrain_level_mean": 3.218017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9962804317474365, 0.9993091821670532, 2.9927961826324463]} {"step": 44910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44910, "total_transitions": 183951360, "num_steps_per_env": 1, "wm_loss": 0.468941867351532, "actor_loss": -8.730679512023926, "critic_loss": 0.023028207942843437, "reward": 0.07109292596578598, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2513579726219177, 0.14968989789485931, 0.2538960874080658], "policy_updates": 44810, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9336.665855976, "contact_bce": 0.32295072078704834, "contact_force_loss": 0.03236585855484009, "terrain_level_mean": 3.218994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9962804317474365, 0.9993091821670532, 2.9927961826324463]} {"step": 44920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44920, "total_transitions": 183992320, "num_steps_per_env": 1, "wm_loss": 0.409579873085022, "actor_loss": -8.714225769042969, "critic_loss": 0.028525322675704956, "reward": 0.07112590223550797, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2534143626689911, 0.15056151151657104, 0.2504935562610626], "policy_updates": 44820, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9340.166134413, "contact_bce": 0.3178199231624603, "contact_force_loss": 0.032978348433971405, "terrain_level_mean": 3.21826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9962804317474365, 0.9993091821670532, 2.9927961826324463]} {"step": 44930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44930, "total_transitions": 184033280, "num_steps_per_env": 1, "wm_loss": 0.4080500602722168, "actor_loss": -8.71419906616211, "critic_loss": 0.029441092163324356, "reward": 0.07128893584012985, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25005096197128296, 0.15039974451065063, 0.2491672784090042], "policy_updates": 44830, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9343.673988678, "contact_bce": 0.313564658164978, "contact_force_loss": 0.03342858701944351, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9962804317474365, 0.9993091821670532, 2.9927961826324463]} {"step": 44940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44940, "total_transitions": 184074240, "num_steps_per_env": 1, "wm_loss": 0.4095125198364258, "actor_loss": -8.716663360595703, "critic_loss": 0.034594159573316574, "reward": 0.07116863131523132, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25086691975593567, 0.1507265716791153, 0.24878577888011932], "policy_updates": 44840, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9347.181430936, "contact_bce": 0.3113909065723419, "contact_force_loss": 0.03256424516439438, "terrain_level_mean": 3.2177734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9962804317474365, 0.9993091821670532, 2.9927961826324463]} {"step": 44950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44950, "total_transitions": 184115200, "num_steps_per_env": 1, "wm_loss": 0.4473611116409302, "actor_loss": -8.677244186401367, "critic_loss": 0.029947249218821526, "reward": 0.07108522951602936, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24717587232589722, 0.15157550573349, 0.24905267357826233], "policy_updates": 44850, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9350.699050851, "contact_bce": 0.3187243342399597, "contact_force_loss": 0.033328983932733536, "terrain_level_mean": 3.218017578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9989312887191772, 0.9993091821670532, 2.9927961826324463]} {"step": 44960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44960, "total_transitions": 184156160, "num_steps_per_env": 1, "wm_loss": 0.41522547602653503, "actor_loss": -8.770479202270508, "critic_loss": 0.026012493297457695, "reward": 0.07110058516263962, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24853824079036713, 0.15039299428462982, 0.24873286485671997], "policy_updates": 44860, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9354.220720107001, "contact_bce": 0.31149354577064514, "contact_force_loss": 0.03209920600056648, "terrain_level_mean": 3.21826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9989312887191772, 0.9993091821670532, 2.992553949356079]} {"step": 44970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44970, "total_transitions": 184197120, "num_steps_per_env": 1, "wm_loss": 0.4028013050556183, "actor_loss": -8.720900535583496, "critic_loss": 0.021098850294947624, "reward": 0.07101002335548401, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24308380484580994, 0.15078018605709076, 0.24867165088653564], "policy_updates": 44870, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9357.743459019, "contact_bce": 0.3124140799045563, "contact_force_loss": 0.03191940113902092, "terrain_level_mean": 3.2197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9989312887191772, 0.9993091821670532, 2.992553949356079]} {"step": 44980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44980, "total_transitions": 184238080, "num_steps_per_env": 1, "wm_loss": 0.4151648283004761, "actor_loss": -8.715143203735352, "critic_loss": 0.027143536135554314, "reward": 0.07066062092781067, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2429904043674469, 0.15362057089805603, 0.2528191804885864], "policy_updates": 44880, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9361.255979492, "contact_bce": 0.3142067790031433, "contact_force_loss": 0.0328194722533226, "terrain_level_mean": 3.21875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9989312887191772, 0.9993091821670532, 2.992553949356079]} {"step": 44990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 44990, "total_transitions": 184279040, "num_steps_per_env": 1, "wm_loss": 0.40149566531181335, "actor_loss": -8.73294448852539, "critic_loss": 0.02694636397063732, "reward": 0.07036533206701279, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24813957512378693, 0.15393222868442535, 0.2524973154067993], "policy_updates": 44890, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9364.775802365, "contact_bce": 0.31101614236831665, "contact_force_loss": 0.03221510350704193, "terrain_level_mean": 3.21875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45000, "total_transitions": 184320000, "num_steps_per_env": 1, "wm_loss": 0.41715019941329956, "actor_loss": -8.71435260772705, "critic_loss": 0.027724910527467728, "reward": 0.07105202227830887, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2467195689678192, 0.1543223112821579, 0.2505841851234436], "policy_updates": 44900, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9368.283927796001, "contact_bce": 0.31274843215942383, "contact_force_loss": 0.032001420855522156, "terrain_level_mean": 3.218994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45010, "total_transitions": 184360960, "num_steps_per_env": 1, "wm_loss": 0.41277799010276794, "actor_loss": -8.7664213180542, "critic_loss": 0.0236086156219244, "reward": 0.071077361702919, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24735412001609802, 0.1535320281982422, 0.2522523105144501], "policy_updates": 44910, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9371.82417405, "contact_bce": 0.3122554123401642, "contact_force_loss": 0.0326160304248333, "terrain_level_mean": 3.219970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45020, "total_transitions": 184401920, "num_steps_per_env": 1, "wm_loss": 0.40569475293159485, "actor_loss": -8.705846786499023, "critic_loss": 0.02884632907807827, "reward": 0.07104665786027908, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2493281066417694, 0.15818987786769867, 0.2521716058254242], "policy_updates": 44920, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9375.593791901001, "contact_bce": 0.307068407535553, "contact_force_loss": 0.031614940613508224, "terrain_level_mean": 3.218994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45030, "total_transitions": 184442880, "num_steps_per_env": 1, "wm_loss": 0.38744404911994934, "actor_loss": -8.770819664001465, "critic_loss": 0.03124779835343361, "reward": 0.07115467637777328, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2520303428173065, 0.15691596269607544, 0.2533606290817261], "policy_updates": 44930, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9379.115815495, "contact_bce": 0.3142475485801697, "contact_force_loss": 0.032885923981666565, "terrain_level_mean": 3.21875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45040, "total_transitions": 184483840, "num_steps_per_env": 1, "wm_loss": 0.395243763923645, "actor_loss": -8.694465637207031, "critic_loss": 0.04184163734316826, "reward": 0.07134847342967987, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25203678011894226, 0.15446768701076508, 0.2502468526363373], "policy_updates": 44940, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9382.636450671, "contact_bce": 0.3090888261795044, "contact_force_loss": 0.031556982547044754, "terrain_level_mean": 3.21826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45050, "total_transitions": 184524800, "num_steps_per_env": 1, "wm_loss": 0.40862682461738586, "actor_loss": -8.74653434753418, "critic_loss": 0.023674452677369118, "reward": 0.07133167237043381, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2532234489917755, 0.15241114795207977, 0.24997055530548096], "policy_updates": 44950, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9386.152338312, "contact_bce": 0.3135572671890259, "contact_force_loss": 0.03287786617875099, "terrain_level_mean": 3.218994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45060, "total_transitions": 184565760, "num_steps_per_env": 1, "wm_loss": 0.4077420234680176, "actor_loss": -8.711673736572266, "critic_loss": 0.034162554889917374, "reward": 0.07134377211332321, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2518202066421509, 0.15357482433319092, 0.2552773654460907], "policy_updates": 44960, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9389.677665516001, "contact_bce": 0.3105185925960541, "contact_force_loss": 0.032390497624874115, "terrain_level_mean": 3.218994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.995327949523926]} {"step": 45070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45070, "total_transitions": 184606720, "num_steps_per_env": 1, "wm_loss": 0.3869384229183197, "actor_loss": -8.732248306274414, "critic_loss": 0.026317259296774864, "reward": 0.07125097513198853, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24911586940288544, 0.1549440324306488, 0.2539826035499573], "policy_updates": 44970, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9393.210169304, "contact_bce": 0.31288644671440125, "contact_force_loss": 0.032317034900188446, "terrain_level_mean": 3.219970703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45080, "total_transitions": 184647680, "num_steps_per_env": 1, "wm_loss": 0.40733304619789124, "actor_loss": -8.707691192626953, "critic_loss": 0.02410765178501606, "reward": 0.07085136324167252, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2543506324291229, 0.15639865398406982, 0.2532704770565033], "policy_updates": 44980, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9396.728154809001, "contact_bce": 0.31266120076179504, "contact_force_loss": 0.032457973808050156, "terrain_level_mean": 3.21875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45090, "total_transitions": 184688640, "num_steps_per_env": 1, "wm_loss": 0.3961964547634125, "actor_loss": -8.773008346557617, "critic_loss": 0.02268817648291588, "reward": 0.07088165730237961, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2557292878627777, 0.15754210948944092, 0.2538030743598938], "policy_updates": 44990, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9400.235842253, "contact_bce": 0.3113035261631012, "contact_force_loss": 0.031707294285297394, "terrain_level_mean": 3.218994140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45100, "total_transitions": 184729600, "num_steps_per_env": 1, "wm_loss": 0.40993866324424744, "actor_loss": -8.741864204406738, "critic_loss": 0.027115775272250175, "reward": 0.07088301330804825, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25248315930366516, 0.15630954504013062, 0.25711023807525635], "policy_updates": 45000, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9403.749597376, "contact_bce": 0.3147999346256256, "contact_force_loss": 0.03303048014640808, "terrain_level_mean": 3.2197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45110, "total_transitions": 184770560, "num_steps_per_env": 1, "wm_loss": 0.38269752264022827, "actor_loss": -8.73997688293457, "critic_loss": 0.02864067628979683, "reward": 0.07072923332452774, "falls": 1, "interval_steps": 10, "velocity_mae": [0.25520893931388855, 0.1567881852388382, 0.2573217451572418], "policy_updates": 45010, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9407.264198046001, "contact_bce": 0.3184199333190918, "contact_force_loss": 0.03250155225396156, "terrain_level_mean": 3.22119140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45120, "total_transitions": 184811520, "num_steps_per_env": 1, "wm_loss": 0.4006687104701996, "actor_loss": -8.714719772338867, "critic_loss": 0.02774454466998577, "reward": 0.0709109827876091, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2565051317214966, 0.15617743134498596, 0.2514024078845978], "policy_updates": 45020, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9410.790276008, "contact_bce": 0.31138622760772705, "contact_force_loss": 0.032897427678108215, "terrain_level_mean": 3.221435546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45130, "total_transitions": 184852480, "num_steps_per_env": 1, "wm_loss": 0.41876116394996643, "actor_loss": -8.739625930786133, "critic_loss": 0.03150443732738495, "reward": 0.07144229859113693, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24773190915584564, 0.1560053527355194, 0.25038906931877136], "policy_updates": 45030, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9414.320981692, "contact_bce": 0.3140782117843628, "contact_force_loss": 0.03269563242793083, "terrain_level_mean": 3.22216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45140, "total_transitions": 184893440, "num_steps_per_env": 1, "wm_loss": 0.41195714473724365, "actor_loss": -8.742792129516602, "critic_loss": 0.02202257327735424, "reward": 0.07125188410282135, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25017428398132324, 0.1541547179222107, 0.2516215741634369], "policy_updates": 45040, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9417.847606857, "contact_bce": 0.3055894374847412, "contact_force_loss": 0.032204434275627136, "terrain_level_mean": 3.223388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45150, "total_transitions": 184934400, "num_steps_per_env": 1, "wm_loss": 0.4143611788749695, "actor_loss": -8.690568923950195, "critic_loss": 0.03794019669294357, "reward": 0.07145955413579941, "falls": 7, "interval_steps": 10, "velocity_mae": [0.248416930437088, 0.15397046506404877, 0.24957893788814545], "policy_updates": 45050, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9421.348931409, "contact_bce": 0.31286969780921936, "contact_force_loss": 0.03259149193763733, "terrain_level_mean": 3.22265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45160, "total_transitions": 184975360, "num_steps_per_env": 1, "wm_loss": 0.39529794454574585, "actor_loss": -8.727773666381836, "critic_loss": 0.03223549202084541, "reward": 0.07101774960756302, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24678826332092285, 0.1554608792066574, 0.25407734513282776], "policy_updates": 45060, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9424.844123335, "contact_bce": 0.30978161096572876, "contact_force_loss": 0.03208761662244797, "terrain_level_mean": 3.22265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45170, "total_transitions": 185016320, "num_steps_per_env": 1, "wm_loss": 0.41118288040161133, "actor_loss": -8.779609680175781, "critic_loss": 0.022519661113619804, "reward": 0.07068920880556107, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2479800134897232, 0.15557938814163208, 0.2539629638195038], "policy_updates": 45070, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9428.344020324, "contact_bce": 0.31269368529319763, "contact_force_loss": 0.033071935176849365, "terrain_level_mean": 3.225341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45180, "total_transitions": 185057280, "num_steps_per_env": 1, "wm_loss": 0.3917536437511444, "actor_loss": -8.74969482421875, "critic_loss": 0.030178982764482498, "reward": 0.0707167536020279, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2496865838766098, 0.15782512724399567, 0.25399595499038696], "policy_updates": 45080, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9431.848284518, "contact_bce": 0.31277817487716675, "contact_force_loss": 0.03173370659351349, "terrain_level_mean": 3.226806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45190, "total_transitions": 185098240, "num_steps_per_env": 1, "wm_loss": 0.41146647930145264, "actor_loss": -8.723426818847656, "critic_loss": 0.029292264953255653, "reward": 0.07077515125274658, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25037384033203125, 0.15588147938251495, 0.2558012008666992], "policy_updates": 45090, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9435.353547159, "contact_bce": 0.30968940258026123, "contact_force_loss": 0.03282371535897255, "terrain_level_mean": 3.226806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9996323585510254, 0.9993091821670532, 2.9970052242279053]} {"step": 45200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45200, "total_transitions": 185139200, "num_steps_per_env": 1, "wm_loss": 0.3836396038532257, "actor_loss": -8.72465991973877, "critic_loss": 0.02770031988620758, "reward": 0.07058306038379669, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24952034652233124, 0.1581442654132843, 0.2541896402835846], "policy_updates": 45100, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9438.855578009001, "contact_bce": 0.31120529770851135, "contact_force_loss": 0.03213456645607948, "terrain_level_mean": 3.226806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9996323585510254, 0.9989778995513916, 2.9970052242279053]} {"step": 45210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45210, "total_transitions": 185180160, "num_steps_per_env": 1, "wm_loss": 0.4086148738861084, "actor_loss": -8.764634132385254, "critic_loss": 0.026489228010177612, "reward": 0.07090836763381958, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24789324402809143, 0.15934155881404877, 0.24958908557891846], "policy_updates": 45110, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9442.370454024001, "contact_bce": 0.31335172057151794, "contact_force_loss": 0.0318036787211895, "terrain_level_mean": 3.2275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9996323585510254, 0.9989778995513916, 2.9970052242279053]} {"step": 45220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45220, "total_transitions": 185221120, "num_steps_per_env": 1, "wm_loss": 0.4001275300979614, "actor_loss": -8.724984169006348, "critic_loss": 0.028148293495178223, "reward": 0.07096447795629501, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24425621330738068, 0.15814432501792908, 0.25236573815345764], "policy_updates": 45120, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9445.896946550001, "contact_bce": 0.31145375967025757, "contact_force_loss": 0.03286084905266762, "terrain_level_mean": 3.227294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9996323585510254, 0.9989778995513916, 2.9970052242279053]} {"step": 45230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45230, "total_transitions": 185262080, "num_steps_per_env": 1, "wm_loss": 0.39807581901550293, "actor_loss": -8.726541519165039, "critic_loss": 0.028565583750605583, "reward": 0.07087545841932297, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24524864554405212, 0.15577661991119385, 0.25376781821250916], "policy_updates": 45130, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9449.412546001, "contact_bce": 0.3094004690647125, "contact_force_loss": 0.03193386271595955, "terrain_level_mean": 3.226318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9996323585510254, 0.9989778995513916, 2.9970052242279053]} Warning: EPA horizon = 24 isn't large enough. {"step": 45240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45240, "total_transitions": 185303040, "num_steps_per_env": 1, "wm_loss": 0.40684574842453003, "actor_loss": -8.745528221130371, "critic_loss": 0.023847704753279686, "reward": 0.07100152969360352, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24674731492996216, 0.15574467182159424, 0.2573741376399994], "policy_updates": 45140, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9452.935508238, "contact_bce": 0.3120151162147522, "contact_force_loss": 0.03236743435263634, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9996323585510254, 0.9989778995513916, 2.9970052242279053]} {"step": 45250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45250, "total_transitions": 185344000, "num_steps_per_env": 1, "wm_loss": 0.3942120373249054, "actor_loss": -8.74751091003418, "critic_loss": 0.027414703741669655, "reward": 0.07104963064193726, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2489442527294159, 0.15628162026405334, 0.2545684278011322], "policy_updates": 45150, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9456.443352751001, "contact_bce": 0.30776292085647583, "contact_force_loss": 0.03218541666865349, "terrain_level_mean": 3.227783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9996323585510254, 0.9965218305587769, 2.9970052242279053]} {"step": 45260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45260, "total_transitions": 185384960, "num_steps_per_env": 1, "wm_loss": 0.38234972953796387, "actor_loss": -8.770759582519531, "critic_loss": 0.02706960216164589, "reward": 0.07122274488210678, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2472214549779892, 0.1566469520330429, 0.25193724036216736], "policy_updates": 45160, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9459.939180677, "contact_bce": 0.30402103066444397, "contact_force_loss": 0.031224824488162994, "terrain_level_mean": 3.227783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9996323585510254, 0.9965218305587769, 2.9970052242279053]} {"step": 45270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45270, "total_transitions": 185425920, "num_steps_per_env": 1, "wm_loss": 0.40879225730895996, "actor_loss": -8.711263656616211, "critic_loss": 0.02941809967160225, "reward": 0.07098131626844406, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24481646716594696, 0.15677626430988312, 0.2526971995830536], "policy_updates": 45170, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9463.459477913, "contact_bce": 0.3079663813114166, "contact_force_loss": 0.03179645165801048, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9970052242279053]} {"step": 45280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45280, "total_transitions": 185466880, "num_steps_per_env": 1, "wm_loss": 0.4054020941257477, "actor_loss": -8.705123901367188, "critic_loss": 0.042716559022665024, "reward": 0.07114876806735992, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24803881347179413, 0.15556323528289795, 0.24801072478294373], "policy_updates": 45180, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9466.980713313, "contact_bce": 0.3146568536758423, "contact_force_loss": 0.03249962255358696, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9970052242279053]} {"step": 45290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45290, "total_transitions": 185507840, "num_steps_per_env": 1, "wm_loss": 0.41071265935897827, "actor_loss": -8.727010726928711, "critic_loss": 0.029629284515976906, "reward": 0.0709570050239563, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24877402186393738, 0.15409716963768005, 0.25120702385902405], "policy_updates": 45190, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9470.502212332001, "contact_bce": 0.3135363459587097, "contact_force_loss": 0.032981205731630325, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9970052242279053]} {"step": 45300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45300, "total_transitions": 185548800, "num_steps_per_env": 1, "wm_loss": 0.38004055619239807, "actor_loss": -8.759550094604492, "critic_loss": 0.024235105141997337, "reward": 0.07098864763975143, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24735091626644135, 0.1534673273563385, 0.25110840797424316], "policy_updates": 45200, "skipped_updates": 0, "invalid_env_resets": 92, "elapsed_s": 9474.018683073, "contact_bce": 0.3061724603176117, "contact_force_loss": 0.03123757801949978, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9973790645599365]} RECOVERY reset 1 invalid environments; first IDs=[858] {"step": 45310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45310, "total_transitions": 185589760, "num_steps_per_env": 1, "wm_loss": 0.39045652747154236, "actor_loss": -8.732975959777832, "critic_loss": 0.029818717390298843, "reward": 0.07062641531229019, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2469479739665985, 0.15366508066654205, 0.24851997196674347], "policy_updates": 45210, "skipped_updates": 0, "invalid_env_resets": 93, "elapsed_s": 9477.558747298, "contact_bce": 0.30899181962013245, "contact_force_loss": 0.03167622908949852, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9973790645599365]} RECOVERY reset 1 invalid environments; first IDs=[2043] {"step": 45320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45320, "total_transitions": 185630720, "num_steps_per_env": 1, "wm_loss": 0.37941592931747437, "actor_loss": -8.767282485961914, "critic_loss": 0.02248762547969818, "reward": 0.07047706097364426, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24666143953800201, 0.15754784643650055, 0.2535073161125183], "policy_updates": 45220, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9481.091362852001, "contact_bce": 0.3091931641101837, "contact_force_loss": 0.031730178743600845, "terrain_level_mean": 3.22802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9973790645599365]} {"step": 45330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45330, "total_transitions": 185671680, "num_steps_per_env": 1, "wm_loss": 0.3942851424217224, "actor_loss": -8.730863571166992, "critic_loss": 0.02974245324730873, "reward": 0.07075951248407364, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2459970861673355, 0.15697169303894043, 0.25714945793151855], "policy_updates": 45230, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9484.595956729001, "contact_bce": 0.30683261156082153, "contact_force_loss": 0.03180825710296631, "terrain_level_mean": 3.2275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9973790645599365]} {"step": 45340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45340, "total_transitions": 185712640, "num_steps_per_env": 1, "wm_loss": 0.40396079421043396, "actor_loss": -8.73124885559082, "critic_loss": 0.0293770432472229, "reward": 0.07066983729600906, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24803131818771362, 0.1562408059835434, 0.25613200664520264], "policy_updates": 45240, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9488.119576611001, "contact_bce": 0.30612680315971375, "contact_force_loss": 0.03253926336765289, "terrain_level_mean": 3.2265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9973790645599365]} {"step": 45350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45350, "total_transitions": 185753600, "num_steps_per_env": 1, "wm_loss": 0.4371998608112335, "actor_loss": -8.70541000366211, "critic_loss": 0.01715194247663021, "reward": 0.07044120132923126, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25042596459388733, 0.15609966218471527, 0.25715094804763794], "policy_updates": 45250, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9491.641135134001, "contact_bce": 0.31521397829055786, "contact_force_loss": 0.033101629465818405, "terrain_level_mean": 3.22705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9996323585510254, 0.9994045495986938, 2.9973790645599365]} {"step": 45360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45360, "total_transitions": 185794560, "num_steps_per_env": 1, "wm_loss": 0.3912848234176636, "actor_loss": -8.712080001831055, "critic_loss": 0.021213693544268608, "reward": 0.07082940638065338, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2500751316547394, 0.15712934732437134, 0.25375157594680786], "policy_updates": 45260, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9495.160354822001, "contact_bce": 0.30962398648262024, "contact_force_loss": 0.03182464838027954, "terrain_level_mean": 3.2275390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9962677955627441, 0.9994045495986938, 2.9973790645599365]} {"step": 45370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45370, "total_transitions": 185835520, "num_steps_per_env": 1, "wm_loss": 0.419918030500412, "actor_loss": -8.772907257080078, "critic_loss": 0.031577181071043015, "reward": 0.07049375027418137, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2489974945783615, 0.15962448716163635, 0.2571307122707367], "policy_updates": 45270, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9498.678954993, "contact_bce": 0.3130773603916168, "contact_force_loss": 0.03215784579515457, "terrain_level_mean": 3.229248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9962677955627441, 0.9994045495986938, 2.9973790645599365]} {"step": 45380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45380, "total_transitions": 185876480, "num_steps_per_env": 1, "wm_loss": 0.4079113006591797, "actor_loss": -8.790824890136719, "critic_loss": 0.02693324163556099, "reward": 0.07014048099517822, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2533639669418335, 0.1605755239725113, 0.25656840205192566], "policy_updates": 45280, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9502.205332119, "contact_bce": 0.31184855103492737, "contact_force_loss": 0.03222370520234108, "terrain_level_mean": 3.228515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9945136308670044, 0.9994045495986938, 2.9973790645599365]} {"step": 45390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45390, "total_transitions": 185917440, "num_steps_per_env": 1, "wm_loss": 0.3954682946205139, "actor_loss": -8.725397109985352, "critic_loss": 0.038371700793504715, "reward": 0.07042767852544785, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2538559138774872, 0.15928487479686737, 0.2566029131412506], "policy_updates": 45290, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9505.727377021001, "contact_bce": 0.30647820234298706, "contact_force_loss": 0.03219012916088104, "terrain_level_mean": 3.228271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9945136308670044, 0.9994045495986938, 2.9973790645599365]} {"step": 45400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45400, "total_transitions": 185958400, "num_steps_per_env": 1, "wm_loss": 0.4038675129413605, "actor_loss": -8.704891204833984, "critic_loss": 0.030115211382508278, "reward": 0.07010822743177414, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25299733877182007, 0.15701231360435486, 0.25923797488212585], "policy_updates": 45300, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9509.242245286001, "contact_bce": 0.30714431405067444, "contact_force_loss": 0.031889043748378754, "terrain_level_mean": 3.228271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9945136308670044, 0.9994045495986938, 2.9973790645599365]} {"step": 45410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45410, "total_transitions": 185999360, "num_steps_per_env": 1, "wm_loss": 0.40029430389404297, "actor_loss": -8.722911834716797, "critic_loss": 0.04220057651400566, "reward": 0.07015914469957352, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25581684708595276, 0.16055423021316528, 0.2516886591911316], "policy_updates": 45310, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9512.770209791, "contact_bce": 0.31179213523864746, "contact_force_loss": 0.03313766047358513, "terrain_level_mean": 3.227783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9945136308670044, 0.9994045495986938, 2.9973790645599365]} {"step": 45420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45420, "total_transitions": 186040320, "num_steps_per_env": 1, "wm_loss": 0.3898714482784271, "actor_loss": -8.747899055480957, "critic_loss": 0.030394170433282852, "reward": 0.07035545259714127, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24962081015110016, 0.16062785685062408, 0.24805374443531036], "policy_updates": 45320, "skipped_updates": 0, "invalid_env_resets": 94, "elapsed_s": 9516.293856229, "contact_bce": 0.30875110626220703, "contact_force_loss": 0.032303787767887115, "terrain_level_mean": 3.227783203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9945136308670044, 0.9994045495986938, 2.9973790645599365]} RECOVERY reset 1 invalid environments; first IDs=[495] {"step": 45430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45430, "total_transitions": 186081280, "num_steps_per_env": 1, "wm_loss": 0.39612388610839844, "actor_loss": -8.740694046020508, "critic_loss": 0.02705371379852295, "reward": 0.07046423107385635, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2456636279821396, 0.1598547250032425, 0.25633227825164795], "policy_updates": 45330, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9519.829478442001, "contact_bce": 0.3102859556674957, "contact_force_loss": 0.03234969079494476, "terrain_level_mean": 3.230224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9945136308670044, 0.9994045495986938, 2.9973790645599365]} {"step": 45440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45440, "total_transitions": 186122240, "num_steps_per_env": 1, "wm_loss": 0.3985084593296051, "actor_loss": -8.737039566040039, "critic_loss": 0.026847360655665398, "reward": 0.07060440629720688, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24371297657489777, 0.15928997099399567, 0.25323814153671265], "policy_updates": 45340, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9523.350125778, "contact_bce": 0.3077355623245239, "contact_force_loss": 0.032220471650362015, "terrain_level_mean": 3.23046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9948899745941162, 0.9988149404525757, 2.9973790645599365]} {"step": 45450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45450, "total_transitions": 186163200, "num_steps_per_env": 1, "wm_loss": 0.41577500104904175, "actor_loss": -8.735649108886719, "critic_loss": 0.021318156272172928, "reward": 0.07069669663906097, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24724024534225464, 0.1566631942987442, 0.25220611691474915], "policy_updates": 45350, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9526.869069358001, "contact_bce": 0.3084227442741394, "contact_force_loss": 0.03292936086654663, "terrain_level_mean": 3.230712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9948899745941162, 0.9988149404525757, 2.9973790645599365]} {"step": 45460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45460, "total_transitions": 186204160, "num_steps_per_env": 1, "wm_loss": 0.40728285908699036, "actor_loss": -8.722378730773926, "critic_loss": 0.033978451043367386, "reward": 0.07109307497739792, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24639198184013367, 0.15419110655784607, 0.255531370639801], "policy_updates": 45360, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9530.393410855, "contact_bce": 0.30652594566345215, "contact_force_loss": 0.03175907954573631, "terrain_level_mean": 3.231201171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45470, "total_transitions": 186245120, "num_steps_per_env": 1, "wm_loss": 0.4112936854362488, "actor_loss": -8.727103233337402, "critic_loss": 0.0313524454832077, "reward": 0.07044165581464767, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2507858872413635, 0.1549958437681198, 0.25577840209007263], "policy_updates": 45370, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9533.917220507, "contact_bce": 0.3130579888820648, "contact_force_loss": 0.03191595897078514, "terrain_level_mean": 3.2314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45480, "total_transitions": 186286080, "num_steps_per_env": 1, "wm_loss": 0.38755807280540466, "actor_loss": -8.762378692626953, "critic_loss": 0.021607328206300735, "reward": 0.06978162378072739, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2551882266998291, 0.15666623413562775, 0.25645312666893005], "policy_updates": 45380, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9537.427690783, "contact_bce": 0.3120008409023285, "contact_force_loss": 0.0324878953397274, "terrain_level_mean": 3.230712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45490, "total_transitions": 186327040, "num_steps_per_env": 1, "wm_loss": 0.3887140154838562, "actor_loss": -8.756227493286133, "critic_loss": 0.03351372480392456, "reward": 0.0701032355427742, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25243905186653137, 0.153847798705101, 0.2530970275402069], "policy_updates": 45390, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9540.935053981, "contact_bce": 0.306789755821228, "contact_force_loss": 0.03173355013132095, "terrain_level_mean": 3.230712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45500, "total_transitions": 186368000, "num_steps_per_env": 1, "wm_loss": 0.40906408429145813, "actor_loss": -8.708171844482422, "critic_loss": 0.032360613346099854, "reward": 0.07052270323038101, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24626070261001587, 0.15417660772800446, 0.25500622391700745], "policy_updates": 45400, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9544.438313036, "contact_bce": 0.3092561662197113, "contact_force_loss": 0.03171825036406517, "terrain_level_mean": 3.2294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45510, "total_transitions": 186408960, "num_steps_per_env": 1, "wm_loss": 0.37736642360687256, "actor_loss": -8.695417404174805, "critic_loss": 0.02686048485338688, "reward": 0.07103516161441803, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24439553916454315, 0.15440452098846436, 0.25305500626564026], "policy_updates": 45410, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9547.972455465, "contact_bce": 0.31269699335098267, "contact_force_loss": 0.0314539298415184, "terrain_level_mean": 3.23046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45520, "total_transitions": 186449920, "num_steps_per_env": 1, "wm_loss": 0.43647652864456177, "actor_loss": -8.750970840454102, "critic_loss": 0.028723597526550293, "reward": 0.07107935845851898, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24685995280742645, 0.15452587604522705, 0.25589779019355774], "policy_updates": 45420, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9551.737507886, "contact_bce": 0.3157205879688263, "contact_force_loss": 0.0333842970430851, "terrain_level_mean": 3.23095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45530, "total_transitions": 186490880, "num_steps_per_env": 1, "wm_loss": 0.3967209458351135, "actor_loss": -8.706045150756836, "critic_loss": 0.03359493613243103, "reward": 0.07041018456220627, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24639633297920227, 0.15652374923229218, 0.25615808367729187], "policy_updates": 45430, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9555.288219793001, "contact_bce": 0.30775687098503113, "contact_force_loss": 0.03145813196897507, "terrain_level_mean": 3.22998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9948899745941162, 0.9989800453186035, 2.9973790645599365]} {"step": 45540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45540, "total_transitions": 186531840, "num_steps_per_env": 1, "wm_loss": 0.4145929217338562, "actor_loss": -8.703287124633789, "critic_loss": 0.023146988824009895, "reward": 0.07026106119155884, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24943868815898895, 0.15506835281848907, 0.25215578079223633], "policy_updates": 45440, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9558.827900477001, "contact_bce": 0.3124823272228241, "contact_force_loss": 0.03234891593456268, "terrain_level_mean": 3.230224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330078125, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.9973790645599365]} {"step": 45550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45550, "total_transitions": 186572800, "num_steps_per_env": 1, "wm_loss": 0.4192759394645691, "actor_loss": -8.754271507263184, "critic_loss": 0.02060299925506115, "reward": 0.07074463367462158, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2487071007490158, 0.15323734283447266, 0.24623803794384003], "policy_updates": 45450, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9562.341216197, "contact_bce": 0.3171400725841522, "contact_force_loss": 0.032503820955753326, "terrain_level_mean": 3.230224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.9973790645599365]} {"step": 45560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45560, "total_transitions": 186613760, "num_steps_per_env": 1, "wm_loss": 0.43683651089668274, "actor_loss": -8.745121002197266, "critic_loss": 0.02431335859000683, "reward": 0.07057778537273407, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2461182028055191, 0.15072840452194214, 0.2493240237236023], "policy_updates": 45460, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9565.852757096001, "contact_bce": 0.3145923912525177, "contact_force_loss": 0.0332520566880703, "terrain_level_mean": 3.22998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333740234375, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.9973790645599365]} {"step": 45570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45570, "total_transitions": 186654720, "num_steps_per_env": 1, "wm_loss": 0.4347347915172577, "actor_loss": -8.76069450378418, "critic_loss": 0.026392323896288872, "reward": 0.0702112466096878, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24930265545845032, 0.14906105399131775, 0.2537352740764618], "policy_updates": 45470, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9569.358885346, "contact_bce": 0.31334593892097473, "contact_force_loss": 0.03360024467110634, "terrain_level_mean": 3.229736328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333984375, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.9973790645599365]} {"step": 45580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45580, "total_transitions": 186695680, "num_steps_per_env": 1, "wm_loss": 0.3981357514858246, "actor_loss": -8.757732391357422, "critic_loss": 0.02515627257525921, "reward": 0.06989020854234695, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2542148232460022, 0.1496240496635437, 0.25109103322029114], "policy_updates": 45480, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9572.876618569, "contact_bce": 0.30900123715400696, "contact_force_loss": 0.03296548128128052, "terrain_level_mean": 3.22998046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.329833984375, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.9973790645599365]} {"step": 45590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45590, "total_transitions": 186736640, "num_steps_per_env": 1, "wm_loss": 0.40447959303855896, "actor_loss": -8.723177909851074, "critic_loss": 0.028369426727294922, "reward": 0.07007347792387009, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2545101046562195, 0.14876942336559296, 0.24826310575008392], "policy_updates": 45490, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9576.38518656, "contact_bce": 0.3064113259315491, "contact_force_loss": 0.031322404742240906, "terrain_level_mean": 3.231689453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331787109375, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.9973790645599365]} {"step": 45600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45600, "total_transitions": 186777600, "num_steps_per_env": 1, "wm_loss": 0.4276731610298157, "actor_loss": -8.751051902770996, "critic_loss": 0.017527461051940918, "reward": 0.07027500122785568, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2522623538970947, 0.15154431760311127, 0.25138720870018005], "policy_updates": 45500, "skipped_updates": 0, "invalid_env_resets": 95, "elapsed_s": 9579.903387645001, "contact_bce": 0.3098510801792145, "contact_force_loss": 0.0331711620092392, "terrain_level_mean": 3.230712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.9973790645599365]} RECOVERY reset 1 invalid environments; first IDs=[1276] {"step": 45610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45610, "total_transitions": 186818560, "num_steps_per_env": 1, "wm_loss": 0.39471185207366943, "actor_loss": -8.770989418029785, "critic_loss": 0.02378327213227749, "reward": 0.07034336030483246, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24925054609775543, 0.1527353823184967, 0.2549574077129364], "policy_updates": 45510, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9583.43806563, "contact_bce": 0.30881887674331665, "contact_force_loss": 0.03123726136982441, "terrain_level_mean": 3.23046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.333251953125, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.999094247817993]} {"step": 45620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45620, "total_transitions": 186859520, "num_steps_per_env": 1, "wm_loss": 0.40600594878196716, "actor_loss": -8.711078643798828, "critic_loss": 0.02218008227646351, "reward": 0.07073985040187836, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24416503310203552, 0.14948049187660217, 0.25422877073287964], "policy_updates": 45520, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9586.947111301, "contact_bce": 0.3143250048160553, "contact_force_loss": 0.0326814204454422, "terrain_level_mean": 3.230224609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.999094247817993]} {"step": 45630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45630, "total_transitions": 186900480, "num_steps_per_env": 1, "wm_loss": 0.41752079129219055, "actor_loss": -8.71071720123291, "critic_loss": 0.023731306195259094, "reward": 0.07082893699407578, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24567604064941406, 0.1494273543357849, 0.24976646900177002], "policy_updates": 45530, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9590.458275755, "contact_bce": 0.3105567991733551, "contact_force_loss": 0.031924769282341, "terrain_level_mean": 3.230712890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3349609375, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.999094247817993]} {"step": 45640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45640, "total_transitions": 186941440, "num_steps_per_env": 1, "wm_loss": 0.4033114016056061, "actor_loss": -8.73953628540039, "critic_loss": 0.021680599078536034, "reward": 0.07107362151145935, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24809575080871582, 0.14920437335968018, 0.2496715486049652], "policy_updates": 45540, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9593.970363386, "contact_bce": 0.31083670258522034, "contact_force_loss": 0.03231588006019592, "terrain_level_mean": 3.2314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.999094247817993]} {"step": 45650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45650, "total_transitions": 186982400, "num_steps_per_env": 1, "wm_loss": 0.43174266815185547, "actor_loss": -8.763384819030762, "critic_loss": 0.019527781754732132, "reward": 0.07111843675374985, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2485499083995819, 0.15169677138328552, 0.2504236102104187], "policy_updates": 45550, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9597.471234806, "contact_bce": 0.31657150387763977, "contact_force_loss": 0.033728718757629395, "terrain_level_mean": 3.23046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9948899745941162, 0.9997014999389648, 2.999094247817993]} {"step": 45660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45660, "total_transitions": 187023360, "num_steps_per_env": 1, "wm_loss": 0.4021676480770111, "actor_loss": -8.732004165649414, "critic_loss": 0.025773832574486732, "reward": 0.0709189772605896, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2494560182094574, 0.15193834900856018, 0.2487933486700058], "policy_updates": 45560, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9600.974926494, "contact_bce": 0.30781906843185425, "contact_force_loss": 0.03111926279962063, "terrain_level_mean": 3.23095703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9911036491394043, 0.9997014999389648, 2.999094247817993]} {"step": 45670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45670, "total_transitions": 187064320, "num_steps_per_env": 1, "wm_loss": 0.39743873476982117, "actor_loss": -8.711177825927734, "critic_loss": 0.025982141494750977, "reward": 0.07085307687520981, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2498704195022583, 0.15383948385715485, 0.24887022376060486], "policy_updates": 45570, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9604.489013052, "contact_bce": 0.3111419975757599, "contact_force_loss": 0.031951457262039185, "terrain_level_mean": 3.23193359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.9922006130218506, 0.9997014999389648, 2.999094247817993]} {"step": 45680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45680, "total_transitions": 187105280, "num_steps_per_env": 1, "wm_loss": 0.4327645003795624, "actor_loss": -8.760780334472656, "critic_loss": 0.019126417115330696, "reward": 0.070564404129982, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24830712378025055, 0.15460728108882904, 0.2503899037837982], "policy_updates": 45580, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9607.991757244, "contact_bce": 0.3093183934688568, "contact_force_loss": 0.032037753611803055, "terrain_level_mean": 3.23388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9922006130218506, 0.9997014999389648, 2.999094247817993]} {"step": 45690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45690, "total_transitions": 187146240, "num_steps_per_env": 1, "wm_loss": 0.41443103551864624, "actor_loss": -8.735445022583008, "critic_loss": 0.029217397794127464, "reward": 0.07078588753938675, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24926865100860596, 0.15550853312015533, 0.25292810797691345], "policy_updates": 45590, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9611.503133969001, "contact_bce": 0.30464789271354675, "contact_force_loss": 0.0320790559053421, "terrain_level_mean": 3.23388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9922006130218506, 0.9997014999389648, 2.999094247817993]} {"step": 45700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45700, "total_transitions": 187187200, "num_steps_per_env": 1, "wm_loss": 0.41796210408210754, "actor_loss": -8.677130699157715, "critic_loss": 0.03205820173025131, "reward": 0.07098207622766495, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25215041637420654, 0.15476767718791962, 0.2500631809234619], "policy_updates": 45600, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9615.005504052, "contact_bce": 0.31372973322868347, "contact_force_loss": 0.03280322998762131, "terrain_level_mean": 3.2333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9922006130218506, 0.9997014999389648, 2.999094247817993]} {"step": 45710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45710, "total_transitions": 187228160, "num_steps_per_env": 1, "wm_loss": 0.38625743985176086, "actor_loss": -8.688682556152344, "critic_loss": 0.031610798090696335, "reward": 0.07082199305295944, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2539735436439514, 0.15362492203712463, 0.2484511137008667], "policy_updates": 45610, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9618.510900315001, "contact_bce": 0.30174097418785095, "contact_force_loss": 0.03082234598696232, "terrain_level_mean": 3.23388671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9922006130218506, 0.9997014999389648, 2.999094247817993]} {"step": 45720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45720, "total_transitions": 187269120, "num_steps_per_env": 1, "wm_loss": 0.4284864068031311, "actor_loss": -8.711158752441406, "critic_loss": 0.029991013929247856, "reward": 0.07111995667219162, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24727268517017365, 0.15280522406101227, 0.24926497042179108], "policy_updates": 45620, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9622.016012306001, "contact_bce": 0.31608814001083374, "contact_force_loss": 0.03241205960512161, "terrain_level_mean": 3.235107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9922006130218506, 0.9997014999389648, 2.999094247817993]} {"step": 45730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45730, "total_transitions": 187310080, "num_steps_per_env": 1, "wm_loss": 0.4071308970451355, "actor_loss": -8.755499839782715, "critic_loss": 0.02607153169810772, "reward": 0.07120873034000397, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2503405809402466, 0.15619704127311707, 0.2494928240776062], "policy_updates": 45630, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9625.516931544, "contact_bce": 0.30980902910232544, "contact_force_loss": 0.032642070204019547, "terrain_level_mean": 3.23486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9950820207595825, 0.9997014999389648, 2.999094247817993]} {"step": 45740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45740, "total_transitions": 187351040, "num_steps_per_env": 1, "wm_loss": 0.3917127549648285, "actor_loss": -8.72831916809082, "critic_loss": 0.02441498264670372, "reward": 0.07104510813951492, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2512647211551666, 0.15848132967948914, 0.25013303756713867], "policy_updates": 45640, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9629.02742195, "contact_bce": 0.3107049763202667, "contact_force_loss": 0.03260257840156555, "terrain_level_mean": 3.23486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9950820207595825, 0.9997014999389648, 2.999094247817993]} {"step": 45750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45750, "total_transitions": 187392000, "num_steps_per_env": 1, "wm_loss": 0.420112669467926, "actor_loss": -8.72203254699707, "critic_loss": 0.03705750033259392, "reward": 0.07100408524274826, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24998749792575836, 0.15754063427448273, 0.24804651737213135], "policy_updates": 45650, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9632.543868857001, "contact_bce": 0.3091767132282257, "contact_force_loss": 0.031143546104431152, "terrain_level_mean": 3.234619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9963502883911133, 0.9997014999389648, 2.9994685649871826]} {"step": 45760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45760, "total_transitions": 187432960, "num_steps_per_env": 1, "wm_loss": 0.4203798770904541, "actor_loss": -8.705246925354004, "critic_loss": 0.02047908306121826, "reward": 0.07054188847541809, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2504291832447052, 0.15859545767307281, 0.25052204728126526], "policy_updates": 45660, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9636.059862349, "contact_bce": 0.31321248412132263, "contact_force_loss": 0.03297792747616768, "terrain_level_mean": 3.234130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9963502883911133, 0.9997014999389648, 2.9994685649871826]} {"step": 45770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45770, "total_transitions": 187473920, "num_steps_per_env": 1, "wm_loss": 0.41663894057273865, "actor_loss": -8.671207427978516, "critic_loss": 0.039394497871398926, "reward": 0.07061883807182312, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2469618171453476, 0.15721915662288666, 0.2511048913002014], "policy_updates": 45670, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9639.568903119001, "contact_bce": 0.3153780400753021, "contact_force_loss": 0.031601883471012115, "terrain_level_mean": 3.2333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9963502883911133, 0.9997014999389648, 2.9994685649871826]} {"step": 45780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45780, "total_transitions": 187514880, "num_steps_per_env": 1, "wm_loss": 0.4591549336910248, "actor_loss": -8.73910140991211, "critic_loss": 0.02231377176940441, "reward": 0.07117155194282532, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2461792230606079, 0.15688112378120422, 0.2509935796260834], "policy_updates": 45680, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9643.076642856, "contact_bce": 0.3131263554096222, "contact_force_loss": 0.03288234397768974, "terrain_level_mean": 3.2333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9963502883911133, 0.9997014999389648, 2.9994685649871826]} {"step": 45790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45790, "total_transitions": 187555840, "num_steps_per_env": 1, "wm_loss": 0.41197896003723145, "actor_loss": -8.738414764404297, "critic_loss": 0.029530245810747147, "reward": 0.07188593596220016, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2459414154291153, 0.1571376770734787, 0.24125441908836365], "policy_updates": 45690, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9646.577550215, "contact_bce": 0.31138864159584045, "contact_force_loss": 0.03305170685052872, "terrain_level_mean": 3.234619140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9963502883911133, 0.9997014999389648, 2.9994685649871826]} {"step": 45800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45800, "total_transitions": 187596800, "num_steps_per_env": 1, "wm_loss": 0.41612499952316284, "actor_loss": -8.73063850402832, "critic_loss": 0.02716240845620632, "reward": 0.07132014632225037, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24352853000164032, 0.15802474319934845, 0.24703072011470795], "policy_updates": 45700, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9650.095176242, "contact_bce": 0.31047195196151733, "contact_force_loss": 0.03191487491130829, "terrain_level_mean": 3.234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9963502883911133, 0.9997014999389648, 2.999094247817993]} {"step": 45810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45810, "total_transitions": 187637760, "num_steps_per_env": 1, "wm_loss": 0.4183228015899658, "actor_loss": -8.657130241394043, "critic_loss": 0.03178448975086212, "reward": 0.0714176818728447, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24400492012500763, 0.15819106996059418, 0.2485227733850479], "policy_updates": 45710, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9653.605437971, "contact_bce": 0.31166619062423706, "contact_force_loss": 0.03249136358499527, "terrain_level_mean": 3.235107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9963502883911133, 0.9997014999389648, 2.999094247817993]} {"step": 45820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45820, "total_transitions": 187678720, "num_steps_per_env": 1, "wm_loss": 0.4037933945655823, "actor_loss": -8.685155868530273, "critic_loss": 0.026489054784178734, "reward": 0.07077324390411377, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24474787712097168, 0.15761277079582214, 0.2489950805902481], "policy_updates": 45720, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9657.129129098, "contact_bce": 0.30923184752464294, "contact_force_loss": 0.03170985355973244, "terrain_level_mean": 3.23486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.999094247817993]} {"step": 45830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45830, "total_transitions": 187719680, "num_steps_per_env": 1, "wm_loss": 0.45617446303367615, "actor_loss": -8.782297134399414, "critic_loss": 0.02259710431098938, "reward": 0.07090939581394196, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2462121844291687, 0.15640972554683685, 0.24984462559223175], "policy_updates": 45730, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9660.652861628001, "contact_bce": 0.3093617558479309, "contact_force_loss": 0.0328109934926033, "terrain_level_mean": 3.2353515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.999094247817993]} {"step": 45840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45840, "total_transitions": 187760640, "num_steps_per_env": 1, "wm_loss": 0.4016162157058716, "actor_loss": -8.722976684570312, "critic_loss": 0.02417479269206524, "reward": 0.07094863802194595, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24342088401317596, 0.15682128071784973, 0.2505381107330322], "policy_updates": 45740, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9664.175735777, "contact_bce": 0.3078114986419678, "contact_force_loss": 0.03154212608933449, "terrain_level_mean": 3.2353515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.9893527030944824]} {"step": 45850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45850, "total_transitions": 187801600, "num_steps_per_env": 1, "wm_loss": 0.4107755720615387, "actor_loss": -8.742233276367188, "critic_loss": 0.025596005842089653, "reward": 0.07128971070051193, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2390439361333847, 0.15887682139873505, 0.25159886479377747], "policy_updates": 45750, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9667.699542376, "contact_bce": 0.31297096610069275, "contact_force_loss": 0.03215270861983299, "terrain_level_mean": 3.23583984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.9893527030944824]} {"step": 45860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45860, "total_transitions": 187842560, "num_steps_per_env": 1, "wm_loss": 0.4095429480075836, "actor_loss": -8.702896118164062, "critic_loss": 0.0356280580163002, "reward": 0.07072142511606216, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24365904927253723, 0.15895050764083862, 0.2553555965423584], "policy_updates": 45760, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9671.221249455, "contact_bce": 0.31253471970558167, "contact_force_loss": 0.03213910013437271, "terrain_level_mean": 3.235595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.9893527030944824]} {"step": 45870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45870, "total_transitions": 187883520, "num_steps_per_env": 1, "wm_loss": 0.4338964521884918, "actor_loss": -8.725712776184082, "critic_loss": 0.025201022624969482, "reward": 0.07122691720724106, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24682191014289856, 0.15637655556201935, 0.250622421503067], "policy_updates": 45770, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9674.737132371001, "contact_bce": 0.31630939245224, "contact_force_loss": 0.03318391740322113, "terrain_level_mean": 3.236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.9983761310577393]} {"step": 45880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45880, "total_transitions": 187924480, "num_steps_per_env": 1, "wm_loss": 0.4059390723705292, "actor_loss": -8.729952812194824, "critic_loss": 0.02600201405584812, "reward": 0.07101964205503464, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2477361112833023, 0.1577065885066986, 0.250535249710083], "policy_updates": 45780, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9678.255479769, "contact_bce": 0.3065289258956909, "contact_force_loss": 0.03212278336286545, "terrain_level_mean": 3.23681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.9983761310577393]} {"step": 45890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45890, "total_transitions": 187965440, "num_steps_per_env": 1, "wm_loss": 0.4169553518295288, "actor_loss": -8.680694580078125, "critic_loss": 0.03161374852061272, "reward": 0.07121757417917252, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24623790383338928, 0.15881945192813873, 0.25024545192718506], "policy_updates": 45790, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9681.77395088, "contact_bce": 0.3088958263397217, "contact_force_loss": 0.031786929816007614, "terrain_level_mean": 3.236572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9963502883911133, 0.9984139204025269, 2.9983761310577393]} {"step": 45900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45900, "total_transitions": 188006400, "num_steps_per_env": 1, "wm_loss": 0.392974317073822, "actor_loss": -8.749382019042969, "critic_loss": 0.03369416669011116, "reward": 0.07111158221960068, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25097012519836426, 0.15879209339618683, 0.25322815775871277], "policy_updates": 45800, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9685.292639573001, "contact_bce": 0.30892160534858704, "contact_force_loss": 0.03235480561852455, "terrain_level_mean": 3.2353515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9963502883911133, 0.9995227456092834, 2.9983761310577393]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_045900.mp4 {"step": 45910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45910, "total_transitions": 188047360, "num_steps_per_env": 1, "wm_loss": 0.41563209891319275, "actor_loss": -8.720590591430664, "critic_loss": 0.028115540742874146, "reward": 0.07090326398611069, "falls": 0, "interval_steps": 10, "velocity_mae": [0.2517927289009094, 0.15970510244369507, 0.2563648819923401], "policy_updates": 45810, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9694.566688859, "contact_bce": 0.31272196769714355, "contact_force_loss": 0.03193271532654762, "terrain_level_mean": 3.236083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9963502883911133, 0.9995227456092834, 2.9983761310577393]} {"step": 45920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45920, "total_transitions": 188088320, "num_steps_per_env": 1, "wm_loss": 0.42140573263168335, "actor_loss": -8.727273941040039, "critic_loss": 0.022112909704446793, "reward": 0.07077784836292267, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2508995234966278, 0.15902170538902283, 0.25866180658340454], "policy_updates": 45820, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9698.080730804, "contact_bce": 0.310712605714798, "contact_force_loss": 0.03222111985087395, "terrain_level_mean": 3.237060546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9963502883911133, 0.9995227456092834, 2.9983761310577393]} {"step": 45930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45930, "total_transitions": 188129280, "num_steps_per_env": 1, "wm_loss": 0.41392385959625244, "actor_loss": -8.70077133178711, "critic_loss": 0.022049156948924065, "reward": 0.07095487415790558, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2523655295372009, 0.15809205174446106, 0.2566864490509033], "policy_updates": 45830, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9701.591891822001, "contact_bce": 0.31211259961128235, "contact_force_loss": 0.032221388071775436, "terrain_level_mean": 3.236083984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9963502883911133, 0.9995227456092834, 2.9983761310577393]} {"step": 45940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45940, "total_transitions": 188170240, "num_steps_per_env": 1, "wm_loss": 0.4112427532672882, "actor_loss": -8.704550743103027, "critic_loss": 0.03195171430706978, "reward": 0.07106000185012817, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2470121830701828, 0.15762054920196533, 0.24997872114181519], "policy_updates": 45840, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9705.105465494, "contact_bce": 0.3089663088321686, "contact_force_loss": 0.03262683004140854, "terrain_level_mean": 3.236572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9928534030914307, 0.9995227456092834, 2.9983761310577393]} {"step": 45950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45950, "total_transitions": 188211200, "num_steps_per_env": 1, "wm_loss": 0.42643722891807556, "actor_loss": -8.711203575134277, "critic_loss": 0.019578343257308006, "reward": 0.07121165096759796, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24870680272579193, 0.1552310287952423, 0.253029465675354], "policy_updates": 45850, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9708.619109070001, "contact_bce": 0.30965447425842285, "contact_force_loss": 0.032183751463890076, "terrain_level_mean": 3.236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9928534030914307, 0.9995227456092834, 2.9983761310577393]} {"step": 45960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45960, "total_transitions": 188252160, "num_steps_per_env": 1, "wm_loss": 0.40770256519317627, "actor_loss": -8.701765060424805, "critic_loss": 0.022714901715517044, "reward": 0.07142937183380127, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24551689624786377, 0.1565428078174591, 0.251947283744812], "policy_updates": 45860, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9712.134585560001, "contact_bce": 0.31141793727874756, "contact_force_loss": 0.03146081417798996, "terrain_level_mean": 3.235595703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9928534030914307, 0.9995227456092834, 2.9983761310577393]} {"step": 45970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45970, "total_transitions": 188293120, "num_steps_per_env": 1, "wm_loss": 0.4326215982437134, "actor_loss": -8.70988655090332, "critic_loss": 0.027072742581367493, "reward": 0.07122147083282471, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24319501221179962, 0.1562306433916092, 0.2534046769142151], "policy_updates": 45870, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9715.653984494, "contact_bce": 0.3080420196056366, "contact_force_loss": 0.03172428160905838, "terrain_level_mean": 3.235107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9928534030914307, 0.9995227456092834, 2.9983761310577393]} {"step": 45980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45980, "total_transitions": 188334080, "num_steps_per_env": 1, "wm_loss": 0.4241035282611847, "actor_loss": -8.732673645019531, "critic_loss": 0.02248959057033062, "reward": 0.07085885852575302, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24728673696517944, 0.15567022562026978, 0.25283318758010864], "policy_updates": 45880, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9719.167011443, "contact_bce": 0.31550005078315735, "contact_force_loss": 0.03230497986078262, "terrain_level_mean": 3.234130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9929838180541992, 0.9995227456092834, 2.9983761310577393]} {"step": 45990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 45990, "total_transitions": 188375040, "num_steps_per_env": 1, "wm_loss": 0.4204692244529724, "actor_loss": -8.707176208496094, "critic_loss": 0.019855208694934845, "reward": 0.07128038257360458, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25001615285873413, 0.15892411768436432, 0.25109386444091797], "policy_updates": 45890, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9722.684660957, "contact_bce": 0.30850842595100403, "contact_force_loss": 0.03238951787352562, "terrain_level_mean": 3.235107421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9944126605987549, 0.9995227456092834, 2.9983761310577393]} {"step": 46000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46000, "total_transitions": 188416000, "num_steps_per_env": 1, "wm_loss": 0.3806087076663971, "actor_loss": -8.736398696899414, "critic_loss": 0.02172468788921833, "reward": 0.07119589298963547, "falls": 10, "interval_steps": 10, "velocity_mae": [0.25179681181907654, 0.1570497304201126, 0.2530565857887268], "policy_updates": 45900, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9726.197269694001, "contact_bce": 0.30503082275390625, "contact_force_loss": 0.031213756650686264, "terrain_level_mean": 3.233642578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9944126605987549, 0.9995227456092834, 2.9983761310577393]} {"step": 46010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46010, "total_transitions": 188456960, "num_steps_per_env": 1, "wm_loss": 0.4270649254322052, "actor_loss": -8.695865631103516, "critic_loss": 0.024967560544610023, "reward": 0.07114268094301224, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24847686290740967, 0.15810073912143707, 0.25251302123069763], "policy_updates": 45910, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9729.733671874, "contact_bce": 0.31254756450653076, "contact_force_loss": 0.03226763382554054, "terrain_level_mean": 3.234130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33642578125, "command_abs_max": [1.9944126605987549, 0.9995227456092834, 2.9983761310577393]} {"step": 46020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46020, "total_transitions": 188497920, "num_steps_per_env": 1, "wm_loss": 0.3953254222869873, "actor_loss": -8.703910827636719, "critic_loss": 0.020978329703211784, "reward": 0.07121402025222778, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24799147248268127, 0.15705913305282593, 0.2562151253223419], "policy_updates": 45920, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9733.49805197, "contact_bce": 0.30721375346183777, "contact_force_loss": 0.031890787184238434, "terrain_level_mean": 3.23291015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9944126605987549, 0.9995227456092834, 2.9983761310577393]} {"step": 46030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46030, "total_transitions": 188538880, "num_steps_per_env": 1, "wm_loss": 0.41525283455848694, "actor_loss": -8.702837944030762, "critic_loss": 0.027950411662459373, "reward": 0.07127237319946289, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2513698935508728, 0.15741030871868134, 0.254084050655365], "policy_updates": 45930, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9737.013871642, "contact_bce": 0.3087245225906372, "contact_force_loss": 0.032606128603219986, "terrain_level_mean": 3.232666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9944126605987549, 0.9995227456092834, 2.9983761310577393]} {"step": 46040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46040, "total_transitions": 188579840, "num_steps_per_env": 1, "wm_loss": 0.44458457827568054, "actor_loss": -8.712039947509766, "critic_loss": 0.026910170912742615, "reward": 0.0709465891122818, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2552075982093811, 0.15642468631267548, 0.2556827962398529], "policy_updates": 45940, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9740.531419894001, "contact_bce": 0.3073555529117584, "contact_force_loss": 0.03213245049118996, "terrain_level_mean": 3.234130859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3359375, "command_abs_max": [1.9944126605987549, 0.9995227456092834, 2.9983761310577393]} {"step": 46050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46050, "total_transitions": 188620800, "num_steps_per_env": 1, "wm_loss": 0.4342733919620514, "actor_loss": -8.732769966125488, "critic_loss": 0.028393900021910667, "reward": 0.0710270032286644, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2523563504219055, 0.15474680066108704, 0.25334692001342773], "policy_updates": 45950, "skipped_updates": 0, "invalid_env_resets": 96, "elapsed_s": 9744.036165732, "contact_bce": 0.3141120970249176, "contact_force_loss": 0.03211423382163048, "terrain_level_mean": 3.233154296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} RECOVERY reset 1 invalid environments; first IDs=[1052] RECOVERY reset 1 invalid environments; first IDs=[1290] {"step": 46060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46060, "total_transitions": 188661760, "num_steps_per_env": 1, "wm_loss": 0.4100615978240967, "actor_loss": -8.753585815429688, "critic_loss": 0.022602643817663193, "reward": 0.07123362272977829, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2514883875846863, 0.15400736033916473, 0.2503725588321686], "policy_updates": 45960, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9747.577038606001, "contact_bce": 0.3098798096179962, "contact_force_loss": 0.03228459134697914, "terrain_level_mean": 3.2333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} {"step": 46070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46070, "total_transitions": 188702720, "num_steps_per_env": 1, "wm_loss": 0.4136156737804413, "actor_loss": -8.718725204467773, "critic_loss": 0.025664225220680237, "reward": 0.07097675651311874, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2539066672325134, 0.1551957130432129, 0.2546444535255432], "policy_updates": 45970, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9751.089677959, "contact_bce": 0.31055253744125366, "contact_force_loss": 0.03248777985572815, "terrain_level_mean": 3.234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33740234375, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} {"step": 46080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46080, "total_transitions": 188743680, "num_steps_per_env": 1, "wm_loss": 0.4359983503818512, "actor_loss": -8.680933952331543, "critic_loss": 0.02814132533967495, "reward": 0.07092162221670151, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2566932439804077, 0.15590493381023407, 0.25252458453178406], "policy_updates": 45980, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9754.596521627, "contact_bce": 0.31430137157440186, "contact_force_loss": 0.033904798328876495, "terrain_level_mean": 3.23486328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.334228515625, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} {"step": 46090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46090, "total_transitions": 188784640, "num_steps_per_env": 1, "wm_loss": 0.4168415069580078, "actor_loss": -8.723041534423828, "critic_loss": 0.02667193114757538, "reward": 0.07110174745321274, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25773122906684875, 0.155878946185112, 0.25478142499923706], "policy_updates": 45990, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9758.106599806, "contact_bce": 0.31358206272125244, "contact_force_loss": 0.032023508101701736, "terrain_level_mean": 3.23681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.335205078125, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} {"step": 46100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46100, "total_transitions": 188825600, "num_steps_per_env": 1, "wm_loss": 0.3904538154602051, "actor_loss": -8.749927520751953, "critic_loss": 0.03281142935156822, "reward": 0.07102461904287338, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25877320766448975, 0.1554710865020752, 0.25588512420654297], "policy_updates": 46000, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9761.622796564001, "contact_bce": 0.3120514452457428, "contact_force_loss": 0.03162684664130211, "terrain_level_mean": 3.238525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} {"step": 46110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46110, "total_transitions": 188866560, "num_steps_per_env": 1, "wm_loss": 0.41463446617126465, "actor_loss": -8.712751388549805, "critic_loss": 0.03320486471056938, "reward": 0.07099633663892746, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25709301233291626, 0.15560314059257507, 0.25261789560317993], "policy_updates": 46010, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9765.14137149, "contact_bce": 0.3099401891231537, "contact_force_loss": 0.03245479241013527, "terrain_level_mean": 3.23828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338134765625, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} {"step": 46120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46120, "total_transitions": 188907520, "num_steps_per_env": 1, "wm_loss": 0.41657814383506775, "actor_loss": -8.751386642456055, "critic_loss": 0.024959120899438858, "reward": 0.07077157497406006, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2585923671722412, 0.1567920595407486, 0.25217756628990173], "policy_updates": 46020, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9768.656483421, "contact_bce": 0.31277406215667725, "contact_force_loss": 0.03262234106659889, "terrain_level_mean": 3.23828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.997629165649414, 0.9995227456092834, 2.9983761310577393]} {"step": 46130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46130, "total_transitions": 188948480, "num_steps_per_env": 1, "wm_loss": 0.41083139181137085, "actor_loss": -8.69178295135498, "critic_loss": 0.0355709083378315, "reward": 0.07084010541439056, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2545568645000458, 0.15463456511497498, 0.25448864698410034], "policy_updates": 46030, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9772.178367779, "contact_bce": 0.30948206782341003, "contact_force_loss": 0.03163314238190651, "terrain_level_mean": 3.236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33935546875, "command_abs_max": [1.997629165649414, 0.9975836277008057, 2.9983761310577393]} {"step": 46140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46140, "total_transitions": 188989440, "num_steps_per_env": 1, "wm_loss": 0.4452242851257324, "actor_loss": -8.715446472167969, "critic_loss": 0.028126507997512817, "reward": 0.07049325853586197, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2508854866027832, 0.1557840257883072, 0.2527303099632263], "policy_updates": 46040, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9775.693947493, "contact_bce": 0.3202417492866516, "contact_force_loss": 0.03344063088297844, "terrain_level_mean": 3.236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.997629165649414, 0.9975836277008057, 2.9983761310577393]} {"step": 46150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46150, "total_transitions": 189030400, "num_steps_per_env": 1, "wm_loss": 0.42116719484329224, "actor_loss": -8.724916458129883, "critic_loss": 0.025655759498476982, "reward": 0.07026022672653198, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24977292120456696, 0.15698234736919403, 0.2543050944805145], "policy_updates": 46050, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9779.209762275, "contact_bce": 0.3100218176841736, "contact_force_loss": 0.03230906277894974, "terrain_level_mean": 3.236328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.997629165649414, 0.9975836277008057, 2.9983761310577393]} {"step": 46160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46160, "total_transitions": 189071360, "num_steps_per_env": 1, "wm_loss": 0.4073808491230011, "actor_loss": -8.73686408996582, "critic_loss": 0.022885635495185852, "reward": 0.0701712816953659, "falls": 3, "interval_steps": 10, "velocity_mae": [0.250488817691803, 0.15547621250152588, 0.2510320246219635], "policy_updates": 46060, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9782.727804053, "contact_bce": 0.3106549084186554, "contact_force_loss": 0.03183770552277565, "terrain_level_mean": 3.236572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.997629165649414, 0.9975836277008057, 2.9983761310577393]} {"step": 46170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46170, "total_transitions": 189112320, "num_steps_per_env": 1, "wm_loss": 0.4211711883544922, "actor_loss": -8.733627319335938, "critic_loss": 0.02301105670630932, "reward": 0.07038521766662598, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24942614138126373, 0.15643584728240967, 0.2547280788421631], "policy_updates": 46070, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9786.240667494001, "contact_bce": 0.30921661853790283, "contact_force_loss": 0.032163236290216446, "terrain_level_mean": 3.23681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.997629165649414, 0.9978099465370178, 2.9963579177856445]} {"step": 46180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46180, "total_transitions": 189153280, "num_steps_per_env": 1, "wm_loss": 0.4020223915576935, "actor_loss": -8.700702667236328, "critic_loss": 0.02155943401157856, "reward": 0.07006572932004929, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2519232928752899, 0.15774862468242645, 0.2553853988647461], "policy_updates": 46080, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9789.762630451001, "contact_bce": 0.3120179772377014, "contact_force_loss": 0.03321714326739311, "terrain_level_mean": 3.2373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.997629165649414, 0.9978099465370178, 2.9963579177856445]} {"step": 46190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46190, "total_transitions": 189194240, "num_steps_per_env": 1, "wm_loss": 0.3783016800880432, "actor_loss": -8.688507080078125, "critic_loss": 0.029081931337714195, "reward": 0.07044651359319687, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2526243329048157, 0.15680375695228577, 0.25301969051361084], "policy_updates": 46090, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9793.281359800001, "contact_bce": 0.3111554980278015, "contact_force_loss": 0.03208516910672188, "terrain_level_mean": 3.23681640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.997629165649414, 0.9978099465370178, 2.9963579177856445]} {"step": 46200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46200, "total_transitions": 189235200, "num_steps_per_env": 1, "wm_loss": 0.3990399241447449, "actor_loss": -8.79153060913086, "critic_loss": 0.0228870939463377, "reward": 0.07062666863203049, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2486993968486786, 0.15569883584976196, 0.2511381208896637], "policy_updates": 46100, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9796.792301765001, "contact_bce": 0.317121297121048, "contact_force_loss": 0.03306316211819649, "terrain_level_mean": 3.236572265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.9968667030334473, 0.9978099465370178, 2.9963579177856445]} {"step": 46210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46210, "total_transitions": 189276160, "num_steps_per_env": 1, "wm_loss": 0.39999744296073914, "actor_loss": -8.779529571533203, "critic_loss": 0.02305004373192787, "reward": 0.07109222561120987, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24385233223438263, 0.15496276319026947, 0.245625838637352], "policy_updates": 46110, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9800.311748559001, "contact_bce": 0.3067966103553772, "contact_force_loss": 0.03193771466612816, "terrain_level_mean": 3.237548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9968667030334473, 0.9978099465370178, 2.9963579177856445]} {"step": 46220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46220, "total_transitions": 189317120, "num_steps_per_env": 1, "wm_loss": 0.40565168857574463, "actor_loss": -8.711942672729492, "critic_loss": 0.02441956289112568, "reward": 0.0708547830581665, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24820572137832642, 0.15726083517074585, 0.25066304206848145], "policy_updates": 46120, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9803.827766001, "contact_bce": 0.31469210982322693, "contact_force_loss": 0.03271782770752907, "terrain_level_mean": 3.238037109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.9968667030334473, 0.9978099465370178, 2.9963579177856445]} {"step": 46230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46230, "total_transitions": 189358080, "num_steps_per_env": 1, "wm_loss": 0.45370540022850037, "actor_loss": -8.716328620910645, "critic_loss": 0.02664429321885109, "reward": 0.07058685272932053, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24786405265331268, 0.15891288220882416, 0.2588014602661133], "policy_updates": 46130, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9807.339157863, "contact_bce": 0.3158096671104431, "contact_force_loss": 0.03357063978910446, "terrain_level_mean": 3.23779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9968667030334473, 0.9978099465370178, 2.9963579177856445]} {"step": 46240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46240, "total_transitions": 189399040, "num_steps_per_env": 1, "wm_loss": 0.3927786946296692, "actor_loss": -8.688224792480469, "critic_loss": 0.024817315861582756, "reward": 0.07038746774196625, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24831169843673706, 0.15985742211341858, 0.2588459253311157], "policy_updates": 46140, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9810.854879343, "contact_bce": 0.31298989057540894, "contact_force_loss": 0.031148700043559074, "terrain_level_mean": 3.23779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9968667030334473, 0.9978099465370178, 2.9963579177856445]} {"step": 46250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46250, "total_transitions": 189440000, "num_steps_per_env": 1, "wm_loss": 0.386111319065094, "actor_loss": -8.721883773803711, "critic_loss": 0.022672085091471672, "reward": 0.07084330916404724, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24489091336727142, 0.15992115437984467, 0.2555968761444092], "policy_updates": 46150, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9814.373353866, "contact_bce": 0.3074764907360077, "contact_force_loss": 0.03087654709815979, "terrain_level_mean": 3.2373046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9973084926605225, 0.9978099465370178, 2.9963579177856445]} {"step": 46260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46260, "total_transitions": 189480960, "num_steps_per_env": 1, "wm_loss": 0.40992271900177, "actor_loss": -8.710737228393555, "critic_loss": 0.022344181314110756, "reward": 0.07058122009038925, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2472362518310547, 0.15876075625419617, 0.2603205740451813], "policy_updates": 46160, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9817.886772238, "contact_bce": 0.31001099944114685, "contact_force_loss": 0.031884048134088516, "terrain_level_mean": 3.237548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9973084926605225, 0.9981390833854675, 2.9994235038757324]} {"step": 46270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46270, "total_transitions": 189521920, "num_steps_per_env": 1, "wm_loss": 0.3970188498497009, "actor_loss": -8.733476638793945, "critic_loss": 0.021398846060037613, "reward": 0.0701407939195633, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2486787587404251, 0.15953297913074493, 0.2600209712982178], "policy_updates": 46170, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9821.401674622, "contact_bce": 0.3113498389720917, "contact_force_loss": 0.032474666833877563, "terrain_level_mean": 3.238525390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9973084926605225, 0.9981390833854675, 2.9994235038757324]} {"step": 46280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46280, "total_transitions": 189562880, "num_steps_per_env": 1, "wm_loss": 0.4048643410205841, "actor_loss": -8.679670333862305, "critic_loss": 0.040044691413640976, "reward": 0.07046312093734741, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24368537962436676, 0.1589272916316986, 0.2528209090232849], "policy_updates": 46180, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9824.919032884001, "contact_bce": 0.31613802909851074, "contact_force_loss": 0.03311533108353615, "terrain_level_mean": 3.23828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9973084926605225, 0.9981390833854675, 2.9994235038757324]} {"step": 46290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46290, "total_transitions": 189603840, "num_steps_per_env": 1, "wm_loss": 0.4170731008052826, "actor_loss": -8.671891212463379, "critic_loss": 0.030945200473070145, "reward": 0.07089196890592575, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24580861628055573, 0.15668116509914398, 0.2518608570098877], "policy_updates": 46190, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9828.434997082, "contact_bce": 0.31165024638175964, "contact_force_loss": 0.03189815580844879, "terrain_level_mean": 3.239013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9973084926605225, 0.9981390833854675, 2.9994235038757324]} {"step": 46300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46300, "total_transitions": 189644800, "num_steps_per_env": 1, "wm_loss": 0.4317910671234131, "actor_loss": -8.749862670898438, "critic_loss": 0.023347018286585808, "reward": 0.07034099102020264, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24758271872997284, 0.1565566211938858, 0.2534991502761841], "policy_updates": 46200, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9831.95665206, "contact_bce": 0.3065340518951416, "contact_force_loss": 0.03281822055578232, "terrain_level_mean": 3.239501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46310, "total_transitions": 189685760, "num_steps_per_env": 1, "wm_loss": 0.4097302556037903, "actor_loss": -8.68330192565918, "critic_loss": 0.02505510486662388, "reward": 0.07020501047372818, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24984654784202576, 0.1593477725982666, 0.252385675907135], "policy_updates": 46210, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9835.471516478001, "contact_bce": 0.3145822286605835, "contact_force_loss": 0.032066866755485535, "terrain_level_mean": 3.240478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46320, "total_transitions": 189726720, "num_steps_per_env": 1, "wm_loss": 0.3946634829044342, "actor_loss": -8.725921630859375, "critic_loss": 0.028074849396944046, "reward": 0.07043450325727463, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2506122887134552, 0.1552000492811203, 0.25469931960105896], "policy_updates": 46220, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9838.98992453, "contact_bce": 0.31035032868385315, "contact_force_loss": 0.03142654895782471, "terrain_level_mean": 3.239990234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46330, "total_transitions": 189767680, "num_steps_per_env": 1, "wm_loss": 0.4057002067565918, "actor_loss": -8.699089050292969, "critic_loss": 0.025728588923811913, "reward": 0.07051967829465866, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25301116704940796, 0.15771733224391937, 0.2528184652328491], "policy_updates": 46230, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9842.507428216, "contact_bce": 0.31142351031303406, "contact_force_loss": 0.032139766961336136, "terrain_level_mean": 3.239013671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46340, "total_transitions": 189808640, "num_steps_per_env": 1, "wm_loss": 0.42759397625923157, "actor_loss": -8.722715377807617, "critic_loss": 0.02719203196465969, "reward": 0.0710459053516388, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2490447610616684, 0.15828144550323486, 0.25241410732269287], "policy_updates": 46240, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9846.012102493001, "contact_bce": 0.3164619505405426, "contact_force_loss": 0.03236326575279236, "terrain_level_mean": 3.240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46350, "total_transitions": 189849600, "num_steps_per_env": 1, "wm_loss": 0.428692102432251, "actor_loss": -8.71654987335205, "critic_loss": 0.02773222327232361, "reward": 0.07058916240930557, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25086912512779236, 0.15784940123558044, 0.25375232100486755], "policy_updates": 46250, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9849.519019742, "contact_bce": 0.31582608819007874, "contact_force_loss": 0.03212249279022217, "terrain_level_mean": 3.241455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46360, "total_transitions": 189890560, "num_steps_per_env": 1, "wm_loss": 0.41565120220184326, "actor_loss": -8.763426780700684, "critic_loss": 0.030035002157092094, "reward": 0.07039349526166916, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24870827794075012, 0.15887707471847534, 0.2524753212928772], "policy_updates": 46260, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9853.028473451, "contact_bce": 0.31638088822364807, "contact_force_loss": 0.032601770013570786, "terrain_level_mean": 3.24072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46370, "total_transitions": 189931520, "num_steps_per_env": 1, "wm_loss": 0.4132099151611328, "actor_loss": -8.69942855834961, "critic_loss": 0.026759067550301552, "reward": 0.07058417052030563, "falls": 10, "interval_steps": 10, "velocity_mae": [0.246667742729187, 0.16144245862960815, 0.2517099380493164], "policy_updates": 46270, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9856.534454845001, "contact_bce": 0.3155362010002136, "contact_force_loss": 0.03243584558367729, "terrain_level_mean": 3.23876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9973084926605225, 0.9997045993804932, 2.9994235038757324]} {"step": 46380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46380, "total_transitions": 189972480, "num_steps_per_env": 1, "wm_loss": 0.4081457257270813, "actor_loss": -8.708747863769531, "critic_loss": 0.03622165322303772, "reward": 0.07074948400259018, "falls": 7, "interval_steps": 10, "velocity_mae": [0.247093066573143, 0.15892554819583893, 0.24929466843605042], "policy_updates": 46280, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9860.048147098001, "contact_bce": 0.31456083059310913, "contact_force_loss": 0.03256949037313461, "terrain_level_mean": 3.23876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46390, "total_transitions": 190013440, "num_steps_per_env": 1, "wm_loss": 0.406870573759079, "actor_loss": -8.727239608764648, "critic_loss": 0.025538189336657524, "reward": 0.07084595412015915, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2453448474407196, 0.15707612037658691, 0.25165650248527527], "policy_updates": 46290, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9863.561969240001, "contact_bce": 0.3132231831550598, "contact_force_loss": 0.03190014138817787, "terrain_level_mean": 3.23828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46400, "total_transitions": 190054400, "num_steps_per_env": 1, "wm_loss": 0.4309544861316681, "actor_loss": -8.713838577270508, "critic_loss": 0.030842024832963943, "reward": 0.07107754796743393, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24643929302692413, 0.1588493436574936, 0.25249144434928894], "policy_updates": 46300, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9867.071301123, "contact_bce": 0.30918410420417786, "contact_force_loss": 0.031277578324079514, "terrain_level_mean": 3.23876953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46410, "total_transitions": 190095360, "num_steps_per_env": 1, "wm_loss": 0.4212557375431061, "actor_loss": -8.741610527038574, "critic_loss": 0.02509543113410473, "reward": 0.07133834809064865, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2455710619688034, 0.16161198914051056, 0.24901866912841797], "policy_updates": 46310, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9870.585147344, "contact_bce": 0.3120078444480896, "contact_force_loss": 0.0322592593729496, "terrain_level_mean": 3.239501953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46420, "total_transitions": 190136320, "num_steps_per_env": 1, "wm_loss": 0.41937893629074097, "actor_loss": -8.740640640258789, "critic_loss": 0.019952930510044098, "reward": 0.07080816477537155, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2473440021276474, 0.16130857169628143, 0.2537297010421753], "policy_updates": 46320, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9874.093268408, "contact_bce": 0.3128991425037384, "contact_force_loss": 0.032246507704257965, "terrain_level_mean": 3.239990234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33544921875, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46430, "total_transitions": 190177280, "num_steps_per_env": 1, "wm_loss": 0.41480618715286255, "actor_loss": -8.722095489501953, "critic_loss": 0.024289285764098167, "reward": 0.07068983465433121, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24498914182186127, 0.16363616287708282, 0.25465527176856995], "policy_updates": 46330, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9877.60663959, "contact_bce": 0.31301409006118774, "contact_force_loss": 0.032344140112400055, "terrain_level_mean": 3.23974609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33447265625, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46440, "total_transitions": 190218240, "num_steps_per_env": 1, "wm_loss": 0.4014721214771271, "actor_loss": -8.746089935302734, "critic_loss": 0.030562421306967735, "reward": 0.07084043323993683, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24827273190021515, 0.16236309707164764, 0.254952996969223], "policy_updates": 46340, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9881.126257767, "contact_bce": 0.3114459812641144, "contact_force_loss": 0.032161228358745575, "terrain_level_mean": 3.24072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33251953125, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46450, "total_transitions": 190259200, "num_steps_per_env": 1, "wm_loss": 0.42879047989845276, "actor_loss": -8.65414810180664, "critic_loss": 0.027159089222550392, "reward": 0.07074204832315445, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25060757994651794, 0.16174861788749695, 0.2550536096096039], "policy_updates": 46350, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9884.643619891001, "contact_bce": 0.3175742030143738, "contact_force_loss": 0.03355976939201355, "terrain_level_mean": 3.240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46460, "total_transitions": 190300160, "num_steps_per_env": 1, "wm_loss": 0.4096560776233673, "actor_loss": -8.702432632446289, "critic_loss": 0.022045237943530083, "reward": 0.07103120535612106, "falls": 5, "interval_steps": 10, "velocity_mae": [0.249750018119812, 0.15903916954994202, 0.253959059715271], "policy_updates": 46360, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9888.162937953, "contact_bce": 0.31296539306640625, "contact_force_loss": 0.0320044681429863, "terrain_level_mean": 3.240966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9972745180130005, 0.9997045993804932, 2.9994235038757324]} {"step": 46470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46470, "total_transitions": 190341120, "num_steps_per_env": 1, "wm_loss": 0.40848466753959656, "actor_loss": -8.687007904052734, "critic_loss": 0.033686913549900055, "reward": 0.07089270651340485, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25077110528945923, 0.15709172189235687, 0.25399118661880493], "policy_updates": 46370, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9891.692182768, "contact_bce": 0.30976203083992004, "contact_force_loss": 0.03213898465037346, "terrain_level_mean": 3.2412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9972745180130005, 0.999114990234375, 2.9994235038757324]} {"step": 46480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46480, "total_transitions": 190382080, "num_steps_per_env": 1, "wm_loss": 0.42291006445884705, "actor_loss": -8.695892333984375, "critic_loss": 0.04034160450100899, "reward": 0.07112064957618713, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2488415688276291, 0.15925760567188263, 0.2519502639770508], "policy_updates": 46380, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9895.214892473, "contact_bce": 0.3139450252056122, "contact_force_loss": 0.032803311944007874, "terrain_level_mean": 3.241455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9972745180130005, 0.999114990234375, 2.9994235038757324]} {"step": 46490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46490, "total_transitions": 190423040, "num_steps_per_env": 1, "wm_loss": 0.3939934968948364, "actor_loss": -8.731119155883789, "critic_loss": 0.027110695838928223, "reward": 0.07127086073160172, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24421162903308868, 0.15810364484786987, 0.2503878176212311], "policy_updates": 46390, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9898.738958282, "contact_bce": 0.30628299713134766, "contact_force_loss": 0.031535230576992035, "terrain_level_mean": 3.240966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9972745180130005, 0.999114990234375, 2.9994235038757324]} {"step": 46500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46500, "total_transitions": 190464000, "num_steps_per_env": 1, "wm_loss": 0.4209435284137726, "actor_loss": -8.682085990905762, "critic_loss": 0.03331371024250984, "reward": 0.0714409127831459, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24509714543819427, 0.15665602684020996, 0.25037139654159546], "policy_updates": 46400, "skipped_updates": 0, "invalid_env_resets": 98, "elapsed_s": 9902.244700041001, "contact_bce": 0.31012585759162903, "contact_force_loss": 0.03274500370025635, "terrain_level_mean": 3.241455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9994235038757324]} RECOVERY reset 1 invalid environments; first IDs=[1601] {"step": 46510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46510, "total_transitions": 190504960, "num_steps_per_env": 1, "wm_loss": 0.40737006068229675, "actor_loss": -8.72214126586914, "critic_loss": 0.01918204128742218, "reward": 0.07086265832185745, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2478901594877243, 0.15824805200099945, 0.25576794147491455], "policy_updates": 46410, "skipped_updates": 0, "invalid_env_resets": 99, "elapsed_s": 9905.806414738001, "contact_bce": 0.31702956557273865, "contact_force_loss": 0.0326811857521534, "terrain_level_mean": 3.242431640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9994235038757324]} {"step": 46520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46520, "total_transitions": 190545920, "num_steps_per_env": 1, "wm_loss": 0.43125125765800476, "actor_loss": -8.731819152832031, "critic_loss": 0.02491365186870098, "reward": 0.07072763890028, "falls": 6, "interval_steps": 10, "velocity_mae": [0.245258629322052, 0.1579168736934662, 0.2544305920600891], "policy_updates": 46420, "skipped_updates": 0, "invalid_env_resets": 99, "elapsed_s": 9909.574921875, "contact_bce": 0.3089611232280731, "contact_force_loss": 0.032748784869909286, "terrain_level_mean": 3.241943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9994235038757324]} {"step": 46530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46530, "total_transitions": 190586880, "num_steps_per_env": 1, "wm_loss": 0.4278346300125122, "actor_loss": -8.723772048950195, "critic_loss": 0.02165139652788639, "reward": 0.07092326134443283, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24534794688224792, 0.16080814599990845, 0.25616857409477234], "policy_updates": 46430, "skipped_updates": 0, "invalid_env_resets": 99, "elapsed_s": 9913.101342743, "contact_bce": 0.3130575120449066, "contact_force_loss": 0.032507527619600296, "terrain_level_mean": 3.24267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9997754096984863]} {"step": 46540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46540, "total_transitions": 190627840, "num_steps_per_env": 1, "wm_loss": 0.3963604271411896, "actor_loss": -8.68256664276123, "critic_loss": 0.03604339808225632, "reward": 0.07097771763801575, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24868908524513245, 0.16265086829662323, 0.25694260001182556], "policy_updates": 46440, "skipped_updates": 0, "invalid_env_resets": 99, "elapsed_s": 9916.624946925, "contact_bce": 0.3102054297924042, "contact_force_loss": 0.032128386199474335, "terrain_level_mean": 3.243408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9997754096984863]} {"step": 46550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46550, "total_transitions": 190668800, "num_steps_per_env": 1, "wm_loss": 0.417330265045166, "actor_loss": -8.7477445602417, "critic_loss": 0.02657402865588665, "reward": 0.07093848288059235, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25457334518432617, 0.16226612031459808, 0.2568705677986145], "policy_updates": 46450, "skipped_updates": 0, "invalid_env_resets": 99, "elapsed_s": 9920.141868844, "contact_bce": 0.3107614517211914, "contact_force_loss": 0.03236006945371628, "terrain_level_mean": 3.244384765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9997754096984863]} {"step": 46560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46560, "total_transitions": 190709760, "num_steps_per_env": 1, "wm_loss": 0.38658440113067627, "actor_loss": -8.715189933776855, "critic_loss": 0.024533061310648918, "reward": 0.07096710801124573, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2550448179244995, 0.1605357527732849, 0.25830310583114624], "policy_updates": 46460, "skipped_updates": 0, "invalid_env_resets": 99, "elapsed_s": 9923.65979542, "contact_bce": 0.3110167384147644, "contact_force_loss": 0.03173248469829559, "terrain_level_mean": 3.244140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9997754096984863]} RECOVERY reset 1 invalid environments; first IDs=[2041] {"step": 46570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46570, "total_transitions": 190750720, "num_steps_per_env": 1, "wm_loss": 0.39214450120925903, "actor_loss": -8.690329551696777, "critic_loss": 0.022970378398895264, "reward": 0.07099639624357224, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25158512592315674, 0.16180992126464844, 0.25512510538101196], "policy_updates": 46470, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9927.193677209001, "contact_bce": 0.30649471282958984, "contact_force_loss": 0.03123658522963524, "terrain_level_mean": 3.24365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34375, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9997754096984863]} {"step": 46580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46580, "total_transitions": 190791680, "num_steps_per_env": 1, "wm_loss": 0.4076365530490875, "actor_loss": -8.759596824645996, "critic_loss": 0.023801526054739952, "reward": 0.07110006362199783, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25065878033638, 0.16107748448848724, 0.25164875388145447], "policy_updates": 46480, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9930.711592484, "contact_bce": 0.30867668986320496, "contact_force_loss": 0.03186115249991417, "terrain_level_mean": 3.243896484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9997754096984863]} {"step": 46590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46590, "total_transitions": 190832640, "num_steps_per_env": 1, "wm_loss": 0.43741631507873535, "actor_loss": -8.754781723022461, "critic_loss": 0.020013147965073586, "reward": 0.07088898122310638, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2539677023887634, 0.16039787232875824, 0.2549918591976166], "policy_updates": 46490, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9934.229101489, "contact_bce": 0.31404536962509155, "contact_force_loss": 0.03353703022003174, "terrain_level_mean": 3.241943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9983543157577515, 0.999114990234375, 2.9997754096984863]} {"step": 46600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46600, "total_transitions": 190873600, "num_steps_per_env": 1, "wm_loss": 0.40460872650146484, "actor_loss": -8.71679973602295, "critic_loss": 0.023351335898041725, "reward": 0.07055085152387619, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2545851767063141, 0.15847276151180267, 0.25236666202545166], "policy_updates": 46500, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9937.741048336, "contact_bce": 0.30767807364463806, "contact_force_loss": 0.032099492847919464, "terrain_level_mean": 3.241943359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46610, "total_transitions": 190914560, "num_steps_per_env": 1, "wm_loss": 0.41491007804870605, "actor_loss": -8.71721363067627, "critic_loss": 0.029685145244002342, "reward": 0.07055210322141647, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24736882746219635, 0.15727275609970093, 0.252892404794693], "policy_updates": 46510, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9941.255438445001, "contact_bce": 0.31360819935798645, "contact_force_loss": 0.032423168420791626, "terrain_level_mean": 3.2421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46620, "total_transitions": 190955520, "num_steps_per_env": 1, "wm_loss": 0.4269600808620453, "actor_loss": -8.70827865600586, "critic_loss": 0.029204100370407104, "reward": 0.07043502479791641, "falls": 5, "interval_steps": 10, "velocity_mae": [0.246494859457016, 0.15965279936790466, 0.2509241998195648], "policy_updates": 46520, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9944.770676829, "contact_bce": 0.3080054819583893, "contact_force_loss": 0.031492672860622406, "terrain_level_mean": 3.2421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46630, "total_transitions": 190996480, "num_steps_per_env": 1, "wm_loss": 0.4020470678806305, "actor_loss": -8.670637130737305, "critic_loss": 0.09823552519083023, "reward": 0.07025007158517838, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2474120855331421, 0.1597111076116562, 0.2514892518520355], "policy_updates": 46530, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9948.282596831, "contact_bce": 0.3123874068260193, "contact_force_loss": 0.03213559091091156, "terrain_level_mean": 3.24267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46640, "total_transitions": 191037440, "num_steps_per_env": 1, "wm_loss": 0.40154150128364563, "actor_loss": -8.70075798034668, "critic_loss": 0.03245967626571655, "reward": 0.07037212699651718, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2486862689256668, 0.15959976613521576, 0.2509402334690094], "policy_updates": 46540, "skipped_updates": 0, "invalid_env_resets": 100, "elapsed_s": 9951.802513643, "contact_bce": 0.3077286183834076, "contact_force_loss": 0.03258179873228073, "terrain_level_mean": 3.243408203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} RECOVERY reset 1 invalid environments; first IDs=[705] {"step": 46650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46650, "total_transitions": 191078400, "num_steps_per_env": 1, "wm_loss": 0.40281134843826294, "actor_loss": -8.712770462036133, "critic_loss": 0.026885172352194786, "reward": 0.0705723986029625, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2456495314836502, 0.1588738113641739, 0.24789473414421082], "policy_updates": 46550, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9955.336625321, "contact_bce": 0.3070531189441681, "contact_force_loss": 0.032571885734796524, "terrain_level_mean": 3.242919921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46660, "total_transitions": 191119360, "num_steps_per_env": 1, "wm_loss": 0.3934989273548126, "actor_loss": -8.710329055786133, "critic_loss": 0.025915279984474182, "reward": 0.0706309899687767, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24418498575687408, 0.1593586802482605, 0.24842596054077148], "policy_updates": 46560, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9958.854194262001, "contact_bce": 0.30536776781082153, "contact_force_loss": 0.031183410435914993, "terrain_level_mean": 3.2421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46670, "total_transitions": 191160320, "num_steps_per_env": 1, "wm_loss": 0.40491604804992676, "actor_loss": -8.715239524841309, "critic_loss": 0.023252874612808228, "reward": 0.07124997675418854, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24666287004947662, 0.1577034592628479, 0.24893641471862793], "policy_updates": 46570, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9962.377485509001, "contact_bce": 0.31106626987457275, "contact_force_loss": 0.031941208988428116, "terrain_level_mean": 3.240966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46680, "total_transitions": 191201280, "num_steps_per_env": 1, "wm_loss": 0.40954118967056274, "actor_loss": -8.771377563476562, "critic_loss": 0.02897905744612217, "reward": 0.07143241167068481, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24764975905418396, 0.15637901425361633, 0.251329243183136], "policy_updates": 46580, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9965.893734702, "contact_bce": 0.3116215467453003, "contact_force_loss": 0.03197192773222923, "terrain_level_mean": 3.24072265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46690, "total_transitions": 191242240, "num_steps_per_env": 1, "wm_loss": 0.4320334792137146, "actor_loss": -8.696002960205078, "critic_loss": 0.024194179102778435, "reward": 0.07125650346279144, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24907484650611877, 0.15378627181053162, 0.2511967718601227], "policy_updates": 46590, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9969.413365975, "contact_bce": 0.31215396523475647, "contact_force_loss": 0.03319958597421646, "terrain_level_mean": 3.240478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.995484471321106, 0.999114990234375, 2.9997754096984863]} {"step": 46700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46700, "total_transitions": 191283200, "num_steps_per_env": 1, "wm_loss": 0.40993189811706543, "actor_loss": -8.716755867004395, "critic_loss": 0.027519112452864647, "reward": 0.07124026864767075, "falls": 5, "interval_steps": 10, "velocity_mae": [0.246700257062912, 0.154874786734581, 0.25390976667404175], "policy_updates": 46600, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9972.93132512, "contact_bce": 0.3166915476322174, "contact_force_loss": 0.03231818974018097, "terrain_level_mean": 3.240966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9962513446807861, 0.999114990234375, 2.9997754096984863]} {"step": 46710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46710, "total_transitions": 191324160, "num_steps_per_env": 1, "wm_loss": 0.4226197302341461, "actor_loss": -8.689608573913574, "critic_loss": 0.027404893189668655, "reward": 0.0713571235537529, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24620233476161957, 0.1572125405073166, 0.25042811036109924], "policy_updates": 46610, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9976.445902985, "contact_bce": 0.30930519104003906, "contact_force_loss": 0.03259369358420372, "terrain_level_mean": 3.240478515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9962513446807861, 0.996462345123291, 2.9997754096984863]} {"step": 46720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46720, "total_transitions": 191365120, "num_steps_per_env": 1, "wm_loss": 0.4126166105270386, "actor_loss": -8.715189933776855, "critic_loss": 0.043414391577243805, "reward": 0.07143718004226685, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24517720937728882, 0.15541109442710876, 0.251021146774292], "policy_updates": 46620, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9979.956680270001, "contact_bce": 0.3113589882850647, "contact_force_loss": 0.032396674156188965, "terrain_level_mean": 3.240966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.997897982597351, 0.996462345123291, 2.9997754096984863]} {"step": 46730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46730, "total_transitions": 191406080, "num_steps_per_env": 1, "wm_loss": 0.42554259300231934, "actor_loss": -8.720513343811035, "critic_loss": 0.03088526800274849, "reward": 0.07167617231607437, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24165990948677063, 0.15323583781719208, 0.2474498152732849], "policy_updates": 46630, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9983.477281746, "contact_bce": 0.3085035979747772, "contact_force_loss": 0.032374706119298935, "terrain_level_mean": 3.240966796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46740, "total_transitions": 191447040, "num_steps_per_env": 1, "wm_loss": 0.3883505165576935, "actor_loss": -8.758872985839844, "critic_loss": 0.026306165382266045, "reward": 0.07155202329158783, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24488338828086853, 0.15194900333881378, 0.25037193298339844], "policy_updates": 46640, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9986.991447726, "contact_bce": 0.3063335716724396, "contact_force_loss": 0.03191712126135826, "terrain_level_mean": 3.241455078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46750, "total_transitions": 191488000, "num_steps_per_env": 1, "wm_loss": 0.35982057452201843, "actor_loss": -8.722522735595703, "critic_loss": 0.02670171670615673, "reward": 0.071507029235363, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24291998147964478, 0.1521076112985611, 0.24729223549365997], "policy_updates": 46650, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9990.495939323, "contact_bce": 0.3114991784095764, "contact_force_loss": 0.03139161318540573, "terrain_level_mean": 3.2412109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46760, "total_transitions": 191528960, "num_steps_per_env": 1, "wm_loss": 0.43619051575660706, "actor_loss": -8.699872016906738, "critic_loss": 0.028648048639297485, "reward": 0.07211711257696152, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23721745610237122, 0.15203417837619781, 0.2449219822883606], "policy_updates": 46660, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9994.006869347, "contact_bce": 0.3144187033176422, "contact_force_loss": 0.033093731850385666, "terrain_level_mean": 3.24169921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46770, "total_transitions": 191569920, "num_steps_per_env": 1, "wm_loss": 0.40470483899116516, "actor_loss": -8.701794624328613, "critic_loss": 0.03912094980478287, "reward": 0.07232239097356796, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23591335117816925, 0.15200471878051758, 0.2468395084142685], "policy_updates": 46670, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 9997.516568954, "contact_bce": 0.31151703000068665, "contact_force_loss": 0.03174842894077301, "terrain_level_mean": 3.2421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46780, "total_transitions": 191610880, "num_steps_per_env": 1, "wm_loss": 0.4284961521625519, "actor_loss": -8.782293319702148, "critic_loss": 0.02599530853331089, "reward": 0.07189486175775528, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23973557353019714, 0.1529836505651474, 0.24892492592334747], "policy_updates": 46680, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10001.038896902, "contact_bce": 0.3096696734428406, "contact_force_loss": 0.032134685665369034, "terrain_level_mean": 3.2421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46790, "total_transitions": 191651840, "num_steps_per_env": 1, "wm_loss": 0.4171241819858551, "actor_loss": -8.704575538635254, "critic_loss": 0.030697423964738846, "reward": 0.07176795601844788, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24460463225841522, 0.1537296324968338, 0.2514561116695404], "policy_updates": 46690, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10004.558481216001, "contact_bce": 0.31553271412849426, "contact_force_loss": 0.032892417162656784, "terrain_level_mean": 3.242919921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46800, "total_transitions": 191692800, "num_steps_per_env": 1, "wm_loss": 0.40933090448379517, "actor_loss": -8.754002571105957, "critic_loss": 0.027415527030825615, "reward": 0.07186775654554367, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2444642186164856, 0.15283553302288055, 0.24696408212184906], "policy_updates": 46700, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10008.078900287, "contact_bce": 0.3070962429046631, "contact_force_loss": 0.03252866491675377, "terrain_level_mean": 3.24365234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46810, "total_transitions": 191733760, "num_steps_per_env": 1, "wm_loss": 0.4073760509490967, "actor_loss": -8.727754592895508, "critic_loss": 0.025949401780962944, "reward": 0.07177402824163437, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2427745908498764, 0.15051774680614471, 0.24982863664627075], "policy_updates": 46710, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10011.606148534, "contact_bce": 0.30847135186195374, "contact_force_loss": 0.03115551359951496, "terrain_level_mean": 3.245849609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46820, "total_transitions": 191774720, "num_steps_per_env": 1, "wm_loss": 0.38784149289131165, "actor_loss": -8.67696762084961, "critic_loss": 0.0332951545715332, "reward": 0.07194793224334717, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24199533462524414, 0.14894232153892517, 0.2481074333190918], "policy_updates": 46720, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10015.124152035001, "contact_bce": 0.30885550379753113, "contact_force_loss": 0.03212015703320503, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46830, "total_transitions": 191815680, "num_steps_per_env": 1, "wm_loss": 0.4085504412651062, "actor_loss": -8.749261856079102, "critic_loss": 0.037870775908231735, "reward": 0.07193741202354431, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2416435331106186, 0.14924825727939606, 0.2536018192768097], "policy_updates": 46730, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10018.643924472, "contact_bce": 0.3095692992210388, "contact_force_loss": 0.032252319157123566, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46840, "total_transitions": 191856640, "num_steps_per_env": 1, "wm_loss": 0.3882423937320709, "actor_loss": -8.733711242675781, "critic_loss": 0.035447604954242706, "reward": 0.07184029370546341, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2452162504196167, 0.15108655393123627, 0.2501848340034485], "policy_updates": 46740, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10022.162453177001, "contact_bce": 0.30796709656715393, "contact_force_loss": 0.032141223549842834, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46850, "total_transitions": 191897600, "num_steps_per_env": 1, "wm_loss": 0.41367363929748535, "actor_loss": -8.750831604003906, "critic_loss": 0.02082778699696064, "reward": 0.07172698527574539, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2440531700849533, 0.15423484146595, 0.24967992305755615], "policy_updates": 46750, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10025.686516446001, "contact_bce": 0.3075525164604187, "contact_force_loss": 0.03234757483005524, "terrain_level_mean": 3.247314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46860, "total_transitions": 191938560, "num_steps_per_env": 1, "wm_loss": 0.3901868462562561, "actor_loss": -8.734561920166016, "critic_loss": 0.02624928019940853, "reward": 0.0714421197772026, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2454882115125656, 0.15612046420574188, 0.25182652473449707], "policy_updates": 46760, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10029.199222568, "contact_bce": 0.30628642439842224, "contact_force_loss": 0.03179793059825897, "terrain_level_mean": 3.247314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46870, "total_transitions": 191979520, "num_steps_per_env": 1, "wm_loss": 0.4060046374797821, "actor_loss": -8.740516662597656, "critic_loss": 0.03352770209312439, "reward": 0.07120044529438019, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24754156172275543, 0.15742455422878265, 0.25522518157958984], "policy_updates": 46770, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10032.701488149001, "contact_bce": 0.3123950660228729, "contact_force_loss": 0.03209290653467178, "terrain_level_mean": 3.24755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9997754096984863]} {"step": 46880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46880, "total_transitions": 192020480, "num_steps_per_env": 1, "wm_loss": 0.3967195749282837, "actor_loss": -8.755724906921387, "critic_loss": 0.02041274681687355, "reward": 0.07113705575466156, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24783992767333984, 0.157368466258049, 0.2552867531776428], "policy_updates": 46780, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10036.214833576001, "contact_bce": 0.30922582745552063, "contact_force_loss": 0.03211184963583946, "terrain_level_mean": 3.24853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.9993486404418945]} {"step": 46890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46890, "total_transitions": 192061440, "num_steps_per_env": 1, "wm_loss": 0.39390262961387634, "actor_loss": -8.754534721374512, "critic_loss": 0.025471866130828857, "reward": 0.07072275131940842, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2476537823677063, 0.1578214168548584, 0.2571697533130646], "policy_updates": 46790, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10039.743175220001, "contact_bce": 0.30678531527519226, "contact_force_loss": 0.03190770745277405, "terrain_level_mean": 3.248779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.999861001968384]} {"step": 46900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46900, "total_transitions": 192102400, "num_steps_per_env": 1, "wm_loss": 0.4067327380180359, "actor_loss": -8.724613189697266, "critic_loss": 0.032561033964157104, "reward": 0.07114305347204208, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24923641979694366, 0.1548262983560562, 0.25181108713150024], "policy_updates": 46800, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10043.266821968, "contact_bce": 0.3101096451282501, "contact_force_loss": 0.032281238585710526, "terrain_level_mean": 3.249267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.999861001968384]} {"step": 46910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46910, "total_transitions": 192143360, "num_steps_per_env": 1, "wm_loss": 0.3817230463027954, "actor_loss": -8.723819732666016, "critic_loss": 0.02342948131263256, "reward": 0.07073774188756943, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24771538376808167, 0.1567022204399109, 0.24954397976398468], "policy_updates": 46810, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10046.787801473001, "contact_bce": 0.3095247745513916, "contact_force_loss": 0.03237595409154892, "terrain_level_mean": 3.249755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.999861001968384]} {"step": 46920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46920, "total_transitions": 192184320, "num_steps_per_env": 1, "wm_loss": 0.4001794755458832, "actor_loss": -8.74728012084961, "critic_loss": 0.021777665242552757, "reward": 0.07056112587451935, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24869124591350555, 0.158517986536026, 0.25456637144088745], "policy_updates": 46820, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10050.305200044, "contact_bce": 0.30888307094573975, "contact_force_loss": 0.031612806022167206, "terrain_level_mean": 3.24853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.999861001968384]} {"step": 46930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46930, "total_transitions": 192225280, "num_steps_per_env": 1, "wm_loss": 0.40026065707206726, "actor_loss": -8.743837356567383, "critic_loss": 0.02517465315759182, "reward": 0.07006325572729111, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2507305145263672, 0.15667575597763062, 0.25377950072288513], "policy_updates": 46830, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10053.827259291, "contact_bce": 0.30871254205703735, "contact_force_loss": 0.031911641359329224, "terrain_level_mean": 3.24853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.997897982597351, 0.9993970990180969, 2.999861001968384]} {"step": 46940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46940, "total_transitions": 192266240, "num_steps_per_env": 1, "wm_loss": 0.38272783160209656, "actor_loss": -8.743490219116211, "critic_loss": 0.026841459795832634, "reward": 0.07044752687215805, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24955347180366516, 0.1579248160123825, 0.25254741311073303], "policy_updates": 46840, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10057.370732129, "contact_bce": 0.3107227683067322, "contact_force_loss": 0.031894948333501816, "terrain_level_mean": 3.2490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9994590282440186, 0.9985952973365784, 2.999861001968384]} {"step": 46950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46950, "total_transitions": 192307200, "num_steps_per_env": 1, "wm_loss": 0.3957652151584625, "actor_loss": -8.755003929138184, "critic_loss": 0.026574665680527687, "reward": 0.07051923871040344, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2481997311115265, 0.1587841659784317, 0.2526249587535858], "policy_updates": 46850, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10060.889322952, "contact_bce": 0.30461451411247253, "contact_force_loss": 0.031181851401925087, "terrain_level_mean": 3.249267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.9994590282440186, 0.9985952973365784, 2.999861001968384]} {"step": 46960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46960, "total_transitions": 192348160, "num_steps_per_env": 1, "wm_loss": 0.4106323719024658, "actor_loss": -8.715652465820312, "critic_loss": 0.03800610825419426, "reward": 0.07067123055458069, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24863530695438385, 0.1570308953523636, 0.25541555881500244], "policy_updates": 46860, "skipped_updates": 0, "invalid_env_resets": 101, "elapsed_s": 10064.405146525001, "contact_bce": 0.31120049953460693, "contact_force_loss": 0.032661762088537216, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9994590282440186, 0.9985952973365784, 2.999861001968384]} RECOVERY reset 1 invalid environments; first IDs=[1851] {"step": 46970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46970, "total_transitions": 192389120, "num_steps_per_env": 1, "wm_loss": 0.4079868793487549, "actor_loss": -8.733582496643066, "critic_loss": 0.03585286810994148, "reward": 0.07091180235147476, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24533694982528687, 0.15769729018211365, 0.25250673294067383], "policy_updates": 46870, "skipped_updates": 0, "invalid_env_resets": 102, "elapsed_s": 10067.937152777, "contact_bce": 0.30525124073028564, "contact_force_loss": 0.03187766671180725, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9994590282440186, 0.9985952973365784, 2.9993486404418945]} {"step": 46980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46980, "total_transitions": 192430080, "num_steps_per_env": 1, "wm_loss": 0.4119320809841156, "actor_loss": -8.717500686645508, "critic_loss": 0.02145121805369854, "reward": 0.07075764983892441, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24466387927532196, 0.15709371864795685, 0.2487700879573822], "policy_updates": 46880, "skipped_updates": 0, "invalid_env_resets": 102, "elapsed_s": 10071.454659378, "contact_bce": 0.31033360958099365, "contact_force_loss": 0.032392993569374084, "terrain_level_mean": 3.2490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9994590282440186, 0.9978691339492798, 2.9993486404418945]} RECOVERY reset 1 invalid environments; first IDs=[1332] {"step": 46990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 46990, "total_transitions": 192471040, "num_steps_per_env": 1, "wm_loss": 0.403293639421463, "actor_loss": -8.729175567626953, "critic_loss": 0.029943695291876793, "reward": 0.07094981521368027, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2454066425561905, 0.15757107734680176, 0.24835117161273956], "policy_updates": 46890, "skipped_updates": 0, "invalid_env_resets": 103, "elapsed_s": 10074.977737428, "contact_bce": 0.31014785170555115, "contact_force_loss": 0.033280011266469955, "terrain_level_mean": 3.2490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9994590282440186, 0.9978691339492798, 2.9993486404418945]} RECOVERY reset 1 invalid environments; first IDs=[1269] {"step": 47000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47000, "total_transitions": 192512000, "num_steps_per_env": 1, "wm_loss": 0.4069857597351074, "actor_loss": -8.744837760925293, "critic_loss": 0.025380292907357216, "reward": 0.07125654071569443, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24710777401924133, 0.15839692950248718, 0.24897150695323944], "policy_updates": 46900, "skipped_updates": 0, "invalid_env_resets": 104, "elapsed_s": 10078.508626363, "contact_bce": 0.30169156193733215, "contact_force_loss": 0.03172997757792473, "terrain_level_mean": 3.248779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9994590282440186, 0.9978691339492798, 2.9993486404418945]} {"step": 47010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47010, "total_transitions": 192552960, "num_steps_per_env": 1, "wm_loss": 0.3905705213546753, "actor_loss": -8.677546501159668, "critic_loss": 0.030872324481606483, "reward": 0.07127203792333603, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2500477135181427, 0.1572338044643402, 0.2538039982318878], "policy_updates": 46910, "skipped_updates": 0, "invalid_env_resets": 104, "elapsed_s": 10082.056744079, "contact_bce": 0.3125910460948944, "contact_force_loss": 0.0324288047850132, "terrain_level_mean": 3.2490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9994590282440186, 0.9978691339492798, 2.9993486404418945]} RECOVERY reset 1 invalid environments; first IDs=[2239] {"step": 47020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47020, "total_transitions": 192593920, "num_steps_per_env": 1, "wm_loss": 0.40205147862434387, "actor_loss": -8.74290657043457, "critic_loss": 0.02288462594151497, "reward": 0.07060310989618301, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25357845425605774, 0.15715116262435913, 0.25813379883766174], "policy_updates": 46920, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10085.845621345, "contact_bce": 0.3102444112300873, "contact_force_loss": 0.032175302505493164, "terrain_level_mean": 3.249267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9994590282440186, 0.9978691339492798, 2.9993486404418945]} {"step": 47030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47030, "total_transitions": 192634880, "num_steps_per_env": 1, "wm_loss": 0.4041481912136078, "actor_loss": -8.711788177490234, "critic_loss": 0.028499145060777664, "reward": 0.07044880092144012, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25372377038002014, 0.1570015847682953, 0.2571961283683777], "policy_updates": 46930, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10089.373762351, "contact_bce": 0.3072171211242676, "contact_force_loss": 0.03223559260368347, "terrain_level_mean": 3.248779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9994590282440186, 0.9980685710906982, 2.9993486404418945]} {"step": 47040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47040, "total_transitions": 192675840, "num_steps_per_env": 1, "wm_loss": 0.37603962421417236, "actor_loss": -8.726997375488281, "critic_loss": 0.02824004553258419, "reward": 0.07114211469888687, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24930648505687714, 0.1573866754770279, 0.25562790036201477], "policy_updates": 46940, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10092.897052227001, "contact_bce": 0.304105281829834, "contact_force_loss": 0.03153451904654503, "terrain_level_mean": 3.247802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9994590282440186, 0.9982898235321045, 2.9993486404418945]} {"step": 47050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47050, "total_transitions": 192716800, "num_steps_per_env": 1, "wm_loss": 0.37754499912261963, "actor_loss": -8.742375373840332, "critic_loss": 0.03449811786413193, "reward": 0.0713074579834938, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24817904829978943, 0.15897725522518158, 0.2521741986274719], "policy_updates": 46950, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10096.424751877, "contact_bce": 0.30568060278892517, "contact_force_loss": 0.031430069357156754, "terrain_level_mean": 3.247314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9994590282440186, 0.9982898235321045, 2.9993486404418945]} {"step": 47060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47060, "total_transitions": 192757760, "num_steps_per_env": 1, "wm_loss": 0.3954589068889618, "actor_loss": -8.730329513549805, "critic_loss": 0.03754475712776184, "reward": 0.07094432413578033, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2518276274204254, 0.16037291288375854, 0.24781742691993713], "policy_updates": 46960, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10099.949894947, "contact_bce": 0.307000070810318, "contact_force_loss": 0.03173578903079033, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.999820351600647, 0.9982898235321045, 2.9993486404418945]} {"step": 47070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47070, "total_transitions": 192798720, "num_steps_per_env": 1, "wm_loss": 0.3971264362335205, "actor_loss": -8.707013130187988, "critic_loss": 0.027241671457886696, "reward": 0.07044809311628342, "falls": 13, "interval_steps": 10, "velocity_mae": [0.25109508633613586, 0.15979455411434174, 0.2512280344963074], "policy_updates": 46970, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10103.473272628, "contact_bce": 0.3079761564731598, "contact_force_loss": 0.03183950483798981, "terrain_level_mean": 3.24462890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341064453125, "command_abs_max": [1.999820351600647, 0.9982898235321045, 2.9993486404418945]} {"step": 47080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47080, "total_transitions": 192839680, "num_steps_per_env": 1, "wm_loss": 0.3760768175125122, "actor_loss": -8.703378677368164, "critic_loss": 0.02648906782269478, "reward": 0.07101853936910629, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2491735965013504, 0.159895122051239, 0.2494250237941742], "policy_updates": 46980, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10106.980743788, "contact_bce": 0.3129243850708008, "contact_force_loss": 0.032018836587667465, "terrain_level_mean": 3.245361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.9994590282440186, 0.9982898235321045, 2.9944050312042236]} {"step": 47090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47090, "total_transitions": 192880640, "num_steps_per_env": 1, "wm_loss": 0.4029695987701416, "actor_loss": -8.675722122192383, "critic_loss": 0.031082693487405777, "reward": 0.07122185081243515, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24663519859313965, 0.15690253674983978, 0.24957484006881714], "policy_updates": 46990, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10110.501621794001, "contact_bce": 0.30576178431510925, "contact_force_loss": 0.031780168414115906, "terrain_level_mean": 3.244873046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9994590282440186, 0.9982898235321045, 2.9944050312042236]} {"step": 47100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47100, "total_transitions": 192921600, "num_steps_per_env": 1, "wm_loss": 0.4132806360721588, "actor_loss": -8.691322326660156, "critic_loss": 0.0248925369232893, "reward": 0.07128550857305527, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24659384787082672, 0.15712377429008484, 0.2506529688835144], "policy_updates": 47000, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10114.017305790001, "contact_bce": 0.31087997555732727, "contact_force_loss": 0.03283074498176575, "terrain_level_mean": 3.244873046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3369140625, "command_abs_max": [1.9994590282440186, 0.9982898235321045, 2.9944050312042236]} {"step": 47110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47110, "total_transitions": 192962560, "num_steps_per_env": 1, "wm_loss": 0.404982328414917, "actor_loss": -8.715912818908691, "critic_loss": 0.020763296633958817, "reward": 0.07113268226385117, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2521856427192688, 0.15691092610359192, 0.25400426983833313], "policy_updates": 47010, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10117.538077225001, "contact_bce": 0.31255730986595154, "contact_force_loss": 0.03274133801460266, "terrain_level_mean": 3.245361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9944050312042236]} {"step": 47120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47120, "total_transitions": 193003520, "num_steps_per_env": 1, "wm_loss": 0.39935365319252014, "actor_loss": -8.700313568115234, "critic_loss": 0.03199443221092224, "reward": 0.07130865007638931, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24937523901462555, 0.15678197145462036, 0.25346094369888306], "policy_updates": 47020, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10121.053434115001, "contact_bce": 0.30990371108055115, "contact_force_loss": 0.03138536214828491, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9944050312042236]} {"step": 47130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47130, "total_transitions": 193044480, "num_steps_per_env": 1, "wm_loss": 0.4105251133441925, "actor_loss": -8.684601783752441, "critic_loss": 0.029137087985873222, "reward": 0.07146143168210983, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25048136711120605, 0.1567762941122055, 0.24943839013576508], "policy_updates": 47030, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10124.571874964, "contact_bce": 0.3169923424720764, "contact_force_loss": 0.03231246769428253, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9944050312042236]} {"step": 47140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47140, "total_transitions": 193085440, "num_steps_per_env": 1, "wm_loss": 0.3750559091567993, "actor_loss": -8.694476127624512, "critic_loss": 0.032203324139118195, "reward": 0.07163407653570175, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2468256652355194, 0.1593521684408188, 0.24932925403118134], "policy_updates": 47040, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10128.082339961, "contact_bce": 0.3045887351036072, "contact_force_loss": 0.0311039537191391, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9944050312042236]} {"step": 47150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47150, "total_transitions": 193126400, "num_steps_per_env": 1, "wm_loss": 0.4078446924686432, "actor_loss": -8.774212837219238, "critic_loss": 0.024749716743826866, "reward": 0.07124540209770203, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24837009608745575, 0.16078215837478638, 0.2506204843521118], "policy_updates": 47050, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10131.600635173001, "contact_bce": 0.31325292587280273, "contact_force_loss": 0.03308067098259926, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9944050312042236]} {"step": 47160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47160, "total_transitions": 193167360, "num_steps_per_env": 1, "wm_loss": 0.3906252682209015, "actor_loss": -8.700399398803711, "critic_loss": 0.03984382376074791, "reward": 0.07100711762905121, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25054076313972473, 0.16044531762599945, 0.2512935996055603], "policy_updates": 47060, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10135.108489755, "contact_bce": 0.3024636507034302, "contact_force_loss": 0.03195187821984291, "terrain_level_mean": 3.247314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9947383403778076]} {"step": 47170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47170, "total_transitions": 193208320, "num_steps_per_env": 1, "wm_loss": 0.3906567096710205, "actor_loss": -8.754800796508789, "critic_loss": 0.025688007473945618, "reward": 0.07137735188007355, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2480623871088028, 0.1596485823392868, 0.25264352560043335], "policy_updates": 47070, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10138.624220784, "contact_bce": 0.31341302394866943, "contact_force_loss": 0.03283883258700371, "terrain_level_mean": 3.2470703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9947383403778076]} {"step": 47180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47180, "total_transitions": 193249280, "num_steps_per_env": 1, "wm_loss": 0.3960660696029663, "actor_loss": -8.711784362792969, "critic_loss": 0.030756408348679543, "reward": 0.07123769074678421, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2508217394351959, 0.15808574855327606, 0.2497025430202484], "policy_updates": 47080, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10142.13519755, "contact_bce": 0.3100312054157257, "contact_force_loss": 0.032205648720264435, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9947383403778076]} {"step": 47190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47190, "total_transitions": 193290240, "num_steps_per_env": 1, "wm_loss": 0.37970590591430664, "actor_loss": -8.686233520507812, "critic_loss": 0.027638209983706474, "reward": 0.07155581563711166, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24646201729774475, 0.15363124012947083, 0.2458115518093109], "policy_updates": 47090, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10145.658395723001, "contact_bce": 0.30612102150917053, "contact_force_loss": 0.03168928623199463, "terrain_level_mean": 3.245361328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9947383403778076]} {"step": 47200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47200, "total_transitions": 193331200, "num_steps_per_env": 1, "wm_loss": 0.40664756298065186, "actor_loss": -8.747178077697754, "critic_loss": 0.02267354167997837, "reward": 0.07186134159564972, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24733631312847137, 0.15313686430454254, 0.24609778821468353], "policy_updates": 47100, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10149.178060426, "contact_bce": 0.30518215894699097, "contact_force_loss": 0.031956277787685394, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9947383403778076]} {"step": 47210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47210, "total_transitions": 193372160, "num_steps_per_env": 1, "wm_loss": 0.40049898624420166, "actor_loss": -8.745271682739258, "critic_loss": 0.02066018432378769, "reward": 0.0717383548617363, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24673683941364288, 0.1575937718153, 0.24751268327236176], "policy_updates": 47110, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10152.696659674, "contact_bce": 0.30989283323287964, "contact_force_loss": 0.03183308616280556, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9994590282440186, 0.9985353946685791, 2.9947383403778076]} {"step": 47220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47220, "total_transitions": 193413120, "num_steps_per_env": 1, "wm_loss": 0.41095662117004395, "actor_loss": -8.724442481994629, "critic_loss": 0.024285748600959778, "reward": 0.07152696698904037, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24430575966835022, 0.15624213218688965, 0.24841025471687317], "policy_updates": 47120, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10156.218313462, "contact_bce": 0.3065684139728546, "contact_force_loss": 0.03224324807524681, "terrain_level_mean": 3.24560546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} {"step": 47230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47230, "total_transitions": 193454080, "num_steps_per_env": 1, "wm_loss": 0.4224916994571686, "actor_loss": -8.769338607788086, "critic_loss": 0.02174062840640545, "reward": 0.07116776704788208, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24719440937042236, 0.15638507902622223, 0.252254456281662], "policy_updates": 47130, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10159.73589621, "contact_bce": 0.31379181146621704, "contact_force_loss": 0.03272450342774391, "terrain_level_mean": 3.24658203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} {"step": 47240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47240, "total_transitions": 193495040, "num_steps_per_env": 1, "wm_loss": 0.4076710641384125, "actor_loss": -8.75710678100586, "critic_loss": 0.02797161601483822, "reward": 0.07115500420331955, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24452635645866394, 0.15805059671401978, 0.2494381070137024], "policy_updates": 47140, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10163.250176653, "contact_bce": 0.3121311664581299, "contact_force_loss": 0.032977405935525894, "terrain_level_mean": 3.2470703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} {"step": 47250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47250, "total_transitions": 193536000, "num_steps_per_env": 1, "wm_loss": 0.397632896900177, "actor_loss": -8.712482452392578, "critic_loss": 0.026417851448059082, "reward": 0.0708656907081604, "falls": 7, "interval_steps": 10, "velocity_mae": [0.244160458445549, 0.1561400443315506, 0.24697920680046082], "policy_updates": 47150, "skipped_updates": 0, "invalid_env_resets": 105, "elapsed_s": 10166.762177544, "contact_bce": 0.3079977035522461, "contact_force_loss": 0.03231482580304146, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336669921875, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} RECOVERY reset 1 invalid environments; first IDs=[1136] {"step": 47260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47260, "total_transitions": 193576960, "num_steps_per_env": 1, "wm_loss": 0.3780074715614319, "actor_loss": -8.781681060791016, "critic_loss": 0.024104991927742958, "reward": 0.07075521349906921, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24678969383239746, 0.15793947875499725, 0.2493065744638443], "policy_updates": 47160, "skipped_updates": 0, "invalid_env_resets": 106, "elapsed_s": 10170.28188939, "contact_bce": 0.3060038685798645, "contact_force_loss": 0.031034423038363457, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} {"step": 47270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47270, "total_transitions": 193617920, "num_steps_per_env": 1, "wm_loss": 0.4140671193599701, "actor_loss": -8.708916664123535, "critic_loss": 0.02674444392323494, "reward": 0.07091431319713593, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24446868896484375, 0.1582898050546646, 0.247205451130867], "policy_updates": 47170, "skipped_updates": 0, "invalid_env_resets": 106, "elapsed_s": 10173.791810221, "contact_bce": 0.31057414412498474, "contact_force_loss": 0.03279900178313255, "terrain_level_mean": 3.247314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} {"step": 47280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47280, "total_transitions": 193658880, "num_steps_per_env": 1, "wm_loss": 0.38240373134613037, "actor_loss": -8.725923538208008, "critic_loss": 0.021757274866104126, "reward": 0.07074254751205444, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24727383255958557, 0.15725652873516083, 0.24777042865753174], "policy_updates": 47180, "skipped_updates": 0, "invalid_env_resets": 106, "elapsed_s": 10177.288030809, "contact_bce": 0.30418455600738525, "contact_force_loss": 0.0315057709813118, "terrain_level_mean": 3.24853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} RECOVERY reset 1 invalid environments; first IDs=[1106] {"step": 47290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47290, "total_transitions": 193699840, "num_steps_per_env": 1, "wm_loss": 0.37585967779159546, "actor_loss": -8.754364967346191, "critic_loss": 0.018826086074113846, "reward": 0.07099810987710953, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24528032541275024, 0.15696974098682404, 0.2478422224521637], "policy_updates": 47190, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10180.804200012, "contact_bce": 0.30751582980155945, "contact_force_loss": 0.03136606141924858, "terrain_level_mean": 3.24853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3427734375, "command_abs_max": [1.998656988143921, 0.9985353946685791, 2.9947383403778076]} {"step": 47300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47300, "total_transitions": 193740800, "num_steps_per_env": 1, "wm_loss": 0.38685381412506104, "actor_loss": -8.714691162109375, "critic_loss": 0.026360780000686646, "reward": 0.07142245024442673, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24113261699676514, 0.1528976857662201, 0.24335268139839172], "policy_updates": 47200, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10184.305312756, "contact_bce": 0.31035682559013367, "contact_force_loss": 0.03194819390773773, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.999711513519287, 0.9985353946685791, 2.9947383403778076]} {"step": 47310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47310, "total_transitions": 193781760, "num_steps_per_env": 1, "wm_loss": 0.41380810737609863, "actor_loss": -8.736404418945312, "critic_loss": 0.019495034590363503, "reward": 0.07132613658905029, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2397913932800293, 0.1523781567811966, 0.24513091146945953], "policy_updates": 47210, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10187.809046874001, "contact_bce": 0.3072371482849121, "contact_force_loss": 0.03195716440677643, "terrain_level_mean": 3.246826171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.9947383403778076]} {"step": 47320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47320, "total_transitions": 193822720, "num_steps_per_env": 1, "wm_loss": 0.4049910306930542, "actor_loss": -8.767557144165039, "critic_loss": 0.025255000218749046, "reward": 0.07154473662376404, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24084539711475372, 0.15418124198913574, 0.24662646651268005], "policy_updates": 47220, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10191.325767922, "contact_bce": 0.3114475905895233, "contact_force_loss": 0.03221236541867256, "terrain_level_mean": 3.2470703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.9947383403778076]} {"step": 47330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47330, "total_transitions": 193863680, "num_steps_per_env": 1, "wm_loss": 0.38807594776153564, "actor_loss": -8.73492431640625, "critic_loss": 0.019694847986102104, "reward": 0.07136225700378418, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2433992177248001, 0.15448209643363953, 0.25242942571640015], "policy_updates": 47230, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10194.837501962, "contact_bce": 0.31079280376434326, "contact_force_loss": 0.032168131321668625, "terrain_level_mean": 3.24755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47340, "total_transitions": 193904640, "num_steps_per_env": 1, "wm_loss": 0.4080566167831421, "actor_loss": -8.719828605651855, "critic_loss": 0.03692038357257843, "reward": 0.07123395055532455, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24474413692951202, 0.1538696140050888, 0.2531439960002899], "policy_updates": 47240, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10198.3482722, "contact_bce": 0.3110192120075226, "contact_force_loss": 0.03243517875671387, "terrain_level_mean": 3.24951171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47350, "total_transitions": 193945600, "num_steps_per_env": 1, "wm_loss": 0.3882366120815277, "actor_loss": -8.734207153320312, "critic_loss": 0.03240962699055672, "reward": 0.0712452083826065, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2436719387769699, 0.15375089645385742, 0.25478264689445496], "policy_updates": 47250, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10201.864940860001, "contact_bce": 0.3082951307296753, "contact_force_loss": 0.031853292137384415, "terrain_level_mean": 3.249267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47360, "total_transitions": 193986560, "num_steps_per_env": 1, "wm_loss": 0.4030875265598297, "actor_loss": -8.726737976074219, "critic_loss": 0.025127682834863663, "reward": 0.0708395466208458, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24465292692184448, 0.1555955559015274, 0.2506732642650604], "policy_updates": 47260, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10205.381232745001, "contact_bce": 0.31387025117874146, "contact_force_loss": 0.03195858374238014, "terrain_level_mean": 3.24853515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47370, "total_transitions": 194027520, "num_steps_per_env": 1, "wm_loss": 0.40566566586494446, "actor_loss": -8.722370147705078, "critic_loss": 0.025339100509881973, "reward": 0.07103817909955978, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24695265293121338, 0.156394362449646, 0.2502494752407074], "policy_updates": 47270, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10208.894117856, "contact_bce": 0.3120667338371277, "contact_force_loss": 0.031662169843912125, "terrain_level_mean": 3.249755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47380, "total_transitions": 194068480, "num_steps_per_env": 1, "wm_loss": 0.39802587032318115, "actor_loss": -8.688272476196289, "critic_loss": 0.02529584802687168, "reward": 0.07083719968795776, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24533751606941223, 0.16057999432086945, 0.2518932521343231], "policy_updates": 47280, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10212.412895673, "contact_bce": 0.29914286732673645, "contact_force_loss": 0.03153401240706444, "terrain_level_mean": 3.248291015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47390, "total_transitions": 194109440, "num_steps_per_env": 1, "wm_loss": 0.3878900706768036, "actor_loss": -8.765129089355469, "critic_loss": 0.018586456775665283, "reward": 0.07104431837797165, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24462100863456726, 0.15855921804904938, 0.2507122755050659], "policy_updates": 47290, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10215.934418116001, "contact_bce": 0.3088749349117279, "contact_force_loss": 0.032609932124614716, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47400, "total_transitions": 194150400, "num_steps_per_env": 1, "wm_loss": 0.3947600722312927, "actor_loss": -8.760875701904297, "critic_loss": 0.024058882147073746, "reward": 0.07106372714042664, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2447422295808792, 0.15744006633758545, 0.24931231141090393], "policy_updates": 47300, "skipped_updates": 0, "invalid_env_resets": 107, "elapsed_s": 10219.458532932, "contact_bce": 0.3074745535850525, "contact_force_loss": 0.03231802210211754, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} RECOVERY reset 1 invalid environments; first IDs=[704] {"step": 47410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47410, "total_transitions": 194191360, "num_steps_per_env": 1, "wm_loss": 0.3794388771057129, "actor_loss": -8.751941680908203, "critic_loss": 0.020749032497406006, "reward": 0.07080124318599701, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2483106255531311, 0.1556394100189209, 0.2568744122982025], "policy_updates": 47310, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10222.988331368, "contact_bce": 0.3027184009552002, "contact_force_loss": 0.03134701028466225, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47420, "total_transitions": 194232320, "num_steps_per_env": 1, "wm_loss": 0.4051137864589691, "actor_loss": -8.752851486206055, "critic_loss": 0.021514853462576866, "reward": 0.07083942741155624, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24886158108711243, 0.15802335739135742, 0.25742584466934204], "policy_updates": 47320, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10226.505522020001, "contact_bce": 0.3098251223564148, "contact_force_loss": 0.03289686143398285, "terrain_level_mean": 3.248779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47430, "total_transitions": 194273280, "num_steps_per_env": 1, "wm_loss": 0.4041192829608917, "actor_loss": -8.72651481628418, "critic_loss": 0.01816585101187229, "reward": 0.07114099711179733, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24722975492477417, 0.15851299464702606, 0.256305068731308], "policy_updates": 47330, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10230.027622003001, "contact_bce": 0.31356504559516907, "contact_force_loss": 0.03221661224961281, "terrain_level_mean": 3.249267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.999711513519287, 0.9978512525558472, 2.999513626098633]} {"step": 47440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47440, "total_transitions": 194314240, "num_steps_per_env": 1, "wm_loss": 0.42223992943763733, "actor_loss": -8.785470962524414, "critic_loss": 0.027780717238783836, "reward": 0.071250319480896, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2447546124458313, 0.1579916924238205, 0.25466224551200867], "policy_updates": 47340, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10233.546711242001, "contact_bce": 0.31072598695755005, "contact_force_loss": 0.032903775572776794, "terrain_level_mean": 3.2490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.999855875968933, 0.9978512525558472, 2.999513626098633]} {"step": 47450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47450, "total_transitions": 194355200, "num_steps_per_env": 1, "wm_loss": 0.38762983679771423, "actor_loss": -8.718788146972656, "critic_loss": 0.02569097839295864, "reward": 0.07099040597677231, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24419499933719635, 0.15972071886062622, 0.2561211884021759], "policy_updates": 47350, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10237.059665062001, "contact_bce": 0.30378833413124084, "contact_force_loss": 0.03154371678829193, "terrain_level_mean": 3.249755859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.999855875968933, 0.9978512525558472, 2.999513626098633]} {"step": 47460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47460, "total_transitions": 194396160, "num_steps_per_env": 1, "wm_loss": 0.36494025588035583, "actor_loss": -8.69659423828125, "critic_loss": 0.041287049651145935, "reward": 0.07056628912687302, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24697023630142212, 0.15983137488365173, 0.25899219512939453], "policy_updates": 47360, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10240.583756542, "contact_bce": 0.3005635738372803, "contact_force_loss": 0.03090633451938629, "terrain_level_mean": 3.248779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.999855875968933, 0.9978512525558472, 2.999513626098633]} {"step": 47470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47470, "total_transitions": 194437120, "num_steps_per_env": 1, "wm_loss": 0.3960065245628357, "actor_loss": -8.785452842712402, "critic_loss": 0.022232534363865852, "reward": 0.07092057913541794, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24388985335826874, 0.15896104276180267, 0.254249632358551], "policy_updates": 47370, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10244.108610471001, "contact_bce": 0.307211309671402, "contact_force_loss": 0.03156145289540291, "terrain_level_mean": 3.247802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.999855875968933, 0.9957664608955383, 2.999513626098633]} {"step": 47480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47480, "total_transitions": 194478080, "num_steps_per_env": 1, "wm_loss": 0.40067023038864136, "actor_loss": -8.693249702453613, "critic_loss": 0.023947371169924736, "reward": 0.07100404798984528, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24347667396068573, 0.158903568983078, 0.24903005361557007], "policy_updates": 47380, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10247.630340248, "contact_bce": 0.31072500348091125, "contact_force_loss": 0.03200804069638252, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.999855875968933, 0.9957664608955383, 2.999513626098633]} {"step": 47490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47490, "total_transitions": 194519040, "num_steps_per_env": 1, "wm_loss": 0.39037731289863586, "actor_loss": -8.713176727294922, "critic_loss": 0.029990578070282936, "reward": 0.07097485661506653, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24143251776695251, 0.15735146403312683, 0.2472369223833084], "policy_updates": 47390, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10251.151004446001, "contact_bce": 0.3070433437824249, "contact_force_loss": 0.032319288700819016, "terrain_level_mean": 3.247314453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.999855875968933, 0.9961349368095398, 2.999513626098633]} {"step": 47500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47500, "total_transitions": 194560000, "num_steps_per_env": 1, "wm_loss": 0.37900397181510925, "actor_loss": -8.711450576782227, "critic_loss": 0.030742546543478966, "reward": 0.07104312628507614, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24103838205337524, 0.15793970227241516, 0.24761606752872467], "policy_updates": 47400, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10254.673258044, "contact_bce": 0.309266060590744, "contact_force_loss": 0.03185195475816727, "terrain_level_mean": 3.247802734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.999855875968933, 0.9961349368095398, 2.999040126800537]} {"step": 47510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47510, "total_transitions": 194600960, "num_steps_per_env": 1, "wm_loss": 0.38647982478141785, "actor_loss": -8.703023910522461, "critic_loss": 0.025924474000930786, "reward": 0.07127457857131958, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24148814380168915, 0.15694017708301544, 0.2461215704679489], "policy_updates": 47410, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10258.227036788001, "contact_bce": 0.30885133147239685, "contact_force_loss": 0.03155362606048584, "terrain_level_mean": 3.248779296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.999855875968933, 0.9961349368095398, 2.999040126800537]} {"step": 47520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47520, "total_transitions": 194641920, "num_steps_per_env": 1, "wm_loss": 0.38368847966194153, "actor_loss": -8.691458702087402, "critic_loss": 0.032365091145038605, "reward": 0.0710567757487297, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2461092174053192, 0.1565990149974823, 0.24891822040081024], "policy_updates": 47420, "skipped_updates": 0, "invalid_env_resets": 108, "elapsed_s": 10262.007540163, "contact_bce": 0.30749475955963135, "contact_force_loss": 0.03168627992272377, "terrain_level_mean": 3.249267578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.999855875968933, 0.9961349368095398, 2.999040126800537]} RECOVERY reset 1 invalid environments; first IDs=[665] {"step": 47530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47530, "total_transitions": 194682880, "num_steps_per_env": 1, "wm_loss": 0.38409075140953064, "actor_loss": -8.689796447753906, "critic_loss": 0.030038489028811455, "reward": 0.07125529646873474, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2482064962387085, 0.1567840725183487, 0.24809220433235168], "policy_updates": 47430, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10265.543212398, "contact_bce": 0.30791133642196655, "contact_force_loss": 0.03126060217618942, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.999855875968933, 0.9961349368095398, 2.999040126800537]} {"step": 47540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47540, "total_transitions": 194723840, "num_steps_per_env": 1, "wm_loss": 0.41169342398643494, "actor_loss": -8.789665222167969, "critic_loss": 0.022956296801567078, "reward": 0.07156302779912949, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24047820270061493, 0.1564742624759674, 0.2457074373960495], "policy_updates": 47440, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10269.060691758, "contact_bce": 0.30761459469795227, "contact_force_loss": 0.03116915188729763, "terrain_level_mean": 3.248046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.999855875968933, 0.9961349368095398, 2.9958643913269043]} {"step": 47550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47550, "total_transitions": 194764800, "num_steps_per_env": 1, "wm_loss": 0.372453898191452, "actor_loss": -8.762361526489258, "critic_loss": 0.022883519530296326, "reward": 0.07110222429037094, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2374705970287323, 0.15390168130397797, 0.24931183457374573], "policy_updates": 47450, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10272.577056158001, "contact_bce": 0.30806243419647217, "contact_force_loss": 0.03153984621167183, "terrain_level_mean": 3.2490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.999711513519287, 0.9961349368095398, 2.9958643913269043]} {"step": 47560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47560, "total_transitions": 194805760, "num_steps_per_env": 1, "wm_loss": 0.39444664120674133, "actor_loss": -8.753999710083008, "critic_loss": 0.021044394001364708, "reward": 0.0714121088385582, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2387499064207077, 0.1528165340423584, 0.2540658414363861], "policy_updates": 47460, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10276.099345212, "contact_bce": 0.3086209297180176, "contact_force_loss": 0.03188982605934143, "terrain_level_mean": 3.2490234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47570, "total_transitions": 194846720, "num_steps_per_env": 1, "wm_loss": 0.3925197720527649, "actor_loss": -8.701287269592285, "critic_loss": 0.025228578597307205, "reward": 0.07122671604156494, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24845387041568756, 0.1533653438091278, 0.2552884519100189], "policy_updates": 47470, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10279.624437576, "contact_bce": 0.3076542615890503, "contact_force_loss": 0.032564904540777206, "terrain_level_mean": 3.250244140625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47580, "total_transitions": 194887680, "num_steps_per_env": 1, "wm_loss": 0.37405234575271606, "actor_loss": -8.776810646057129, "critic_loss": 0.029286960139870644, "reward": 0.07123783975839615, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2465103715658188, 0.15376250445842743, 0.24802911281585693], "policy_updates": 47480, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10283.138808585001, "contact_bce": 0.30686086416244507, "contact_force_loss": 0.031212328001856804, "terrain_level_mean": 3.2509765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347900390625, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47590, "total_transitions": 194928640, "num_steps_per_env": 1, "wm_loss": 0.40693172812461853, "actor_loss": -8.740633010864258, "critic_loss": 0.028776679188013077, "reward": 0.07156132161617279, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24274545907974243, 0.15282535552978516, 0.24816329777240753], "policy_updates": 47490, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10286.657161215, "contact_bce": 0.30822744965553284, "contact_force_loss": 0.03150129318237305, "terrain_level_mean": 3.251220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47600, "total_transitions": 194969600, "num_steps_per_env": 1, "wm_loss": 0.3821951150894165, "actor_loss": -8.751789093017578, "critic_loss": 0.020907355472445488, "reward": 0.0711151584982872, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24494746327400208, 0.15323728322982788, 0.2531799077987671], "policy_updates": 47500, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10290.176226812, "contact_bce": 0.30401432514190674, "contact_force_loss": 0.03164165839552879, "terrain_level_mean": 3.251220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346435546875, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47610, "total_transitions": 195010560, "num_steps_per_env": 1, "wm_loss": 0.39948639273643494, "actor_loss": -8.778332710266113, "critic_loss": 0.029171371832489967, "reward": 0.07136270403862, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2441369742155075, 0.15505293011665344, 0.2524506449699402], "policy_updates": 47510, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10293.695167336, "contact_bce": 0.3089412748813629, "contact_force_loss": 0.03170342743396759, "terrain_level_mean": 3.252197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47620, "total_transitions": 195051520, "num_steps_per_env": 1, "wm_loss": 0.3887912929058075, "actor_loss": -8.727258682250977, "critic_loss": 0.02789766900241375, "reward": 0.07104744762182236, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24377930164337158, 0.1566268652677536, 0.2567838430404663], "policy_updates": 47520, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10297.210968543, "contact_bce": 0.31048619747161865, "contact_force_loss": 0.03240463510155678, "terrain_level_mean": 3.253173828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47630, "total_transitions": 195092480, "num_steps_per_env": 1, "wm_loss": 0.3832131028175354, "actor_loss": -8.74725341796875, "critic_loss": 0.025103801861405373, "reward": 0.07117822021245956, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24404162168502808, 0.156942218542099, 0.25476908683776855], "policy_updates": 47530, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10300.730086524001, "contact_bce": 0.3050357401371002, "contact_force_loss": 0.03141070529818535, "terrain_level_mean": 3.2529296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47640, "total_transitions": 195133440, "num_steps_per_env": 1, "wm_loss": 0.40063580870628357, "actor_loss": -8.763955116271973, "critic_loss": 0.023640481755137444, "reward": 0.07128693908452988, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24560491740703583, 0.15676884353160858, 0.25382113456726074], "policy_updates": 47540, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10304.243560424, "contact_bce": 0.3090847134590149, "contact_force_loss": 0.03202120587229729, "terrain_level_mean": 3.251708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47650, "total_transitions": 195174400, "num_steps_per_env": 1, "wm_loss": 0.39689958095550537, "actor_loss": -8.689672470092773, "critic_loss": 0.024419071152806282, "reward": 0.07130192220211029, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24238571524620056, 0.15476347506046295, 0.2554902732372284], "policy_updates": 47550, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10307.758011415, "contact_bce": 0.3063391447067261, "contact_force_loss": 0.03160993009805679, "terrain_level_mean": 3.252197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47660, "total_transitions": 195215360, "num_steps_per_env": 1, "wm_loss": 0.3784557282924652, "actor_loss": -8.712743759155273, "critic_loss": 0.02704198658466339, "reward": 0.07159173488616943, "falls": 0, "interval_steps": 10, "velocity_mae": [0.23972967267036438, 0.15185727179050446, 0.2538714110851288], "policy_updates": 47560, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10311.275445118, "contact_bce": 0.30321329832077026, "contact_force_loss": 0.03182118386030197, "terrain_level_mean": 3.25341796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47670, "total_transitions": 195256320, "num_steps_per_env": 1, "wm_loss": 0.39215588569641113, "actor_loss": -8.802213668823242, "critic_loss": 0.018467331305146217, "reward": 0.07143036276102066, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24361540377140045, 0.15363092720508575, 0.25145938992500305], "policy_updates": 47570, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10314.792791607, "contact_bce": 0.30243244767189026, "contact_force_loss": 0.03143938630819321, "terrain_level_mean": 3.251953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.999711513519287, 0.9996806383132935, 2.9958643913269043]} {"step": 47680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47680, "total_transitions": 195297280, "num_steps_per_env": 1, "wm_loss": 0.3988451659679413, "actor_loss": -8.760541915893555, "critic_loss": 0.02194107137620449, "reward": 0.07115763425827026, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24141408503055573, 0.15504589676856995, 0.25499051809310913], "policy_updates": 47580, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10318.304877863, "contact_bce": 0.3146628439426422, "contact_force_loss": 0.03238693252205849, "terrain_level_mean": 3.251220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9955096244812012, 0.9996806383132935, 2.9958643913269043]} {"step": 47690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47690, "total_transitions": 195338240, "num_steps_per_env": 1, "wm_loss": 0.3873736262321472, "actor_loss": -8.750749588012695, "critic_loss": 0.02817048504948616, "reward": 0.07053776830434799, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2405162900686264, 0.15496180951595306, 0.2569396197795868], "policy_updates": 47590, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10321.820122553001, "contact_bce": 0.31006598472595215, "contact_force_loss": 0.03195558488368988, "terrain_level_mean": 3.251708984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9955096244812012, 0.9996806383132935, 2.9958643913269043]} {"step": 47700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47700, "total_transitions": 195379200, "num_steps_per_env": 1, "wm_loss": 0.3929002583026886, "actor_loss": -8.680099487304688, "critic_loss": 0.022249041125178337, "reward": 0.07104124873876572, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2389584183692932, 0.15379026532173157, 0.2519107758998871], "policy_updates": 47600, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10325.336286278001, "contact_bce": 0.3129853308200836, "contact_force_loss": 0.03219250217080116, "terrain_level_mean": 3.251953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9955096244812012, 0.9996806383132935, 2.9958643913269043]} {"step": 47710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47710, "total_transitions": 195420160, "num_steps_per_env": 1, "wm_loss": 0.4114421308040619, "actor_loss": -8.769500732421875, "critic_loss": 0.01953454315662384, "reward": 0.07139458507299423, "falls": 3, "interval_steps": 10, "velocity_mae": [0.23875778913497925, 0.15493156015872955, 0.2562810778617859], "policy_updates": 47610, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10328.862341423, "contact_bce": 0.3111632168292999, "contact_force_loss": 0.032824333757162094, "terrain_level_mean": 3.252685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9955096244812012, 0.9996806383132935, 2.9958643913269043]} {"step": 47720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47720, "total_transitions": 195461120, "num_steps_per_env": 1, "wm_loss": 0.4029017984867096, "actor_loss": -8.763434410095215, "critic_loss": 0.02383318543434143, "reward": 0.0716049000620842, "falls": 1, "interval_steps": 10, "velocity_mae": [0.23905014991760254, 0.1538309007883072, 0.2524625062942505], "policy_updates": 47620, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10332.385953001001, "contact_bce": 0.306650847196579, "contact_force_loss": 0.031342875212430954, "terrain_level_mean": 3.254638671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9955096244812012, 0.9999607801437378, 2.9958643913269043]} {"step": 47730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47730, "total_transitions": 195502080, "num_steps_per_env": 1, "wm_loss": 0.3918418288230896, "actor_loss": -8.753877639770508, "critic_loss": 0.02942085638642311, "reward": 0.07119899988174438, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2427959442138672, 0.15438205003738403, 0.25112006068229675], "policy_updates": 47630, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10335.913355050001, "contact_bce": 0.3083255887031555, "contact_force_loss": 0.0318681038916111, "terrain_level_mean": 3.2548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9955096244812012, 0.9999607801437378, 2.9952714443206787]} {"step": 47740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47740, "total_transitions": 195543040, "num_steps_per_env": 1, "wm_loss": 0.3903942108154297, "actor_loss": -8.745563507080078, "critic_loss": 0.020047519356012344, "reward": 0.07177989184856415, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24335502088069916, 0.15533769130706787, 0.24945686757564545], "policy_updates": 47640, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10339.43398698, "contact_bce": 0.30887311697006226, "contact_force_loss": 0.03150854632258415, "terrain_level_mean": 3.254150390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9956090450286865, 0.9999607801437378, 2.9952714443206787]} {"step": 47750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47750, "total_transitions": 195584000, "num_steps_per_env": 1, "wm_loss": 0.3829752206802368, "actor_loss": -8.771326065063477, "critic_loss": 0.019942205399274826, "reward": 0.0717896819114685, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24191172420978546, 0.1547800451517105, 0.2507043182849884], "policy_updates": 47650, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10342.96377704, "contact_bce": 0.3098946213722229, "contact_force_loss": 0.031575217843055725, "terrain_level_mean": 3.255615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9956090450286865, 0.9999607801437378, 2.9952714443206787]} {"step": 47760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47760, "total_transitions": 195624960, "num_steps_per_env": 1, "wm_loss": 0.39947113394737244, "actor_loss": -8.772289276123047, "critic_loss": 0.023671915754675865, "reward": 0.07162470370531082, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24124950170516968, 0.15501751005649567, 0.25108760595321655], "policy_updates": 47660, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10346.491576323, "contact_bce": 0.30724820494651794, "contact_force_loss": 0.032315853983163834, "terrain_level_mean": 3.256103515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.9956090450286865, 0.9999607801437378, 2.9952714443206787]} {"step": 47770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47770, "total_transitions": 195665920, "num_steps_per_env": 1, "wm_loss": 0.40627115964889526, "actor_loss": -8.718677520751953, "critic_loss": 0.02170933224260807, "reward": 0.07142616808414459, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24069060385227203, 0.15365885198116302, 0.25193366408348083], "policy_updates": 47670, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10350.012823004, "contact_bce": 0.31203868985176086, "contact_force_loss": 0.030707908794283867, "terrain_level_mean": 3.25537109375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9956090450286865, 0.9999607801437378, 2.9952714443206787]} {"step": 47780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47780, "total_transitions": 195706880, "num_steps_per_env": 1, "wm_loss": 0.4211593568325043, "actor_loss": -8.726631164550781, "critic_loss": 0.017781801521778107, "reward": 0.07083537429571152, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24520297348499298, 0.15394853055477142, 0.24906189739704132], "policy_updates": 47680, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10353.533047581, "contact_bce": 0.31452932953834534, "contact_force_loss": 0.03327126428484917, "terrain_level_mean": 3.2548828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.996189832687378, 0.9999607801437378, 2.9952714443206787]} {"step": 47790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47790, "total_transitions": 195747840, "num_steps_per_env": 1, "wm_loss": 0.39887183904647827, "actor_loss": -8.763162612915039, "critic_loss": 0.022794948890805244, "reward": 0.07061702758073807, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24712054431438446, 0.15787944197654724, 0.25259557366371155], "policy_updates": 47690, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10357.05484198, "contact_bce": 0.312762588262558, "contact_force_loss": 0.032116565853357315, "terrain_level_mean": 3.25390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.996189832687378, 0.9999607801437378, 2.9952714443206787]} {"step": 47800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47800, "total_transitions": 195788800, "num_steps_per_env": 1, "wm_loss": 0.4076154828071594, "actor_loss": -8.739337921142578, "critic_loss": 0.02758067287504673, "reward": 0.0708472952246666, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24643804132938385, 0.15795713663101196, 0.2537061870098114], "policy_updates": 47700, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10360.580048606, "contact_bce": 0.3044917583465576, "contact_force_loss": 0.032007381319999695, "terrain_level_mean": 3.254638671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350830078125, "command_abs_max": [1.996189832687378, 0.9999607801437378, 2.9952714443206787]} {"step": 47810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47810, "total_transitions": 195829760, "num_steps_per_env": 1, "wm_loss": 0.39312639832496643, "actor_loss": -8.747941970825195, "critic_loss": 0.022834105417132378, "reward": 0.0711522325873375, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24759945273399353, 0.15502677857875824, 0.2542165219783783], "policy_updates": 47710, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10364.108034959001, "contact_bce": 0.30658864974975586, "contact_force_loss": 0.031221656128764153, "terrain_level_mean": 3.255126953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.996189832687378, 0.9999607801437378, 2.9962546825408936]} {"step": 47820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47820, "total_transitions": 195870720, "num_steps_per_env": 1, "wm_loss": 0.3897296190261841, "actor_loss": -8.771188735961914, "critic_loss": 0.021626336500048637, "reward": 0.0710165724158287, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24542981386184692, 0.15404559671878815, 0.2517717778682709], "policy_updates": 47720, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10367.633225465, "contact_bce": 0.3050011694431305, "contact_force_loss": 0.031678106635808945, "terrain_level_mean": 3.255615234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.996189832687378, 0.9999607801437378, 2.9962546825408936]} {"step": 47830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47830, "total_transitions": 195911680, "num_steps_per_env": 1, "wm_loss": 0.39642274379730225, "actor_loss": -8.766519546508789, "critic_loss": 0.01826324500143528, "reward": 0.07124992460012436, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24721992015838623, 0.1551809012889862, 0.2502731680870056], "policy_updates": 47730, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10371.158795658, "contact_bce": 0.3094235062599182, "contact_force_loss": 0.03147196024656296, "terrain_level_mean": 3.25634765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9962687492370605, 0.9999607801437378, 2.9962546825408936]} {"step": 47840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47840, "total_transitions": 195952640, "num_steps_per_env": 1, "wm_loss": 0.3823402225971222, "actor_loss": -8.79610824584961, "critic_loss": 0.02273060381412506, "reward": 0.07123283296823502, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24871256947517395, 0.15699376165866852, 0.25023627281188965], "policy_updates": 47740, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10374.682757723, "contact_bce": 0.305584579706192, "contact_force_loss": 0.03139661252498627, "terrain_level_mean": 3.258056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9962687492370605, 0.9999607801437378, 2.9962546825408936]} {"step": 47850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47850, "total_transitions": 195993600, "num_steps_per_env": 1, "wm_loss": 0.3966962695121765, "actor_loss": -8.753368377685547, "critic_loss": 0.02000768855214119, "reward": 0.07109854370355606, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24916402995586395, 0.155335932970047, 0.2495548129081726], "policy_updates": 47750, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10378.198460148, "contact_bce": 0.30489015579223633, "contact_force_loss": 0.03070753440260887, "terrain_level_mean": 3.25830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9981296062469482, 0.9999607801437378, 2.9962546825408936]} {"step": 47860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47860, "total_transitions": 196034560, "num_steps_per_env": 1, "wm_loss": 0.38011491298675537, "actor_loss": -8.743942260742188, "critic_loss": 0.026433829218149185, "reward": 0.07130178064107895, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2468557059764862, 0.15174725651741028, 0.2508593797683716], "policy_updates": 47760, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10381.705284102001, "contact_bce": 0.30737486481666565, "contact_force_loss": 0.03182312473654747, "terrain_level_mean": 3.25927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9981296062469482, 0.9999607801437378, 2.9962546825408936]} {"step": 47870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47870, "total_transitions": 196075520, "num_steps_per_env": 1, "wm_loss": 0.3976432681083679, "actor_loss": -8.73720932006836, "critic_loss": 0.02204846404492855, "reward": 0.07129973918199539, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2466421276330948, 0.15401239693164825, 0.2533034086227417], "policy_updates": 47770, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10385.20982992, "contact_bce": 0.31178393959999084, "contact_force_loss": 0.031247563660144806, "terrain_level_mean": 3.259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9981296062469482, 0.9999607801437378, 2.9962546825408936]} {"step": 47880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47880, "total_transitions": 196116480, "num_steps_per_env": 1, "wm_loss": 0.376324862241745, "actor_loss": -8.775667190551758, "critic_loss": 0.021624011918902397, "reward": 0.07128195464611053, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24483980238437653, 0.15440301597118378, 0.2514313757419586], "policy_updates": 47780, "skipped_updates": 0, "invalid_env_resets": 109, "elapsed_s": 10388.731000602, "contact_bce": 0.30574312806129456, "contact_force_loss": 0.03069230169057846, "terrain_level_mean": 3.259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9981296062469482, 0.9999607801437378, 2.9962546825408936]} RECOVERY reset 1 invalid environments; first IDs=[562] {"step": 47890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47890, "total_transitions": 196157440, "num_steps_per_env": 1, "wm_loss": 0.395973801612854, "actor_loss": -8.715093612670898, "critic_loss": 0.023045523092150688, "reward": 0.07136379927396774, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24396683275699615, 0.15597288310527802, 0.2521815598011017], "policy_updates": 47790, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10392.264072080001, "contact_bce": 0.3120647668838501, "contact_force_loss": 0.03211874142289162, "terrain_level_mean": 3.260986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9981296062469482, 0.9999607801437378, 2.9962546825408936]} {"step": 47900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47900, "total_transitions": 196198400, "num_steps_per_env": 1, "wm_loss": 0.377013623714447, "actor_loss": -8.724040985107422, "critic_loss": 0.021561671048402786, "reward": 0.07096092402935028, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2464085966348648, 0.15440160036087036, 0.25378286838531494], "policy_updates": 47800, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10395.781062225, "contact_bce": 0.30522117018699646, "contact_force_loss": 0.03079323098063469, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9981296062469482, 0.9999607801437378, 2.9962546825408936]} {"step": 47910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47910, "total_transitions": 196239360, "num_steps_per_env": 1, "wm_loss": 0.37135910987854004, "actor_loss": -8.752300262451172, "critic_loss": 0.01843574456870556, "reward": 0.0706620141863823, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24728554487228394, 0.15731672942638397, 0.2578052580356598], "policy_updates": 47810, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10399.300878866, "contact_bce": 0.3007954955101013, "contact_force_loss": 0.03098704107105732, "terrain_level_mean": 3.259521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9981296062469482, 0.9999607801437378, 2.9962546825408936]} {"step": 47920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47920, "total_transitions": 196280320, "num_steps_per_env": 1, "wm_loss": 0.3770377039909363, "actor_loss": -8.723630905151367, "critic_loss": 0.02320104092359543, "reward": 0.0706697627902031, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2501220405101776, 0.15676963329315186, 0.25566911697387695], "policy_updates": 47820, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10402.823121243, "contact_bce": 0.304095059633255, "contact_force_loss": 0.031287435442209244, "terrain_level_mean": 3.2587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9981296062469482, 0.9994720220565796, 2.9962546825408936]} {"step": 47930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47930, "total_transitions": 196321280, "num_steps_per_env": 1, "wm_loss": 0.4210987091064453, "actor_loss": -8.749150276184082, "critic_loss": 0.02108764834702015, "reward": 0.07072974741458893, "falls": 2, "interval_steps": 10, "velocity_mae": [0.250612735748291, 0.15673157572746277, 0.2547019422054291], "policy_updates": 47830, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10406.343080731, "contact_bce": 0.3154411315917969, "contact_force_loss": 0.03328268975019455, "terrain_level_mean": 3.259521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9981296062469482, 0.9994720220565796, 2.9962546825408936]} {"step": 47940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47940, "total_transitions": 196362240, "num_steps_per_env": 1, "wm_loss": 0.40972405672073364, "actor_loss": -8.744479179382324, "critic_loss": 0.02468382753431797, "reward": 0.07090435922145844, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25260114669799805, 0.15904107689857483, 0.25588324666023254], "policy_updates": 47840, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10409.865694381, "contact_bce": 0.3105384111404419, "contact_force_loss": 0.03153885900974274, "terrain_level_mean": 3.260009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9981296062469482, 0.9994720220565796, 2.9962546825408936]} {"step": 47950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47950, "total_transitions": 196403200, "num_steps_per_env": 1, "wm_loss": 0.382244735956192, "actor_loss": -8.706724166870117, "critic_loss": 0.02400180883705616, "reward": 0.07086894661188126, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25433632731437683, 0.15901590883731842, 0.2574012875556946], "policy_updates": 47850, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10413.387291384, "contact_bce": 0.30402711033821106, "contact_force_loss": 0.031642988324165344, "terrain_level_mean": 3.26025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9981296062469482, 0.9994720220565796, 2.9962546825408936]} {"step": 47960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47960, "total_transitions": 196444160, "num_steps_per_env": 1, "wm_loss": 0.42500558495521545, "actor_loss": -8.73348617553711, "critic_loss": 0.02115926705300808, "reward": 0.07119565457105637, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25234225392341614, 0.15984757244586945, 0.2547359764575958], "policy_updates": 47860, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10416.908776026, "contact_bce": 0.31547921895980835, "contact_force_loss": 0.03273652866482735, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9981296062469482, 0.9994720220565796, 2.9962546825408936]} {"step": 47970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47970, "total_transitions": 196485120, "num_steps_per_env": 1, "wm_loss": 0.39529210329055786, "actor_loss": -8.724635124206543, "critic_loss": 0.028601903468370438, "reward": 0.07111692428588867, "falls": 7, "interval_steps": 10, "velocity_mae": [0.252808541059494, 0.16063903272151947, 0.2520146071910858], "policy_updates": 47870, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10420.423156058001, "contact_bce": 0.3140796422958374, "contact_force_loss": 0.03229315206408501, "terrain_level_mean": 3.260009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9987539052963257, 0.9994720220565796, 2.9962546825408936]} {"step": 47980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47980, "total_transitions": 196526080, "num_steps_per_env": 1, "wm_loss": 0.38319480419158936, "actor_loss": -8.735675811767578, "critic_loss": 0.02727302350103855, "reward": 0.07083501666784286, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25077009201049805, 0.16097614169120789, 0.25190719962120056], "policy_updates": 47880, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10423.948907198, "contact_bce": 0.308085173368454, "contact_force_loss": 0.032319575548172, "terrain_level_mean": 3.25927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9987539052963257, 0.9994720220565796, 2.9962546825408936]} {"step": 47990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 47990, "total_transitions": 196567040, "num_steps_per_env": 1, "wm_loss": 0.39777880907058716, "actor_loss": -8.718620300292969, "critic_loss": 0.031444210559129715, "reward": 0.07100279629230499, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25197193026542664, 0.16032524406909943, 0.2554897964000702], "policy_updates": 47890, "skipped_updates": 0, "invalid_env_resets": 110, "elapsed_s": 10427.463857449, "contact_bce": 0.30623671412467957, "contact_force_loss": 0.031406156718730927, "terrain_level_mean": 3.2587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9987539052963257, 0.9994720220565796, 2.9962546825408936]} RECOVERY reset 1 invalid environments; first IDs=[1858] {"step": 48000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48000, "total_transitions": 196608000, "num_steps_per_env": 1, "wm_loss": 0.4052000641822815, "actor_loss": -8.69149398803711, "critic_loss": 0.03207186982035637, "reward": 0.07058819383382797, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25406762957572937, 0.16050571203231812, 0.2608444094657898], "policy_updates": 47900, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10431.001750781, "contact_bce": 0.3113163709640503, "contact_force_loss": 0.03259576857089996, "terrain_level_mean": 3.25830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9987539052963257, 0.9994720220565796, 2.9962546825408936]} {"step": 48010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48010, "total_transitions": 196648960, "num_steps_per_env": 1, "wm_loss": 0.3802105784416199, "actor_loss": -8.750055313110352, "critic_loss": 0.025279909372329712, "reward": 0.07046770304441452, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2557678818702698, 0.15980246663093567, 0.2628917992115021], "policy_updates": 47910, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10434.548557584001, "contact_bce": 0.30780574679374695, "contact_force_loss": 0.03167276829481125, "terrain_level_mean": 3.259033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9987539052963257, 0.9994720220565796, 2.9962546825408936]} {"step": 48020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48020, "total_transitions": 196689920, "num_steps_per_env": 1, "wm_loss": 0.4326353371143341, "actor_loss": -8.734375, "critic_loss": 0.026781082153320312, "reward": 0.06971655786037445, "falls": 12, "interval_steps": 10, "velocity_mae": [0.25880342721939087, 0.1610892117023468, 0.2609042823314667], "policy_updates": 47920, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10438.3249097, "contact_bce": 0.30976852774620056, "contact_force_loss": 0.03344927355647087, "terrain_level_mean": 3.2578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9987539052963257, 0.9994720220565796, 2.995154619216919]} {"step": 48030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48030, "total_transitions": 196730880, "num_steps_per_env": 1, "wm_loss": 0.39111241698265076, "actor_loss": -8.780824661254883, "critic_loss": 0.018166719004511833, "reward": 0.07089412212371826, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2535863518714905, 0.15803714096546173, 0.25375890731811523], "policy_updates": 47930, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10441.847513844, "contact_bce": 0.30442875623703003, "contact_force_loss": 0.031350649893283844, "terrain_level_mean": 3.25732421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9987539052963257, 0.9994720220565796, 2.995154619216919]} {"step": 48040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48040, "total_transitions": 196771840, "num_steps_per_env": 1, "wm_loss": 0.41100311279296875, "actor_loss": -8.717619895935059, "critic_loss": 0.026311153545975685, "reward": 0.07108622044324875, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2509985566139221, 0.15699754655361176, 0.2523173391819], "policy_updates": 47940, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10445.367628106, "contact_bce": 0.311782568693161, "contact_force_loss": 0.031802255660295486, "terrain_level_mean": 3.2568359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.995154619216919]} {"step": 48050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48050, "total_transitions": 196812800, "num_steps_per_env": 1, "wm_loss": 0.4018774628639221, "actor_loss": -8.778779983520508, "critic_loss": 0.019137326627969742, "reward": 0.0710027664899826, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2500520646572113, 0.1566607654094696, 0.25020989775657654], "policy_updates": 47950, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10448.876138653, "contact_bce": 0.3117932975292206, "contact_force_loss": 0.032117754220962524, "terrain_level_mean": 3.256591796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.995154619216919]} {"step": 48060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48060, "total_transitions": 196853760, "num_steps_per_env": 1, "wm_loss": 0.42472773790359497, "actor_loss": -8.681618690490723, "critic_loss": 0.021212467923760414, "reward": 0.07113718241453171, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24857781827449799, 0.15751147270202637, 0.24968844652175903], "policy_updates": 47960, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10452.387581667, "contact_bce": 0.3124588131904602, "contact_force_loss": 0.03264463320374489, "terrain_level_mean": 3.257568359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.9994492530822754]} {"step": 48070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48070, "total_transitions": 196894720, "num_steps_per_env": 1, "wm_loss": 0.41513338685035706, "actor_loss": -8.677236557006836, "critic_loss": 0.027736151590943336, "reward": 0.0707290768623352, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2514210641384125, 0.159271702170372, 0.25667259097099304], "policy_updates": 47970, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10455.91143045, "contact_bce": 0.30736738443374634, "contact_force_loss": 0.03252269700169563, "terrain_level_mean": 3.25830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.9994492530822754]} {"step": 48080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48080, "total_transitions": 196935680, "num_steps_per_env": 1, "wm_loss": 0.39573416113853455, "actor_loss": -8.741043090820312, "critic_loss": 0.019374676048755646, "reward": 0.07072720676660538, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2557588815689087, 0.15814299881458282, 0.2571689188480377], "policy_updates": 47980, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10459.425803587, "contact_bce": 0.3055168092250824, "contact_force_loss": 0.031663618981838226, "terrain_level_mean": 3.25927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.9994492530822754]} {"step": 48090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48090, "total_transitions": 196976640, "num_steps_per_env": 1, "wm_loss": 0.41309115290641785, "actor_loss": -8.688305854797363, "critic_loss": 0.026071984320878983, "reward": 0.07061897963285446, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25304192304611206, 0.155954048037529, 0.25508061051368713], "policy_updates": 47990, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10462.943640396, "contact_bce": 0.3088175356388092, "contact_force_loss": 0.03234102949500084, "terrain_level_mean": 3.2587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.9994492530822754]} {"step": 48100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48100, "total_transitions": 197017600, "num_steps_per_env": 1, "wm_loss": 0.40330466628074646, "actor_loss": -8.703903198242188, "critic_loss": 0.019386161118745804, "reward": 0.07024472951889038, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2530120015144348, 0.15567289292812347, 0.2541765868663788], "policy_updates": 48000, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10466.451531404, "contact_bce": 0.3079608678817749, "contact_force_loss": 0.031153922900557518, "terrain_level_mean": 3.259033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.9994492530822754]} {"step": 48110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48110, "total_transitions": 197058560, "num_steps_per_env": 1, "wm_loss": 0.408393919467926, "actor_loss": -8.765342712402344, "critic_loss": 0.02597256377339363, "reward": 0.07009073346853256, "falls": 7, "interval_steps": 10, "velocity_mae": [0.249637171626091, 0.15589159727096558, 0.24980956315994263], "policy_updates": 48010, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10469.966490723, "contact_bce": 0.30860307812690735, "contact_force_loss": 0.03180268779397011, "terrain_level_mean": 3.25830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.9994492530822754]} {"step": 48120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48120, "total_transitions": 197099520, "num_steps_per_env": 1, "wm_loss": 0.41506847739219666, "actor_loss": -8.764704704284668, "critic_loss": 0.021051151677966118, "reward": 0.07054654508829117, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2473585456609726, 0.15670442581176758, 0.24712036550045013], "policy_updates": 48020, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10473.4925604, "contact_bce": 0.30914339423179626, "contact_force_loss": 0.03186875581741333, "terrain_level_mean": 3.25830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.9987539052963257, 0.9997601509094238, 2.9994492530822754]} {"step": 48130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48130, "total_transitions": 197140480, "num_steps_per_env": 1, "wm_loss": 0.39539146423339844, "actor_loss": -8.730359077453613, "critic_loss": 0.03846590593457222, "reward": 0.07098699361085892, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24544742703437805, 0.15554022789001465, 0.25000831484794617], "policy_updates": 48030, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10477.015057875, "contact_bce": 0.3069818913936615, "contact_force_loss": 0.032074421644210815, "terrain_level_mean": 3.2587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9987539052963257, 0.9999192357063293, 2.9994492530822754]} {"step": 48140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48140, "total_transitions": 197181440, "num_steps_per_env": 1, "wm_loss": 0.4077072739601135, "actor_loss": -8.721835136413574, "critic_loss": 0.024803882464766502, "reward": 0.07100795954465866, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24572429060935974, 0.15729102492332458, 0.25027111172676086], "policy_updates": 48040, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10480.532778667, "contact_bce": 0.3122597634792328, "contact_force_loss": 0.03184342011809349, "terrain_level_mean": 3.2587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9987539052963257, 0.9999192357063293, 2.9994492530822754]} {"step": 48150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48150, "total_transitions": 197222400, "num_steps_per_env": 1, "wm_loss": 0.4006861746311188, "actor_loss": -8.740874290466309, "critic_loss": 0.026471441611647606, "reward": 0.07103382050991058, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24842675030231476, 0.15758897364139557, 0.2529882490634918], "policy_updates": 48050, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10484.056419176, "contact_bce": 0.3121091425418854, "contact_force_loss": 0.03204089403152466, "terrain_level_mean": 3.25830078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9987539052963257, 0.9999192357063293, 2.9994492530822754]} {"step": 48160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48160, "total_transitions": 197263360, "num_steps_per_env": 1, "wm_loss": 0.39767101407051086, "actor_loss": -8.746047973632812, "critic_loss": 0.02545507811009884, "reward": 0.0711427703499794, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24550120532512665, 0.15551763772964478, 0.2510634958744049], "policy_updates": 48060, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10487.567557034, "contact_bce": 0.3113498389720917, "contact_force_loss": 0.032543983310461044, "terrain_level_mean": 3.258544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353515625, "command_abs_max": [1.9987539052963257, 0.9999192357063293, 2.9994492530822754]} {"step": 48170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48170, "total_transitions": 197304320, "num_steps_per_env": 1, "wm_loss": 0.37014904618263245, "actor_loss": -8.708719253540039, "critic_loss": 0.022841457277536392, "reward": 0.07076756656169891, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2497146725654602, 0.15350331366062164, 0.254219651222229], "policy_updates": 48070, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10491.092095253001, "contact_bce": 0.305528461933136, "contact_force_loss": 0.03058205172419548, "terrain_level_mean": 3.258544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9987539052963257, 0.9999192357063293, 2.9994492530822754]} {"step": 48180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48180, "total_transitions": 197345280, "num_steps_per_env": 1, "wm_loss": 0.39537736773490906, "actor_loss": -8.750200271606445, "critic_loss": 0.022466110065579414, "reward": 0.07093004137277603, "falls": 1, "interval_steps": 10, "velocity_mae": [0.25043681263923645, 0.15288449823856354, 0.2496795803308487], "policy_updates": 48080, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10494.624877108, "contact_bce": 0.31149259209632874, "contact_force_loss": 0.03163580968976021, "terrain_level_mean": 3.259033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9987539052963257, 0.9999192357063293, 2.9994492530822754]} {"step": 48190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48190, "total_transitions": 197386240, "num_steps_per_env": 1, "wm_loss": 0.39055341482162476, "actor_loss": -8.749412536621094, "critic_loss": 0.033961642533540726, "reward": 0.07096519321203232, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2526871860027313, 0.15310260653495789, 0.25231224298477173], "policy_updates": 48090, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10498.150346447, "contact_bce": 0.309176504611969, "contact_force_loss": 0.03141628950834274, "terrain_level_mean": 3.260009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35693359375, "command_abs_max": [1.9987539052963257, 0.9999192357063293, 2.9994492530822754]} {"step": 48200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48200, "total_transitions": 197427200, "num_steps_per_env": 1, "wm_loss": 0.3801952004432678, "actor_loss": -8.730268478393555, "critic_loss": 0.019759783521294594, "reward": 0.0704348012804985, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2521045506000519, 0.154914990067482, 0.2530044913291931], "policy_updates": 48100, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10501.674611995, "contact_bce": 0.30846187472343445, "contact_force_loss": 0.03099282830953598, "terrain_level_mean": 3.26123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359619140625, "command_abs_max": [1.9976959228515625, 0.9999192357063293, 2.9994492530822754]} {"step": 48210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48210, "total_transitions": 197468160, "num_steps_per_env": 1, "wm_loss": 0.39954209327697754, "actor_loss": -8.71839714050293, "critic_loss": 0.02641219273209572, "reward": 0.07040126621723175, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24852851033210754, 0.15703076124191284, 0.24935759603977203], "policy_updates": 48110, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10505.198191935, "contact_bce": 0.30647575855255127, "contact_force_loss": 0.0319349467754364, "terrain_level_mean": 3.261474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35888671875, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48220, "total_transitions": 197509120, "num_steps_per_env": 1, "wm_loss": 0.402989000082016, "actor_loss": -8.729815483093262, "critic_loss": 0.03018452785909176, "reward": 0.07065406441688538, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24073919653892517, 0.15570157766342163, 0.24734348058700562], "policy_updates": 48120, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10508.724354972, "contact_bce": 0.307372510433197, "contact_force_loss": 0.032508932054042816, "terrain_level_mean": 3.26123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35888671875, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48230, "total_transitions": 197550080, "num_steps_per_env": 1, "wm_loss": 0.4490879774093628, "actor_loss": -8.752763748168945, "critic_loss": 0.0271521657705307, "reward": 0.07106224447488785, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2378547340631485, 0.1559503674507141, 0.2499009370803833], "policy_updates": 48130, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10512.23917739, "contact_bce": 0.3108042776584625, "contact_force_loss": 0.03231602907180786, "terrain_level_mean": 3.26220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.359130859375, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48240, "total_transitions": 197591040, "num_steps_per_env": 1, "wm_loss": 0.4117286801338196, "actor_loss": -8.690006256103516, "critic_loss": 0.02059314027428627, "reward": 0.0709545910358429, "falls": 2, "interval_steps": 10, "velocity_mae": [0.23968249559402466, 0.1543836146593094, 0.2538262903690338], "policy_updates": 48140, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10515.758608056001, "contact_bce": 0.30798450112342834, "contact_force_loss": 0.032167404890060425, "terrain_level_mean": 3.262939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3603515625, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48250, "total_transitions": 197632000, "num_steps_per_env": 1, "wm_loss": 0.38186994194984436, "actor_loss": -8.720144271850586, "critic_loss": 0.025748660787940025, "reward": 0.07103651016950607, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24147439002990723, 0.15468740463256836, 0.25445449352264404], "policy_updates": 48150, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10519.283140598001, "contact_bce": 0.3104981780052185, "contact_force_loss": 0.03181142359972, "terrain_level_mean": 3.2626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.361328125, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48260, "total_transitions": 197672960, "num_steps_per_env": 1, "wm_loss": 0.410223126411438, "actor_loss": -8.781103134155273, "critic_loss": 0.019508181139826775, "reward": 0.0710323229432106, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24648228287696838, 0.154392272233963, 0.25193580985069275], "policy_updates": 48160, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10522.799001355, "contact_bce": 0.3107690215110779, "contact_force_loss": 0.03252523019909859, "terrain_level_mean": 3.2626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.36083984375, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48270, "total_transitions": 197713920, "num_steps_per_env": 1, "wm_loss": 0.39153414964675903, "actor_loss": -8.733530044555664, "critic_loss": 0.02703750692307949, "reward": 0.07108952105045319, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24675863981246948, 0.15643514692783356, 0.24842821061611176], "policy_updates": 48170, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10526.307223214, "contact_bce": 0.3049725294113159, "contact_force_loss": 0.03170505166053772, "terrain_level_mean": 3.26220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3603515625, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48280, "total_transitions": 197754880, "num_steps_per_env": 1, "wm_loss": 0.3855275809764862, "actor_loss": -8.655439376831055, "critic_loss": 0.031305115669965744, "reward": 0.07088790833950043, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24910061061382294, 0.15997084975242615, 0.2534205913543701], "policy_updates": 48180, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10529.829589999, "contact_bce": 0.3081667721271515, "contact_force_loss": 0.03205793723464012, "terrain_level_mean": 3.26318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3603515625, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48290, "total_transitions": 197795840, "num_steps_per_env": 1, "wm_loss": 0.4032691419124603, "actor_loss": -8.691398620605469, "critic_loss": 0.023540183901786804, "reward": 0.07088878005743027, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2510761022567749, 0.15812617540359497, 0.254862904548645], "policy_updates": 48190, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10533.33588891, "contact_bce": 0.31049326062202454, "contact_force_loss": 0.03204117715358734, "terrain_level_mean": 3.262939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48300, "total_transitions": 197836800, "num_steps_per_env": 1, "wm_loss": 0.4065982699394226, "actor_loss": -8.761356353759766, "critic_loss": 0.020298272371292114, "reward": 0.07087642699480057, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24684520065784454, 0.16046622395515442, 0.25635287165641785], "policy_updates": 48200, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10536.85621154, "contact_bce": 0.3165770471096039, "contact_force_loss": 0.03282115235924721, "terrain_level_mean": 3.263916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48310, "total_transitions": 197877760, "num_steps_per_env": 1, "wm_loss": 0.39285707473754883, "actor_loss": -8.727418899536133, "critic_loss": 0.02242255210876465, "reward": 0.07096295803785324, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24823865294456482, 0.15940365195274353, 0.2513839304447174], "policy_updates": 48210, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10540.35536849, "contact_bce": 0.31831520795822144, "contact_force_loss": 0.03208279609680176, "terrain_level_mean": 3.264892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48320, "total_transitions": 197918720, "num_steps_per_env": 1, "wm_loss": 0.39431440830230713, "actor_loss": -8.688667297363281, "critic_loss": 0.024238863959908485, "reward": 0.07071936875581741, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24741502106189728, 0.15853677690029144, 0.2494378685951233], "policy_updates": 48220, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10543.878210747, "contact_bce": 0.3071683347225189, "contact_force_loss": 0.03230949118733406, "terrain_level_mean": 3.264892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48330, "total_transitions": 197959680, "num_steps_per_env": 1, "wm_loss": 0.40847960114479065, "actor_loss": -8.678882598876953, "critic_loss": 0.031235575675964355, "reward": 0.07111483067274094, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24741709232330322, 0.15659120678901672, 0.25311872363090515], "policy_updates": 48230, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10547.392035657, "contact_bce": 0.315775603055954, "contact_force_loss": 0.033041149377822876, "terrain_level_mean": 3.265380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.999065637588501, 0.9999192357063293, 2.9994492530822754]} {"step": 48340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48340, "total_transitions": 198000640, "num_steps_per_env": 1, "wm_loss": 0.40697357058525085, "actor_loss": -8.700688362121582, "critic_loss": 0.024348130449652672, "reward": 0.0710945874452591, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2469015121459961, 0.15672124922275543, 0.2496296465396881], "policy_updates": 48240, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10550.923732000001, "contact_bce": 0.3137386739253998, "contact_force_loss": 0.03246696665883064, "terrain_level_mean": 3.26513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9994492530822754]} {"step": 48350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48350, "total_transitions": 198041600, "num_steps_per_env": 1, "wm_loss": 0.39339888095855713, "actor_loss": -8.679341316223145, "critic_loss": 0.030473846942186356, "reward": 0.07064478099346161, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24802729487419128, 0.1576974093914032, 0.25405004620552063], "policy_updates": 48250, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10554.452061080001, "contact_bce": 0.31350967288017273, "contact_force_loss": 0.03220982849597931, "terrain_level_mean": 3.26611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9994492530822754]} {"step": 48360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48360, "total_transitions": 198082560, "num_steps_per_env": 1, "wm_loss": 0.38723626732826233, "actor_loss": -8.740822792053223, "critic_loss": 0.027046451345086098, "reward": 0.07075192034244537, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24737636744976044, 0.15519188344478607, 0.2544681131839752], "policy_updates": 48260, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10557.978407472001, "contact_bce": 0.3095560669898987, "contact_force_loss": 0.031617119908332825, "terrain_level_mean": 3.268310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352294921875, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9975802898406982]} {"step": 48370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48370, "total_transitions": 198123520, "num_steps_per_env": 1, "wm_loss": 0.44391027092933655, "actor_loss": -8.75353717803955, "critic_loss": 0.023464374244213104, "reward": 0.07026728242635727, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25254034996032715, 0.15662409365177155, 0.25652503967285156], "policy_updates": 48270, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10561.507476775001, "contact_bce": 0.3154561519622803, "contact_force_loss": 0.03283096104860306, "terrain_level_mean": 3.26806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35546875, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9975802898406982]} {"step": 48380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48380, "total_transitions": 198164480, "num_steps_per_env": 1, "wm_loss": 0.38259953260421753, "actor_loss": -8.707601547241211, "critic_loss": 0.02322571910917759, "reward": 0.07023562490940094, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25225889682769775, 0.15742969512939453, 0.2550499141216278], "policy_updates": 48280, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10565.035263528, "contact_bce": 0.31007930636405945, "contact_force_loss": 0.031752053648233414, "terrain_level_mean": 3.26806640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9975802898406982]} {"step": 48390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48390, "total_transitions": 198205440, "num_steps_per_env": 1, "wm_loss": 0.4057907462120056, "actor_loss": -8.710668563842773, "critic_loss": 0.026077240705490112, "reward": 0.07035592198371887, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24944397807121277, 0.15810850262641907, 0.25431758165359497], "policy_updates": 48290, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10568.563608968001, "contact_bce": 0.3113120496273041, "contact_force_loss": 0.03253515064716339, "terrain_level_mean": 3.268798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.357177734375, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9975802898406982]} {"step": 48400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48400, "total_transitions": 198246400, "num_steps_per_env": 1, "wm_loss": 0.42364707589149475, "actor_loss": -8.67776870727539, "critic_loss": 0.032264258712530136, "reward": 0.07090786099433899, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24931474030017853, 0.1574341058731079, 0.2530704140663147], "policy_updates": 48300, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10572.084983627, "contact_bce": 0.3133813142776489, "contact_force_loss": 0.03297805041074753, "terrain_level_mean": 3.270751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9975802898406982]} {"step": 48410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48410, "total_transitions": 198287360, "num_steps_per_env": 1, "wm_loss": 0.4193681478500366, "actor_loss": -8.67237377166748, "critic_loss": 0.027012718841433525, "reward": 0.0710393637418747, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24825410544872284, 0.15714925527572632, 0.2532466948032379], "policy_updates": 48310, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10575.607592082, "contact_bce": 0.3090430498123169, "contact_force_loss": 0.03253059461712837, "terrain_level_mean": 3.27001953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35791015625, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9975802898406982]} {"step": 48420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48420, "total_transitions": 198328320, "num_steps_per_env": 1, "wm_loss": 0.41339224576950073, "actor_loss": -8.705938339233398, "critic_loss": 0.03009445033967495, "reward": 0.07078956812620163, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2455155998468399, 0.1556965857744217, 0.2530355751514435], "policy_updates": 48320, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10579.127961597, "contact_bce": 0.31467798352241516, "contact_force_loss": 0.03286879137158394, "terrain_level_mean": 3.26953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354248046875, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9959816932678223]} {"step": 48430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48430, "total_transitions": 198369280, "num_steps_per_env": 1, "wm_loss": 0.40660855174064636, "actor_loss": -8.732851028442383, "critic_loss": 0.02089112065732479, "reward": 0.0703640878200531, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25141778588294983, 0.15585680305957794, 0.25470319390296936], "policy_updates": 48330, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10582.644528244, "contact_bce": 0.3118784427642822, "contact_force_loss": 0.03202755004167557, "terrain_level_mean": 3.26904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.9959816932678223]} {"step": 48440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48440, "total_transitions": 198410240, "num_steps_per_env": 1, "wm_loss": 0.39563116431236267, "actor_loss": -8.712764739990234, "critic_loss": 0.027179265394806862, "reward": 0.07035820931196213, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25617149472236633, 0.15921606123447418, 0.26015982031822205], "policy_updates": 48340, "skipped_updates": 0, "invalid_env_resets": 111, "elapsed_s": 10586.14887096, "contact_bce": 0.3060336410999298, "contact_force_loss": 0.03234942629933357, "terrain_level_mean": 3.268798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9993929862976074, 0.9999192357063293, 2.999605178833008]} RECOVERY reset 1 invalid environments; first IDs=[1158] {"step": 48450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48450, "total_transitions": 198451200, "num_steps_per_env": 1, "wm_loss": 0.40007397532463074, "actor_loss": -8.742513656616211, "critic_loss": 0.022513801231980324, "reward": 0.07013197988271713, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25682809948921204, 0.16378812491893768, 0.26555266976356506], "policy_updates": 48350, "skipped_updates": 0, "invalid_env_resets": 112, "elapsed_s": 10589.666313425001, "contact_bce": 0.31243500113487244, "contact_force_loss": 0.03199509158730507, "terrain_level_mean": 3.26953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9993929862976074, 0.999182939529419, 2.999605178833008]} {"step": 48460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48460, "total_transitions": 198492160, "num_steps_per_env": 1, "wm_loss": 0.4205034077167511, "actor_loss": -8.691202163696289, "critic_loss": 0.025036944076418877, "reward": 0.07059136778116226, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25497952103614807, 0.16202685236930847, 0.25822585821151733], "policy_updates": 48360, "skipped_updates": 0, "invalid_env_resets": 112, "elapsed_s": 10593.187823607, "contact_bce": 0.3106616139411926, "contact_force_loss": 0.03188403695821762, "terrain_level_mean": 3.268798828125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} {"step": 48470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48470, "total_transitions": 198533120, "num_steps_per_env": 1, "wm_loss": 0.44113633036613464, "actor_loss": -8.700032234191895, "critic_loss": 0.03350403532385826, "reward": 0.07077846676111221, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2541066110134125, 0.16234074532985687, 0.2545204758644104], "policy_updates": 48370, "skipped_updates": 0, "invalid_env_resets": 112, "elapsed_s": 10596.707912, "contact_bce": 0.3126984238624573, "contact_force_loss": 0.03208163380622864, "terrain_level_mean": 3.267822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3447265625, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} {"step": 48480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48480, "total_transitions": 198574080, "num_steps_per_env": 1, "wm_loss": 0.41792359948158264, "actor_loss": -8.714527130126953, "critic_loss": 0.0162645410746336, "reward": 0.07067693024873734, "falls": 9, "interval_steps": 10, "velocity_mae": [0.2509184181690216, 0.15987654030323029, 0.25351446866989136], "policy_updates": 48380, "skipped_updates": 0, "invalid_env_resets": 112, "elapsed_s": 10600.228387511, "contact_bce": 0.30621060729026794, "contact_force_loss": 0.032172247767448425, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} {"step": 48490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48490, "total_transitions": 198615040, "num_steps_per_env": 1, "wm_loss": 0.4175683856010437, "actor_loss": -8.69261360168457, "critic_loss": 0.02654089964926243, "reward": 0.07093916833400726, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2535179853439331, 0.15673688054084778, 0.2503776252269745], "policy_updates": 48390, "skipped_updates": 0, "invalid_env_resets": 112, "elapsed_s": 10603.745658525, "contact_bce": 0.30921217799186707, "contact_force_loss": 0.03266482055187225, "terrain_level_mean": 3.26611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} {"step": 48500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48500, "total_transitions": 198656000, "num_steps_per_env": 1, "wm_loss": 0.4201186001300812, "actor_loss": -8.6314058303833, "critic_loss": 0.030393658205866814, "reward": 0.07113955914974213, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2537453770637512, 0.15816225111484528, 0.2529503107070923], "policy_updates": 48400, "skipped_updates": 0, "invalid_env_resets": 112, "elapsed_s": 10607.264781303, "contact_bce": 0.3100111782550812, "contact_force_loss": 0.032251957803964615, "terrain_level_mean": 3.2666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339599609375, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} RECOVERY reset 1 invalid environments; first IDs=[1876] {"step": 48510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48510, "total_transitions": 198696960, "num_steps_per_env": 1, "wm_loss": 0.43755024671554565, "actor_loss": -8.686409950256348, "critic_loss": 0.03178105503320694, "reward": 0.0713406652212143, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2493501901626587, 0.1590038239955902, 0.2522357404232025], "policy_updates": 48410, "skipped_updates": 0, "invalid_env_resets": 113, "elapsed_s": 10610.822989761, "contact_bce": 0.31982165575027466, "contact_force_loss": 0.03315227851271629, "terrain_level_mean": 3.2666015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337890625, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} {"step": 48520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48520, "total_transitions": 198737920, "num_steps_per_env": 1, "wm_loss": 0.42149585485458374, "actor_loss": -8.731675148010254, "critic_loss": 0.022208979353308678, "reward": 0.07117991149425507, "falls": 0, "interval_steps": 10, "velocity_mae": [0.2487415224313736, 0.15637925267219543, 0.2549867630004883], "policy_updates": 48420, "skipped_updates": 0, "invalid_env_resets": 113, "elapsed_s": 10614.575722441, "contact_bce": 0.31299254298210144, "contact_force_loss": 0.032762330025434494, "terrain_level_mean": 3.267333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} {"step": 48530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48530, "total_transitions": 198778880, "num_steps_per_env": 1, "wm_loss": 0.4027581214904785, "actor_loss": -8.737545013427734, "critic_loss": 0.032048746943473816, "reward": 0.07113543897867203, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25024521350860596, 0.155325785279274, 0.2545826733112335], "policy_updates": 48430, "skipped_updates": 0, "invalid_env_resets": 113, "elapsed_s": 10618.097678505, "contact_bce": 0.3107462525367737, "contact_force_loss": 0.03243550658226013, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9993929862976074, 0.9998463988304138, 2.999605178833008]} RECOVERY reset 1 invalid environments; first IDs=[872] {"step": 48540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48540, "total_transitions": 198819840, "num_steps_per_env": 1, "wm_loss": 0.4098770022392273, "actor_loss": -8.706376075744629, "critic_loss": 0.021258393302559853, "reward": 0.07140492647886276, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2490672916173935, 0.15371057391166687, 0.24848872423171997], "policy_updates": 48440, "skipped_updates": 0, "invalid_env_resets": 114, "elapsed_s": 10621.637122221, "contact_bce": 0.3084070086479187, "contact_force_loss": 0.03257416561245918, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33203125, "command_abs_max": [1.9969120025634766, 0.9998463988304138, 2.999605178833008]} {"step": 48550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48550, "total_transitions": 198860800, "num_steps_per_env": 1, "wm_loss": 0.42699626088142395, "actor_loss": -8.721104621887207, "critic_loss": 0.0243561789393425, "reward": 0.07118135690689087, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24692413210868835, 0.15509915351867676, 0.2491464763879776], "policy_updates": 48450, "skipped_updates": 0, "invalid_env_resets": 114, "elapsed_s": 10625.160160517, "contact_bce": 0.31238171458244324, "contact_force_loss": 0.032662149518728256, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.330078125, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} {"step": 48560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48560, "total_transitions": 198901760, "num_steps_per_env": 1, "wm_loss": 0.4192313551902771, "actor_loss": -8.6913480758667, "critic_loss": 0.026765814051032066, "reward": 0.07144389301538467, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24385365843772888, 0.1555684357881546, 0.24591973423957825], "policy_updates": 48460, "skipped_updates": 0, "invalid_env_resets": 114, "elapsed_s": 10628.681500029, "contact_bce": 0.3167349100112915, "contact_force_loss": 0.033419329673051834, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3271484375, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} {"step": 48570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48570, "total_transitions": 198942720, "num_steps_per_env": 1, "wm_loss": 0.4098951816558838, "actor_loss": -8.683319091796875, "critic_loss": 0.020600125193595886, "reward": 0.07101389020681381, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24476222693920135, 0.15536771714687347, 0.2505955994129181], "policy_updates": 48470, "skipped_updates": 0, "invalid_env_resets": 114, "elapsed_s": 10632.197425244001, "contact_bce": 0.3083387315273285, "contact_force_loss": 0.03234424442052841, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.325439453125, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} {"step": 48580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48580, "total_transitions": 198983680, "num_steps_per_env": 1, "wm_loss": 0.40318936109542847, "actor_loss": -8.721353530883789, "critic_loss": 0.024478651583194733, "reward": 0.0715109184384346, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24086429178714752, 0.1541115641593933, 0.2506882846355438], "policy_updates": 48480, "skipped_updates": 0, "invalid_env_resets": 114, "elapsed_s": 10635.713108607, "contact_bce": 0.312008261680603, "contact_force_loss": 0.03250579908490181, "terrain_level_mean": 3.267822265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32666015625, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} RECOVERY reset 1 invalid environments; first IDs=[2237] {"step": 48590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48590, "total_transitions": 199024640, "num_steps_per_env": 1, "wm_loss": 0.4016583561897278, "actor_loss": -8.70656967163086, "critic_loss": 0.02481680177152157, "reward": 0.07174815982580185, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24010364711284637, 0.15143133699893951, 0.24835491180419922], "policy_updates": 48490, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10639.25145173, "contact_bce": 0.31159040331840515, "contact_force_loss": 0.03216252848505974, "terrain_level_mean": 3.2685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3251953125, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} {"step": 48600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48600, "total_transitions": 199065600, "num_steps_per_env": 1, "wm_loss": 0.4187783896923065, "actor_loss": -8.740106582641602, "critic_loss": 0.023457607254385948, "reward": 0.07154573500156403, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24355271458625793, 0.15314701199531555, 0.24753256142139435], "policy_updates": 48500, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10642.766192328001, "contact_bce": 0.3106763958930969, "contact_force_loss": 0.033791281282901764, "terrain_level_mean": 3.269775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.322998046875, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_048600.mp4 {"step": 48610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48610, "total_transitions": 199106560, "num_steps_per_env": 1, "wm_loss": 0.379018634557724, "actor_loss": -8.733441352844238, "critic_loss": 0.026840800419449806, "reward": 0.07150942087173462, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24348846077919006, 0.1549610048532486, 0.24802155792713165], "policy_updates": 48510, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10651.951528964, "contact_bce": 0.3080102503299713, "contact_force_loss": 0.0318186953663826, "terrain_level_mean": 3.2705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32421875, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} {"step": 48620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48620, "total_transitions": 199147520, "num_steps_per_env": 1, "wm_loss": 0.4163481295108795, "actor_loss": -8.689340591430664, "critic_loss": 0.027708297595381737, "reward": 0.07147979736328125, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24199244379997253, 0.15444272756576538, 0.24716128408908844], "policy_updates": 48520, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10655.470012257001, "contact_bce": 0.31019172072410583, "contact_force_loss": 0.031968846917152405, "terrain_level_mean": 3.270751953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.323486328125, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} {"step": 48630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48630, "total_transitions": 199188480, "num_steps_per_env": 1, "wm_loss": 0.4033532738685608, "actor_loss": -8.73604965209961, "critic_loss": 0.030765367671847343, "reward": 0.07173066586256027, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24398085474967957, 0.153504878282547, 0.24886009097099304], "policy_updates": 48530, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10658.990719298, "contact_bce": 0.3130720555782318, "contact_force_loss": 0.03199553117156029, "terrain_level_mean": 3.27099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.32421875, "command_abs_max": [1.9985499382019043, 0.9998463988304138, 2.999605178833008]} {"step": 48640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48640, "total_transitions": 199229440, "num_steps_per_env": 1, "wm_loss": 0.4296225905418396, "actor_loss": -8.732702255249023, "critic_loss": 0.023858562111854553, "reward": 0.07169544696807861, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23989492654800415, 0.15481022000312805, 0.24918018281459808], "policy_updates": 48540, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10662.510094529001, "contact_bce": 0.314020574092865, "contact_force_loss": 0.03309324383735657, "terrain_level_mean": 3.271728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326416015625, "command_abs_max": [1.991821050643921, 0.9998463988304138, 2.999605178833008]} {"step": 48650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48650, "total_transitions": 199270400, "num_steps_per_env": 1, "wm_loss": 0.3771018087863922, "actor_loss": -8.703657150268555, "critic_loss": 0.03360019251704216, "reward": 0.07178045064210892, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2418733835220337, 0.15432323515415192, 0.24896612763404846], "policy_updates": 48550, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10666.023457261, "contact_bce": 0.3113665282726288, "contact_force_loss": 0.03208427131175995, "terrain_level_mean": 3.27197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.326416015625, "command_abs_max": [1.991821050643921, 0.9998463988304138, 2.999605178833008]} {"step": 48660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48660, "total_transitions": 199311360, "num_steps_per_env": 1, "wm_loss": 0.4235899746417999, "actor_loss": -8.766071319580078, "critic_loss": 0.01946616731584072, "reward": 0.07124953716993332, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24734538793563843, 0.15549802780151367, 0.2528635561466217], "policy_updates": 48560, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10669.536121245, "contact_bce": 0.31169670820236206, "contact_force_loss": 0.03194158524274826, "terrain_level_mean": 3.271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3291015625, "command_abs_max": [1.991821050643921, 0.9998463988304138, 2.999605178833008]} {"step": 48670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48670, "total_transitions": 199352320, "num_steps_per_env": 1, "wm_loss": 0.3768269121646881, "actor_loss": -8.7081298828125, "critic_loss": 0.02734917402267456, "reward": 0.07124277204275131, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24730272591114044, 0.1539703607559204, 0.2518470883369446], "policy_updates": 48570, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10673.048442004001, "contact_bce": 0.3094981014728546, "contact_force_loss": 0.03164905309677124, "terrain_level_mean": 3.27197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.991821050643921, 0.9998463988304138, 2.999605178833008]} {"step": 48680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48680, "total_transitions": 199393280, "num_steps_per_env": 1, "wm_loss": 0.4225725829601288, "actor_loss": -8.729650497436523, "critic_loss": 0.018961844965815544, "reward": 0.07121225446462631, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24817626178264618, 0.15318453311920166, 0.25828391313552856], "policy_updates": 48580, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10676.551011288, "contact_bce": 0.30832985043525696, "contact_force_loss": 0.032638538628816605, "terrain_level_mean": 3.2724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332275390625, "command_abs_max": [1.991821050643921, 0.9998463988304138, 2.999605178833008]} {"step": 48690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48690, "total_transitions": 199434240, "num_steps_per_env": 1, "wm_loss": 0.4132045805454254, "actor_loss": -8.728766441345215, "critic_loss": 0.02420022152364254, "reward": 0.07093648612499237, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24693821370601654, 0.15625238418579102, 0.26046010851860046], "policy_updates": 48590, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10680.063249572, "contact_bce": 0.3125995397567749, "contact_force_loss": 0.03236423060297966, "terrain_level_mean": 3.272216796875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.331298828125, "command_abs_max": [1.991821050643921, 0.9998463988304138, 2.999605178833008]} {"step": 48700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48700, "total_transitions": 199475200, "num_steps_per_env": 1, "wm_loss": 0.41821637749671936, "actor_loss": -8.721912384033203, "critic_loss": 0.023191118612885475, "reward": 0.06988207250833511, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25239062309265137, 0.1576600819826126, 0.2588801085948944], "policy_updates": 48600, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10683.574292947, "contact_bce": 0.31064894795417786, "contact_force_loss": 0.03256582096219063, "terrain_level_mean": 3.27197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.332763671875, "command_abs_max": [1.992800235748291, 0.9998463988304138, 2.999605178833008]} {"step": 48710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48710, "total_transitions": 199516160, "num_steps_per_env": 1, "wm_loss": 0.4265941083431244, "actor_loss": -8.701675415039062, "critic_loss": 0.031366001814603806, "reward": 0.07056693732738495, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2502800524234772, 0.15858156979084015, 0.2538486123085022], "policy_updates": 48610, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10687.082500646, "contact_bce": 0.31577304005622864, "contact_force_loss": 0.033361803740262985, "terrain_level_mean": 3.27197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33349609375, "command_abs_max": [1.992800235748291, 0.9998463988304138, 2.999605178833008]} {"step": 48720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48720, "total_transitions": 199557120, "num_steps_per_env": 1, "wm_loss": 0.40907278656959534, "actor_loss": -8.712552070617676, "critic_loss": 0.02875618450343609, "reward": 0.07097131013870239, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24554984271526337, 0.1568090319633484, 0.2526325285434723], "policy_updates": 48620, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10690.600857819001, "contact_bce": 0.3150251805782318, "contact_force_loss": 0.032299041748046875, "terrain_level_mean": 3.271728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.99422287940979, 0.9998463988304138, 2.999605178833008]} {"step": 48730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48730, "total_transitions": 199598080, "num_steps_per_env": 1, "wm_loss": 0.4167640805244446, "actor_loss": -8.720916748046875, "critic_loss": 0.021981457248330116, "reward": 0.07097535580396652, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24518942832946777, 0.15670587122440338, 0.2534712255001068], "policy_updates": 48630, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10694.105566749, "contact_bce": 0.3103770613670349, "contact_force_loss": 0.03260774537920952, "terrain_level_mean": 3.27294921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.99422287940979, 0.9997985363006592, 2.999605178833008]} {"step": 48740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48740, "total_transitions": 199639040, "num_steps_per_env": 1, "wm_loss": 0.4263900816440582, "actor_loss": -8.702146530151367, "critic_loss": 0.029143517836928368, "reward": 0.07091675698757172, "falls": 10, "interval_steps": 10, "velocity_mae": [0.24840274453163147, 0.15791332721710205, 0.25376373529434204], "policy_updates": 48640, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10697.618697527001, "contact_bce": 0.3079931437969208, "contact_force_loss": 0.0321187786757946, "terrain_level_mean": 3.27099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.338623046875, "command_abs_max": [1.99422287940979, 0.9997985363006592, 2.997563362121582]} {"step": 48750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48750, "total_transitions": 199680000, "num_steps_per_env": 1, "wm_loss": 0.40851524472236633, "actor_loss": -8.753927230834961, "critic_loss": 0.021152686327695847, "reward": 0.07133648544549942, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2530946135520935, 0.15740163624286652, 0.25343549251556396], "policy_updates": 48650, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10701.13456238, "contact_bce": 0.30660659074783325, "contact_force_loss": 0.03212840482592583, "terrain_level_mean": 3.2705078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9995453357696533, 0.9997985363006592, 2.997563362121582]} {"step": 48760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48760, "total_transitions": 199720960, "num_steps_per_env": 1, "wm_loss": 0.4217851459980011, "actor_loss": -8.720672607421875, "critic_loss": 0.02097674086689949, "reward": 0.07077480107545853, "falls": 2, "interval_steps": 10, "velocity_mae": [0.25526943802833557, 0.1577640026807785, 0.25536030530929565], "policy_updates": 48660, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10704.661607012, "contact_bce": 0.31032422184944153, "contact_force_loss": 0.033083122223615646, "terrain_level_mean": 3.27099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9995453357696533, 0.9997985363006592, 2.997563362121582]} {"step": 48770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48770, "total_transitions": 199761920, "num_steps_per_env": 1, "wm_loss": 0.40535664558410645, "actor_loss": -8.694419860839844, "critic_loss": 0.022899791598320007, "reward": 0.07088830322027206, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2532031536102295, 0.1580178588628769, 0.257649689912796], "policy_updates": 48670, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10708.17657307, "contact_bce": 0.31012704968452454, "contact_force_loss": 0.03227992355823517, "terrain_level_mean": 3.271240234375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9995453357696533, 0.9997985363006592, 2.997563362121582]} {"step": 48780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48780, "total_transitions": 199802880, "num_steps_per_env": 1, "wm_loss": 0.40008094906806946, "actor_loss": -8.781452178955078, "critic_loss": 0.0235823392868042, "reward": 0.07117271423339844, "falls": 1, "interval_steps": 10, "velocity_mae": [0.25344493985176086, 0.15834467113018036, 0.2547615170478821], "policy_updates": 48680, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10711.700550904001, "contact_bce": 0.3087797462940216, "contact_force_loss": 0.031707752496004105, "terrain_level_mean": 3.271484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9995453357696533, 0.9997985363006592, 2.997563362121582]} {"step": 48790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48790, "total_transitions": 199843840, "num_steps_per_env": 1, "wm_loss": 0.39986106753349304, "actor_loss": -8.663202285766602, "critic_loss": 0.03697296604514122, "reward": 0.07092364877462387, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2539452910423279, 0.15929850935935974, 0.25927942991256714], "policy_updates": 48690, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10715.213744198001, "contact_bce": 0.31372255086898804, "contact_force_loss": 0.0326940156519413, "terrain_level_mean": 3.2724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33984375, "command_abs_max": [1.9995453357696533, 0.9997985363006592, 2.997563362121582]} {"step": 48800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48800, "total_transitions": 199884800, "num_steps_per_env": 1, "wm_loss": 0.4276672899723053, "actor_loss": -8.752423286437988, "critic_loss": 0.027640018612146378, "reward": 0.07101844251155853, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2512073516845703, 0.16037622094154358, 0.2605525553226471], "policy_updates": 48700, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10718.722089456001, "contact_bce": 0.30636072158813477, "contact_force_loss": 0.03192806988954544, "terrain_level_mean": 3.271728515625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9995453357696533, 0.9997985363006592, 2.997563362121582]} {"step": 48810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48810, "total_transitions": 199925760, "num_steps_per_env": 1, "wm_loss": 0.3889625370502472, "actor_loss": -8.741424560546875, "critic_loss": 0.031359415501356125, "reward": 0.07099925726652145, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25152119994163513, 0.16064654290676117, 0.2597143054008484], "policy_updates": 48710, "skipped_updates": 0, "invalid_env_resets": 115, "elapsed_s": 10722.234511643, "contact_bce": 0.3117408752441406, "contact_force_loss": 0.03216398134827614, "terrain_level_mean": 3.2724609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9995453357696533, 0.9997985363006592, 2.997563362121582]} RECOVERY reset 1 invalid environments; first IDs=[504] {"step": 48820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48820, "total_transitions": 199966720, "num_steps_per_env": 1, "wm_loss": 0.38094770908355713, "actor_loss": -8.776994705200195, "critic_loss": 0.026970839127898216, "reward": 0.0708676427602768, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25161653757095337, 0.160484179854393, 0.26001837849617004], "policy_updates": 48720, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10725.763954515001, "contact_bce": 0.312164843082428, "contact_force_loss": 0.03184543177485466, "terrain_level_mean": 3.27197265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.997563362121582]} {"step": 48830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48830, "total_transitions": 200007680, "num_steps_per_env": 1, "wm_loss": 0.4237854480743408, "actor_loss": -8.708269119262695, "critic_loss": 0.03099345602095127, "reward": 0.07073678821325302, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25555387139320374, 0.1607462614774704, 0.25635644793510437], "policy_updates": 48730, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10729.288703875001, "contact_bce": 0.3082227408885956, "contact_force_loss": 0.03254278749227524, "terrain_level_mean": 3.27099609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.997563362121582]} {"step": 48840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48840, "total_transitions": 200048640, "num_steps_per_env": 1, "wm_loss": 0.38872891664505005, "actor_loss": -8.727340698242188, "critic_loss": 0.024112990126013756, "reward": 0.07092174887657166, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2558406889438629, 0.15948309004306793, 0.25625503063201904], "policy_updates": 48740, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10732.815538653, "contact_bce": 0.31041714549064636, "contact_force_loss": 0.03186498582363129, "terrain_level_mean": 3.270263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.997563362121582]} {"step": 48850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48850, "total_transitions": 200089600, "num_steps_per_env": 1, "wm_loss": 0.4549650251865387, "actor_loss": -8.653390884399414, "critic_loss": 0.027909213677048683, "reward": 0.0709599182009697, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2527197599411011, 0.1601385623216629, 0.25949540734291077], "policy_updates": 48750, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10736.330681306, "contact_bce": 0.31009772419929504, "contact_force_loss": 0.03247397765517235, "terrain_level_mean": 3.27001953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.997563362121582]} {"step": 48860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48860, "total_transitions": 200130560, "num_steps_per_env": 1, "wm_loss": 0.4137025773525238, "actor_loss": -8.71844482421875, "critic_loss": 0.022177770733833313, "reward": 0.0704282596707344, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2545793354511261, 0.15971492230892181, 0.2575209438800812], "policy_updates": 48760, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10739.837546552, "contact_bce": 0.30862370133399963, "contact_force_loss": 0.031635627150535583, "terrain_level_mean": 3.268310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.997563362121582]} {"step": 48870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48870, "total_transitions": 200171520, "num_steps_per_env": 1, "wm_loss": 0.42058688402175903, "actor_loss": -8.716791152954102, "critic_loss": 0.023559847846627235, "reward": 0.07058995217084885, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25249743461608887, 0.16009758412837982, 0.2547868490219116], "policy_updates": 48770, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10743.351903074, "contact_bce": 0.31348663568496704, "contact_force_loss": 0.03229863941669464, "terrain_level_mean": 3.2685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.9994025230407715]} {"step": 48880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48880, "total_transitions": 200212480, "num_steps_per_env": 1, "wm_loss": 0.4063238799571991, "actor_loss": -8.692060470581055, "critic_loss": 0.0374700166285038, "reward": 0.07089813798666, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2517363429069519, 0.15967035293579102, 0.25420036911964417], "policy_updates": 48780, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10746.876977990001, "contact_bce": 0.313185453414917, "contact_force_loss": 0.03259240835905075, "terrain_level_mean": 3.26953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.9994025230407715]} {"step": 48890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48890, "total_transitions": 200253440, "num_steps_per_env": 1, "wm_loss": 0.406695693731308, "actor_loss": -8.724254608154297, "critic_loss": 0.026132358238101006, "reward": 0.07085912674665451, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24987442791461945, 0.1585535854101181, 0.2588208317756653], "policy_updates": 48790, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10750.407849546, "contact_bce": 0.3082362711429596, "contact_force_loss": 0.03195052221417427, "terrain_level_mean": 3.269775390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.9994025230407715]} {"step": 48900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48900, "total_transitions": 200294400, "num_steps_per_env": 1, "wm_loss": 0.4258555769920349, "actor_loss": -8.74032211303711, "critic_loss": 0.03178892284631729, "reward": 0.07086142152547836, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2521437704563141, 0.1601065844297409, 0.2587089240550995], "policy_updates": 48800, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10753.91781036, "contact_bce": 0.31501123309135437, "contact_force_loss": 0.03244573995471001, "terrain_level_mean": 3.26904296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.9994025230407715]} {"step": 48910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48910, "total_transitions": 200335360, "num_steps_per_env": 1, "wm_loss": 0.4153769910335541, "actor_loss": -8.672120094299316, "critic_loss": 0.0263168066740036, "reward": 0.07085241377353668, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2548033595085144, 0.16037476062774658, 0.2545188367366791], "policy_updates": 48810, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10757.426636074, "contact_bce": 0.31128576397895813, "contact_force_loss": 0.03280261158943176, "terrain_level_mean": 3.2685546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.9994025230407715]} {"step": 48920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48920, "total_transitions": 200376320, "num_steps_per_env": 1, "wm_loss": 0.41673555970191956, "actor_loss": -8.67419147491455, "critic_loss": 0.025626633316278458, "reward": 0.07067352533340454, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25637567043304443, 0.15917013585567474, 0.25909626483917236], "policy_updates": 48820, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10760.924713149001, "contact_bce": 0.30873286724090576, "contact_force_loss": 0.03213663026690483, "terrain_level_mean": 3.268310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9995453357696533, 0.999819278717041, 2.9994025230407715]} {"step": 48930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48930, "total_transitions": 200417280, "num_steps_per_env": 1, "wm_loss": 0.4092105031013489, "actor_loss": -8.691047668457031, "critic_loss": 0.03197683021426201, "reward": 0.07078126817941666, "falls": 5, "interval_steps": 10, "velocity_mae": [0.25362810492515564, 0.16004522144794464, 0.2562372088432312], "policy_updates": 48830, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10764.427614171, "contact_bce": 0.3077138364315033, "contact_force_loss": 0.03238220512866974, "terrain_level_mean": 3.268310546875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348876953125, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 48940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48940, "total_transitions": 200458240, "num_steps_per_env": 1, "wm_loss": 0.46045055985450745, "actor_loss": -8.716019630432129, "critic_loss": 0.027878601104021072, "reward": 0.07096434384584427, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24796172976493835, 0.1594756692647934, 0.2549259662628174], "policy_updates": 48840, "skipped_updates": 0, "invalid_env_resets": 116, "elapsed_s": 10767.932648084, "contact_bce": 0.3163999021053314, "contact_force_loss": 0.03351711481809616, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} RECOVERY reset 1 invalid environments; first IDs=[1651] {"step": 48950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48950, "total_transitions": 200499200, "num_steps_per_env": 1, "wm_loss": 0.4124062657356262, "actor_loss": -8.739847183227539, "critic_loss": 0.02687467448413372, "reward": 0.07133384048938751, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24696050584316254, 0.1578400880098343, 0.2538316249847412], "policy_updates": 48850, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10771.457549896, "contact_bce": 0.31379762291908264, "contact_force_loss": 0.03232279792428017, "terrain_level_mean": 3.267333984375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 48960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48960, "total_transitions": 200540160, "num_steps_per_env": 1, "wm_loss": 0.43594735860824585, "actor_loss": -8.643932342529297, "critic_loss": 0.031053325161337852, "reward": 0.07047712057828903, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24877771735191345, 0.15854474902153015, 0.25936195254325867], "policy_updates": 48860, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10774.972044127, "contact_bce": 0.3099595606327057, "contact_force_loss": 0.03252985700964928, "terrain_level_mean": 3.266845703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 48970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48970, "total_transitions": 200581120, "num_steps_per_env": 1, "wm_loss": 0.43056297302246094, "actor_loss": -8.731791496276855, "critic_loss": 0.02352120541036129, "reward": 0.07030604779720306, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2519742548465729, 0.15854933857917786, 0.25880739092826843], "policy_updates": 48870, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10778.478133927001, "contact_bce": 0.31588906049728394, "contact_force_loss": 0.03297687694430351, "terrain_level_mean": 3.26611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343505859375, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 48980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48980, "total_transitions": 200622080, "num_steps_per_env": 1, "wm_loss": 0.41908639669418335, "actor_loss": -8.739681243896484, "critic_loss": 0.024925125762820244, "reward": 0.0708361268043518, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2478327453136444, 0.15814945101737976, 0.25409993529319763], "policy_updates": 48880, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10781.982533101, "contact_bce": 0.31309252977371216, "contact_force_loss": 0.03240107744932175, "terrain_level_mean": 3.265380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 48990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 48990, "total_transitions": 200663040, "num_steps_per_env": 1, "wm_loss": 0.41300442814826965, "actor_loss": -8.753376007080078, "critic_loss": 0.022712886333465576, "reward": 0.07107417285442352, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24855837225914001, 0.15760047733783722, 0.25797995924949646], "policy_updates": 48890, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10785.485252938, "contact_bce": 0.3050074279308319, "contact_force_loss": 0.03139675408601761, "terrain_level_mean": 3.265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.33837890625, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 49000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49000, "total_transitions": 200704000, "num_steps_per_env": 1, "wm_loss": 0.4243227541446686, "actor_loss": -8.648391723632812, "critic_loss": 0.03664327785372734, "reward": 0.07090320438146591, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25332069396972656, 0.15833227336406708, 0.25590625405311584], "policy_updates": 48900, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10788.995205276, "contact_bce": 0.30875363945961, "contact_force_loss": 0.03229917585849762, "terrain_level_mean": 3.265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337646484375, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 49010, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49010, "total_transitions": 200744960, "num_steps_per_env": 1, "wm_loss": 0.42167508602142334, "actor_loss": -8.693105697631836, "critic_loss": 0.04533655568957329, "reward": 0.07078588008880615, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2524433135986328, 0.15947610139846802, 0.25600433349609375], "policy_updates": 48910, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10792.531418, "contact_bce": 0.3138539791107178, "contact_force_loss": 0.033389702439308167, "terrain_level_mean": 3.264404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.339111328125, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 49020, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49020, "total_transitions": 200785920, "num_steps_per_env": 1, "wm_loss": 0.4306471645832062, "actor_loss": -8.70470142364502, "critic_loss": 0.03067384473979473, "reward": 0.07073161751031876, "falls": 8, "interval_steps": 10, "velocity_mae": [0.2497807890176773, 0.16103495657444, 0.25574350357055664], "policy_updates": 48920, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10796.292585633, "contact_bce": 0.3091331124305725, "contact_force_loss": 0.032465558499097824, "terrain_level_mean": 3.263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9994025230407715]} {"step": 49030, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49030, "total_transitions": 200826880, "num_steps_per_env": 1, "wm_loss": 0.40689706802368164, "actor_loss": -8.727814674377441, "critic_loss": 0.03467803820967674, "reward": 0.07087276875972748, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25115886330604553, 0.16218414902687073, 0.2582244575023651], "policy_updates": 48930, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10799.806370945, "contact_bce": 0.3147089183330536, "contact_force_loss": 0.03242778778076172, "terrain_level_mean": 3.264892578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341552734375, "command_abs_max": [1.9965078830718994, 0.999819278717041, 2.9993844032287598]} {"step": 49040, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49040, "total_transitions": 200867840, "num_steps_per_env": 1, "wm_loss": 0.40891575813293457, "actor_loss": -8.730903625488281, "critic_loss": 0.02263946272432804, "reward": 0.0711044892668724, "falls": 7, "interval_steps": 10, "velocity_mae": [0.25127658247947693, 0.15980811417102814, 0.25415152311325073], "policy_updates": 48940, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10803.316010183, "contact_bce": 0.3122542202472687, "contact_force_loss": 0.03213166818022728, "terrain_level_mean": 3.263427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9984920024871826, 0.999819278717041, 2.9993844032287598]} {"step": 49050, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49050, "total_transitions": 200908800, "num_steps_per_env": 1, "wm_loss": 0.4414310157299042, "actor_loss": -8.705533027648926, "critic_loss": 0.031067628413438797, "reward": 0.07119383662939072, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24817082285881042, 0.15965351462364197, 0.25561100244522095], "policy_updates": 48950, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10806.827993534, "contact_bce": 0.3139949142932892, "contact_force_loss": 0.03358212485909462, "terrain_level_mean": 3.263916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9984920024871826, 0.999819278717041, 2.9993844032287598]} {"step": 49060, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49060, "total_transitions": 200949760, "num_steps_per_env": 1, "wm_loss": 0.3899131417274475, "actor_loss": -8.698200225830078, "critic_loss": 0.028439849615097046, "reward": 0.07141987979412079, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2424207478761673, 0.15808410942554474, 0.2555989623069763], "policy_updates": 48960, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10810.325784103, "contact_bce": 0.3070114254951477, "contact_force_loss": 0.03186418488621712, "terrain_level_mean": 3.26416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340576171875, "command_abs_max": [1.9984920024871826, 0.999819278717041, 2.9993844032287598]} {"step": 49070, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49070, "total_transitions": 200990720, "num_steps_per_env": 1, "wm_loss": 0.4010315537452698, "actor_loss": -8.638622283935547, "critic_loss": 0.03305426239967346, "reward": 0.07164408266544342, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24134792387485504, 0.1583106368780136, 0.251460999250412], "policy_updates": 48970, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10813.821686963001, "contact_bce": 0.3106805980205536, "contact_force_loss": 0.031726542860269547, "terrain_level_mean": 3.2646484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3388671875, "command_abs_max": [1.9984920024871826, 0.999819278717041, 2.9993844032287598]} {"step": 49080, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49080, "total_transitions": 201031680, "num_steps_per_env": 1, "wm_loss": 0.413959801197052, "actor_loss": -8.687450408935547, "critic_loss": 0.02542872540652752, "reward": 0.07150078564882278, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24490056931972504, 0.1596584916114807, 0.2478443831205368], "policy_updates": 48980, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10817.314141287, "contact_bce": 0.31075364351272583, "contact_force_loss": 0.032315608114004135, "terrain_level_mean": 3.265380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34130859375, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49090, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49090, "total_transitions": 201072640, "num_steps_per_env": 1, "wm_loss": 0.4109072983264923, "actor_loss": -8.752447128295898, "critic_loss": 0.02256845496594906, "reward": 0.07149196416139603, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24472317099571228, 0.15889166295528412, 0.25368428230285645], "policy_updates": 48990, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10820.816110685, "contact_bce": 0.3126368522644043, "contact_force_loss": 0.03234681114554405, "terrain_level_mean": 3.265625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3408203125, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49100, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49100, "total_transitions": 201113600, "num_steps_per_env": 1, "wm_loss": 0.43091416358947754, "actor_loss": -8.769824981689453, "critic_loss": 0.018714580684900284, "reward": 0.07136126607656479, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24514085054397583, 0.1609317511320114, 0.2566017210483551], "policy_updates": 49000, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10824.31530693, "contact_bce": 0.3134477734565735, "contact_force_loss": 0.03247636556625366, "terrain_level_mean": 3.26611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49110, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49110, "total_transitions": 201154560, "num_steps_per_env": 1, "wm_loss": 0.4024081826210022, "actor_loss": -8.69862174987793, "critic_loss": 0.03249720484018326, "reward": 0.07118137180805206, "falls": 3, "interval_steps": 10, "velocity_mae": [0.245523139834404, 0.15869943797588348, 0.25523310899734497], "policy_updates": 49010, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10827.811354064, "contact_bce": 0.30198654532432556, "contact_force_loss": 0.031806278973817825, "terrain_level_mean": 3.26611328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343994140625, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49120, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49120, "total_transitions": 201195520, "num_steps_per_env": 1, "wm_loss": 0.40199002623558044, "actor_loss": -8.664820671081543, "critic_loss": 0.03002987802028656, "reward": 0.07090043276548386, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2447357028722763, 0.15871292352676392, 0.2558841109275818], "policy_updates": 49020, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10831.308022037001, "contact_bce": 0.31519177556037903, "contact_force_loss": 0.03288194164633751, "terrain_level_mean": 3.265380859375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49130, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49130, "total_transitions": 201236480, "num_steps_per_env": 1, "wm_loss": 0.45136991143226624, "actor_loss": -8.729891777038574, "critic_loss": 0.017858097329735756, "reward": 0.07105004787445068, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24571627378463745, 0.16002586483955383, 0.2575709819793701], "policy_updates": 49030, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10834.806032275, "contact_bce": 0.3132927119731903, "contact_force_loss": 0.032756298780441284, "terrain_level_mean": 3.26416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49140, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49140, "total_transitions": 201277440, "num_steps_per_env": 1, "wm_loss": 0.4104290008544922, "actor_loss": -8.711155891418457, "critic_loss": 0.02554762363433838, "reward": 0.07114552706480026, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24566051363945007, 0.15941911935806274, 0.2533873915672302], "policy_updates": 49040, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10838.307805485001, "contact_bce": 0.31104812026023865, "contact_force_loss": 0.032618749886751175, "terrain_level_mean": 3.263427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49150, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49150, "total_transitions": 201318400, "num_steps_per_env": 1, "wm_loss": 0.40437570214271545, "actor_loss": -8.707308769226074, "critic_loss": 0.02961299754679203, "reward": 0.07115893810987473, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24808625876903534, 0.1584986448287964, 0.25201597809791565], "policy_updates": 49050, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10841.809776952, "contact_bce": 0.3123082220554352, "contact_force_loss": 0.03234008327126503, "terrain_level_mean": 3.264404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49160, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49160, "total_transitions": 201359360, "num_steps_per_env": 1, "wm_loss": 0.3894825577735901, "actor_loss": -8.678536415100098, "critic_loss": 0.027815794572234154, "reward": 0.07096564769744873, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2489461749792099, 0.15874110162258148, 0.2520657181739807], "policy_updates": 49060, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10845.309944977, "contact_bce": 0.30419284105300903, "contact_force_loss": 0.032494112849235535, "terrain_level_mean": 3.26416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34716796875, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49170, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49170, "total_transitions": 201400320, "num_steps_per_env": 1, "wm_loss": 0.4206206500530243, "actor_loss": -8.660046577453613, "critic_loss": 0.036997564136981964, "reward": 0.07113274186849594, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24710388481616974, 0.16002853214740753, 0.25188565254211426], "policy_updates": 49070, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10848.830819345001, "contact_bce": 0.307457834482193, "contact_force_loss": 0.031646713614463806, "terrain_level_mean": 3.264404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49180, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49180, "total_transitions": 201441280, "num_steps_per_env": 1, "wm_loss": 0.41818109154701233, "actor_loss": -8.689233779907227, "critic_loss": 0.02682098187506199, "reward": 0.0714477077126503, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24467577040195465, 0.15859293937683105, 0.24982307851314545], "policy_updates": 49080, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10852.346603973001, "contact_bce": 0.3141827881336212, "contact_force_loss": 0.033268678933382034, "terrain_level_mean": 3.263916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34912109375, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49190, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49190, "total_transitions": 201482240, "num_steps_per_env": 1, "wm_loss": 0.42201054096221924, "actor_loss": -8.709452629089355, "critic_loss": 0.030014902353286743, "reward": 0.07126563042402267, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24451780319213867, 0.15873420238494873, 0.2536182999610901], "policy_updates": 49090, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10855.865016817, "contact_bce": 0.3121846318244934, "contact_force_loss": 0.03280821815133095, "terrain_level_mean": 3.26416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.999413251876831, 0.999819278717041, 2.9993844032287598]} {"step": 49200, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49200, "total_transitions": 201523200, "num_steps_per_env": 1, "wm_loss": 0.3984232544898987, "actor_loss": -8.711657524108887, "critic_loss": 0.030139068141579628, "reward": 0.07105782628059387, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24736477434635162, 0.1613149791955948, 0.25394174456596375], "policy_updates": 49100, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10859.381859139, "contact_bce": 0.3033663034439087, "contact_force_loss": 0.03162374719977379, "terrain_level_mean": 3.263427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.999413251876831, 0.9987244606018066, 2.9993844032287598]} {"step": 49210, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49210, "total_transitions": 201564160, "num_steps_per_env": 1, "wm_loss": 0.4215027391910553, "actor_loss": -8.762138366699219, "critic_loss": 0.026578489691019058, "reward": 0.07133548706769943, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24754661321640015, 0.16353867948055267, 0.25465837121009827], "policy_updates": 49110, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10862.896232391, "contact_bce": 0.3083961009979248, "contact_force_loss": 0.03255476430058479, "terrain_level_mean": 3.263916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.999413251876831, 0.9996622800827026, 2.9993844032287598]} {"step": 49220, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49220, "total_transitions": 201605120, "num_steps_per_env": 1, "wm_loss": 0.3993869721889496, "actor_loss": -8.67172908782959, "critic_loss": 0.020801005885004997, "reward": 0.07106554508209229, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24488696455955505, 0.16447840631008148, 0.2567402124404907], "policy_updates": 49120, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10866.424756955, "contact_bce": 0.313708633184433, "contact_force_loss": 0.03187892958521843, "terrain_level_mean": 3.262939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.999413251876831, 0.9996622800827026, 2.9993844032287598]} {"step": 49230, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49230, "total_transitions": 201646080, "num_steps_per_env": 1, "wm_loss": 0.4128738343715668, "actor_loss": -8.71721076965332, "critic_loss": 0.023726938292384148, "reward": 0.07111997157335281, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24340684711933136, 0.16208341717720032, 0.2574734091758728], "policy_updates": 49130, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10869.955303144001, "contact_bce": 0.30625343322753906, "contact_force_loss": 0.03226173296570778, "terrain_level_mean": 3.263427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.999413251876831, 0.9996622800827026, 2.9993844032287598]} {"step": 49240, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49240, "total_transitions": 201687040, "num_steps_per_env": 1, "wm_loss": 0.43486666679382324, "actor_loss": -8.71529769897461, "critic_loss": 0.02473428286612034, "reward": 0.0707622542977333, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24332894384860992, 0.15925584733486176, 0.2561241388320923], "policy_updates": 49140, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10873.477747928, "contact_bce": 0.312319815158844, "contact_force_loss": 0.03239919990301132, "terrain_level_mean": 3.262939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3466796875, "command_abs_max": [1.999241828918457, 0.9996622800827026, 2.9993844032287598]} {"step": 49250, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49250, "total_transitions": 201728000, "num_steps_per_env": 1, "wm_loss": 0.3976185917854309, "actor_loss": -8.668724060058594, "critic_loss": 0.04099048301577568, "reward": 0.07091184705495834, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2393384426832199, 0.15886414051055908, 0.25286737084388733], "policy_updates": 49150, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10876.997568386001, "contact_bce": 0.3054185211658478, "contact_force_loss": 0.031884364783763885, "terrain_level_mean": 3.263427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.999241828918457, 0.9996622800827026, 2.9993844032287598]} {"step": 49260, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49260, "total_transitions": 201768960, "num_steps_per_env": 1, "wm_loss": 0.403504341840744, "actor_loss": -8.778104782104492, "critic_loss": 0.020242519676685333, "reward": 0.07111353427171707, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23653198778629303, 0.15564167499542236, 0.2518741488456726], "policy_updates": 49160, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10880.509870442, "contact_bce": 0.30595922470092773, "contact_force_loss": 0.032068200409412384, "terrain_level_mean": 3.26318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9984920024871826, 0.9996622800827026, 2.9993844032287598]} {"step": 49270, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49270, "total_transitions": 201809920, "num_steps_per_env": 1, "wm_loss": 0.3841629922389984, "actor_loss": -8.711980819702148, "critic_loss": 0.029561150819063187, "reward": 0.07151097804307938, "falls": 4, "interval_steps": 10, "velocity_mae": [0.23769201338291168, 0.1563808023929596, 0.24916784465312958], "policy_updates": 49170, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10884.024741106, "contact_bce": 0.31017711758613586, "contact_force_loss": 0.031972452998161316, "terrain_level_mean": 3.264404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344482421875, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} {"step": 49280, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49280, "total_transitions": 201850880, "num_steps_per_env": 1, "wm_loss": 0.3980500400066376, "actor_loss": -8.714683532714844, "critic_loss": 0.040526147931814194, "reward": 0.07183398306369781, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2358253002166748, 0.15536901354789734, 0.2511466443538666], "policy_updates": 49180, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10887.547461846001, "contact_bce": 0.310312956571579, "contact_force_loss": 0.0313786156475544, "terrain_level_mean": 3.264404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34521484375, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} {"step": 49290, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49290, "total_transitions": 201891840, "num_steps_per_env": 1, "wm_loss": 0.3988952040672302, "actor_loss": -8.716268539428711, "critic_loss": 0.02791118621826172, "reward": 0.07101456820964813, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24270667135715485, 0.15841802954673767, 0.25469550490379333], "policy_updates": 49190, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10891.065850294, "contact_bce": 0.30770063400268555, "contact_force_loss": 0.03158486261963844, "terrain_level_mean": 3.2646484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} {"step": 49300, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49300, "total_transitions": 201932800, "num_steps_per_env": 1, "wm_loss": 0.39568501710891724, "actor_loss": -8.755763053894043, "critic_loss": 0.02689340151846409, "reward": 0.0705459713935852, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24564549326896667, 0.15847736597061157, 0.2532869577407837], "policy_updates": 49200, "skipped_updates": 0, "invalid_env_resets": 117, "elapsed_s": 10894.581213961, "contact_bce": 0.30902034044265747, "contact_force_loss": 0.032189756631851196, "terrain_level_mean": 3.26513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} RECOVERY reset 1 invalid environments; first IDs=[1193] {"step": 49310, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49310, "total_transitions": 201973760, "num_steps_per_env": 1, "wm_loss": 0.37796130776405334, "actor_loss": -8.731781005859375, "critic_loss": 0.022469131276011467, "reward": 0.0707656741142273, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24679124355316162, 0.15921804308891296, 0.2524893879890442], "policy_updates": 49210, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10898.115191984001, "contact_bce": 0.31034159660339355, "contact_force_loss": 0.03216007724404335, "terrain_level_mean": 3.26513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34326171875, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} {"step": 49320, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49320, "total_transitions": 202014720, "num_steps_per_env": 1, "wm_loss": 0.40133577585220337, "actor_loss": -8.68574333190918, "critic_loss": 0.026657357811927795, "reward": 0.07095220685005188, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24382133781909943, 0.15868182480335236, 0.24971359968185425], "policy_updates": 49220, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10901.634446325, "contact_bce": 0.3102993369102478, "contact_force_loss": 0.03192441537976265, "terrain_level_mean": 3.26513671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.340087890625, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} {"step": 49330, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49330, "total_transitions": 202055680, "num_steps_per_env": 1, "wm_loss": 0.4080665111541748, "actor_loss": -8.700779914855957, "critic_loss": 0.0273284949362278, "reward": 0.07052528113126755, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23935197293758392, 0.1586635559797287, 0.24709565937519073], "policy_updates": 49230, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10905.133698536001, "contact_bce": 0.3112199306488037, "contact_force_loss": 0.032878533005714417, "terrain_level_mean": 3.263916015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34228515625, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} {"step": 49340, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49340, "total_transitions": 202096640, "num_steps_per_env": 1, "wm_loss": 0.39736536145210266, "actor_loss": -8.736656188964844, "critic_loss": 0.04117262363433838, "reward": 0.07081101834774017, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23717620968818665, 0.1604093313217163, 0.2492491602897644], "policy_updates": 49240, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10908.635797596, "contact_bce": 0.30507785081863403, "contact_force_loss": 0.031461261212825775, "terrain_level_mean": 3.2626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9993844032287598]} {"step": 49350, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49350, "total_transitions": 202137600, "num_steps_per_env": 1, "wm_loss": 0.4400733709335327, "actor_loss": -8.707328796386719, "critic_loss": 0.022267771884799004, "reward": 0.07044459879398346, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24168337881565094, 0.16072437167167664, 0.24947330355644226], "policy_updates": 49250, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10912.160838034, "contact_bce": 0.30805349349975586, "contact_force_loss": 0.032257165759801865, "terrain_level_mean": 3.262451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.336181640625, "command_abs_max": [1.9996426105499268, 0.9996622800827026, 2.9964497089385986]} {"step": 49360, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49360, "total_transitions": 202178560, "num_steps_per_env": 1, "wm_loss": 0.43489569425582886, "actor_loss": -8.693148612976074, "critic_loss": 0.021134618669748306, "reward": 0.07066977024078369, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24687859416007996, 0.15933603048324585, 0.24914681911468506], "policy_updates": 49260, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10915.680431767001, "contact_bce": 0.3148593306541443, "contact_force_loss": 0.03279039263725281, "terrain_level_mean": 3.262451171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.337158203125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49370, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49370, "total_transitions": 202219520, "num_steps_per_env": 1, "wm_loss": 0.39441579580307007, "actor_loss": -8.68770980834961, "critic_loss": 0.023333102464675903, "reward": 0.07099977880716324, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24270343780517578, 0.15929502248764038, 0.25107699632644653], "policy_updates": 49270, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10919.206632947, "contact_bce": 0.3154078722000122, "contact_force_loss": 0.03205002844333649, "terrain_level_mean": 3.26220703125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34033203125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49380, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49380, "total_transitions": 202260480, "num_steps_per_env": 1, "wm_loss": 0.41486218571662903, "actor_loss": -8.668632507324219, "critic_loss": 0.030363980680704117, "reward": 0.07104264944791794, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24119995534420013, 0.15872937440872192, 0.2482430785894394], "policy_updates": 49280, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10922.721995825, "contact_bce": 0.31253257393836975, "contact_force_loss": 0.03222057968378067, "terrain_level_mean": 3.26171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49390, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49390, "total_transitions": 202301440, "num_steps_per_env": 1, "wm_loss": 0.44466421008110046, "actor_loss": -8.671272277832031, "critic_loss": 0.024235621094703674, "reward": 0.07104689627885818, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2433582842350006, 0.1590997576713562, 0.25247010588645935], "policy_updates": 49290, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10926.235849727, "contact_bce": 0.313324511051178, "contact_force_loss": 0.03299086168408394, "terrain_level_mean": 3.26171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34423828125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49400, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49400, "total_transitions": 202342400, "num_steps_per_env": 1, "wm_loss": 0.39123278856277466, "actor_loss": -8.700434684753418, "critic_loss": 0.024692349135875702, "reward": 0.07116495072841644, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2468632608652115, 0.15789863467216492, 0.251742959022522], "policy_updates": 49300, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10929.758749407001, "contact_bce": 0.30835476517677307, "contact_force_loss": 0.0321163646876812, "terrain_level_mean": 3.26171875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345703125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49410, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49410, "total_transitions": 202383360, "num_steps_per_env": 1, "wm_loss": 0.4205717146396637, "actor_loss": -8.74032211303711, "critic_loss": 0.021395454183220863, "reward": 0.07118775695562363, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2440718114376068, 0.1603119969367981, 0.25079041719436646], "policy_updates": 49310, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10933.267973771, "contact_bce": 0.31213992834091187, "contact_force_loss": 0.03307017311453819, "terrain_level_mean": 3.261962890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49420, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49420, "total_transitions": 202424320, "num_steps_per_env": 1, "wm_loss": 0.3886353373527527, "actor_loss": -8.7471284866333, "critic_loss": 0.026069939136505127, "reward": 0.07124863564968109, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24501486122608185, 0.15879333019256592, 0.2514527440071106], "policy_updates": 49320, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10936.765314997001, "contact_bce": 0.30894705653190613, "contact_force_loss": 0.032428763806819916, "terrain_level_mean": 3.261474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49430, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49430, "total_transitions": 202465280, "num_steps_per_env": 1, "wm_loss": 0.4315367341041565, "actor_loss": -8.694130897521973, "critic_loss": 0.02529345266520977, "reward": 0.0711241364479065, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24875129759311676, 0.15582089126110077, 0.24979864060878754], "policy_updates": 49330, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10940.290966702001, "contact_bce": 0.3115532100200653, "contact_force_loss": 0.032219450920820236, "terrain_level_mean": 3.262939453125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49440, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49440, "total_transitions": 202506240, "num_steps_per_env": 1, "wm_loss": 0.4029475450515747, "actor_loss": -8.744704246520996, "critic_loss": 0.025867408141493797, "reward": 0.07129555195569992, "falls": 3, "interval_steps": 10, "velocity_mae": [0.25185808539390564, 0.15561237931251526, 0.25039979815483093], "policy_updates": 49340, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10943.821014044, "contact_bce": 0.3125821053981781, "contact_force_loss": 0.03266226127743721, "terrain_level_mean": 3.263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49450, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49450, "total_transitions": 202547200, "num_steps_per_env": 1, "wm_loss": 0.4095601439476013, "actor_loss": -8.750076293945312, "critic_loss": 0.029646826907992363, "reward": 0.07165396213531494, "falls": 1, "interval_steps": 10, "velocity_mae": [0.2420956939458847, 0.1535373330116272, 0.24643650650978088], "policy_updates": 49350, "skipped_updates": 0, "invalid_env_resets": 118, "elapsed_s": 10947.344590396, "contact_bce": 0.30611687898635864, "contact_force_loss": 0.03243492916226387, "terrain_level_mean": 3.2646484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.346923828125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} RECOVERY reset 1 invalid environments; first IDs=[1986] {"step": 49460, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49460, "total_transitions": 202588160, "num_steps_per_env": 1, "wm_loss": 0.41824302077293396, "actor_loss": -8.74873161315918, "critic_loss": 0.022198250517249107, "reward": 0.07180345803499222, "falls": 5, "interval_steps": 10, "velocity_mae": [0.23421768844127655, 0.15196791291236877, 0.2468554824590683], "policy_updates": 49360, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10950.880600870001, "contact_bce": 0.30497804284095764, "contact_force_loss": 0.03238920494914055, "terrain_level_mean": 3.26416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345947265625, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49470, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49470, "total_transitions": 202629120, "num_steps_per_env": 1, "wm_loss": 0.40857571363449097, "actor_loss": -8.679388046264648, "critic_loss": 0.032393328845500946, "reward": 0.07123946398496628, "falls": 7, "interval_steps": 10, "velocity_mae": [0.23719632625579834, 0.15444114804267883, 0.24908488988876343], "policy_updates": 49370, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10954.403240296, "contact_bce": 0.3059099316596985, "contact_force_loss": 0.031344279646873474, "terrain_level_mean": 3.26416015625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.344970703125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49480, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49480, "total_transitions": 202670080, "num_steps_per_env": 1, "wm_loss": 0.3860916197299957, "actor_loss": -8.701711654663086, "critic_loss": 0.03019801340997219, "reward": 0.07091005891561508, "falls": 2, "interval_steps": 10, "velocity_mae": [0.241078183054924, 0.15805628895759583, 0.24977940320968628], "policy_updates": 49380, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10957.928860615, "contact_bce": 0.3082723319530487, "contact_force_loss": 0.03182009980082512, "terrain_level_mean": 3.264404296875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49490, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49490, "total_transitions": 202711040, "num_steps_per_env": 1, "wm_loss": 0.4064945876598358, "actor_loss": -8.728559494018555, "critic_loss": 0.027471888810396194, "reward": 0.07088395208120346, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24381442368030548, 0.15917766094207764, 0.25075867772102356], "policy_updates": 49390, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10961.442935750001, "contact_bce": 0.3102821111679077, "contact_force_loss": 0.031947050243616104, "terrain_level_mean": 3.26318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342529296875, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49500, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49500, "total_transitions": 202752000, "num_steps_per_env": 1, "wm_loss": 0.38851046562194824, "actor_loss": -8.755735397338867, "critic_loss": 0.01829405128955841, "reward": 0.07123785465955734, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24079768359661102, 0.15925222635269165, 0.2512291669845581], "policy_updates": 49400, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10964.961848734001, "contact_bce": 0.30939772725105286, "contact_force_loss": 0.032570235431194305, "terrain_level_mean": 3.26318359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.341796875, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49510, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49510, "total_transitions": 202792960, "num_steps_per_env": 1, "wm_loss": 0.4072056710720062, "actor_loss": -8.735828399658203, "critic_loss": 0.022607913240790367, "reward": 0.07108812779188156, "falls": 6, "interval_steps": 10, "velocity_mae": [0.23993775248527527, 0.15997062623500824, 0.2503224015235901], "policy_updates": 49410, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10968.508704904001, "contact_bce": 0.30788150429725647, "contact_force_loss": 0.031184498220682144, "terrain_level_mean": 3.2626953125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.342041015625, "command_abs_max": [1.9996426105499268, 0.9986540675163269, 2.997551918029785]} {"step": 49520, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49520, "total_transitions": 202833920, "num_steps_per_env": 1, "wm_loss": 0.40415897965431213, "actor_loss": -8.704469680786133, "critic_loss": 0.02540893666446209, "reward": 0.0710466131567955, "falls": 2, "interval_steps": 10, "velocity_mae": [0.2445925623178482, 0.1620195060968399, 0.2511199414730072], "policy_updates": 49420, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10972.280118247001, "contact_bce": 0.30933359265327454, "contact_force_loss": 0.0323612354695797, "terrain_level_mean": 3.263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.343017578125, "command_abs_max": [1.9993805885314941, 0.9986540675163269, 2.997551918029785]} {"step": 49530, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49530, "total_transitions": 202874880, "num_steps_per_env": 1, "wm_loss": 0.4049965739250183, "actor_loss": -8.769929885864258, "critic_loss": 0.018406938761472702, "reward": 0.07084937393665314, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25231263041496277, 0.1607581079006195, 0.25318098068237305], "policy_updates": 49430, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10975.796616813, "contact_bce": 0.3091011047363281, "contact_force_loss": 0.0312679260969162, "terrain_level_mean": 3.263671875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.345458984375, "command_abs_max": [1.9993805885314941, 0.9975863695144653, 2.997551918029785]} {"step": 49540, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49540, "total_transitions": 202915840, "num_steps_per_env": 1, "wm_loss": 0.3770403563976288, "actor_loss": -8.731078147888184, "critic_loss": 0.02160477451980114, "reward": 0.07117404043674469, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24863611161708832, 0.16092738509178162, 0.2503826916217804], "policy_updates": 49440, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10979.313405216, "contact_bce": 0.3061162233352661, "contact_force_loss": 0.03141145035624504, "terrain_level_mean": 3.263427734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34619140625, "command_abs_max": [1.9993805885314941, 0.9975863695144653, 2.997551918029785]} {"step": 49550, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49550, "total_transitions": 202956800, "num_steps_per_env": 1, "wm_loss": 0.4016638994216919, "actor_loss": -8.699131965637207, "critic_loss": 0.031052833423018456, "reward": 0.07141872495412827, "falls": 9, "interval_steps": 10, "velocity_mae": [0.24364854395389557, 0.1594136506319046, 0.24962173402309418], "policy_updates": 49450, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10982.838012993001, "contact_bce": 0.30278903245925903, "contact_force_loss": 0.031840190291404724, "terrain_level_mean": 3.261474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9993805885314941, 0.9975863695144653, 2.997551918029785]} {"step": 49560, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49560, "total_transitions": 202997760, "num_steps_per_env": 1, "wm_loss": 0.40111660957336426, "actor_loss": -8.688804626464844, "critic_loss": 0.02931789867579937, "reward": 0.07119245827198029, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24670742452144623, 0.15894117951393127, 0.2522867023944855], "policy_updates": 49460, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10986.349786807, "contact_bce": 0.31052127480506897, "contact_force_loss": 0.03166898712515831, "terrain_level_mean": 3.2607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9993805885314941, 0.9975863695144653, 2.997551918029785]} {"step": 49570, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49570, "total_transitions": 203038720, "num_steps_per_env": 1, "wm_loss": 0.3924436569213867, "actor_loss": -8.73543930053711, "critic_loss": 0.02851473167538643, "reward": 0.07095184177160263, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24698038399219513, 0.16035880148410797, 0.25050783157348633], "policy_updates": 49470, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10989.870200626001, "contact_bce": 0.30401960015296936, "contact_force_loss": 0.03153815492987633, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9993805885314941, 0.9975863695144653, 2.997551918029785]} {"step": 49580, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49580, "total_transitions": 203079680, "num_steps_per_env": 1, "wm_loss": 0.4228042662143707, "actor_loss": -8.719738006591797, "critic_loss": 0.02538381889462471, "reward": 0.07097014039754868, "falls": 4, "interval_steps": 10, "velocity_mae": [0.250063419342041, 0.1588944047689438, 0.24690258502960205], "policy_updates": 49480, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10993.390502403001, "contact_bce": 0.31006985902786255, "contact_force_loss": 0.03277862071990967, "terrain_level_mean": 3.26123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9993805885314941, 0.9975863695144653, 2.997551918029785]} {"step": 49590, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49590, "total_transitions": 203120640, "num_steps_per_env": 1, "wm_loss": 0.3849698603153229, "actor_loss": -8.665987014770508, "critic_loss": 0.029834289103746414, "reward": 0.0704159066081047, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2477966696023941, 0.15988123416900635, 0.25411203503608704], "policy_updates": 49490, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 10996.896245652, "contact_bce": 0.3042829930782318, "contact_force_loss": 0.03213401138782501, "terrain_level_mean": 3.2607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351318359375, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.997551918029785]} {"step": 49600, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49600, "total_transitions": 203161600, "num_steps_per_env": 1, "wm_loss": 0.3837588429450989, "actor_loss": -8.729854583740234, "critic_loss": 0.026608234271407127, "reward": 0.07039707899093628, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24897907674312592, 0.16193504631519318, 0.25617629289627075], "policy_updates": 49500, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11000.420681726, "contact_bce": 0.3115200400352478, "contact_force_loss": 0.03127603605389595, "terrain_level_mean": 3.2607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.997551918029785]} {"step": 49610, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49610, "total_transitions": 203202560, "num_steps_per_env": 1, "wm_loss": 0.3880351483821869, "actor_loss": -8.708967208862305, "critic_loss": 0.031034385785460472, "reward": 0.07037527114152908, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25058430433273315, 0.16154052317142487, 0.2575920522212982], "policy_updates": 49510, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11003.937157175, "contact_bce": 0.30729055404663086, "contact_force_loss": 0.031626492738723755, "terrain_level_mean": 3.2607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.997551918029785]} {"step": 49620, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49620, "total_transitions": 203243520, "num_steps_per_env": 1, "wm_loss": 0.39418381452560425, "actor_loss": -8.74791145324707, "critic_loss": 0.022320525720715523, "reward": 0.07076787203550339, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25072258710861206, 0.16201400756835938, 0.25398439168930054], "policy_updates": 49520, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11007.453174701, "contact_bce": 0.3100614845752716, "contact_force_loss": 0.03254128247499466, "terrain_level_mean": 3.260986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.997551918029785]} {"step": 49630, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49630, "total_transitions": 203284480, "num_steps_per_env": 1, "wm_loss": 0.39828965067863464, "actor_loss": -8.739994049072266, "critic_loss": 0.023297378793358803, "reward": 0.07100618630647659, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24990566074848175, 0.1594020277261734, 0.2513347566127777], "policy_updates": 49530, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11010.964002440001, "contact_bce": 0.3076041340827942, "contact_force_loss": 0.031738847494125366, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.997551918029785]} {"step": 49640, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49640, "total_transitions": 203325440, "num_steps_per_env": 1, "wm_loss": 0.38619324564933777, "actor_loss": -8.71477222442627, "critic_loss": 0.024902377277612686, "reward": 0.07087752223014832, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2500336468219757, 0.15928339958190918, 0.2503712773323059], "policy_updates": 49540, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11014.480943319, "contact_bce": 0.30663302540779114, "contact_force_loss": 0.031109465286135674, "terrain_level_mean": 3.259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.997551918029785]} {"step": 49650, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49650, "total_transitions": 203366400, "num_steps_per_env": 1, "wm_loss": 0.4150184690952301, "actor_loss": -8.696229934692383, "critic_loss": 0.028347570449113846, "reward": 0.07073374837636948, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25174713134765625, 0.15715506672859192, 0.2529521584510803], "policy_updates": 49550, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11018.000273668, "contact_bce": 0.30776968598365784, "contact_force_loss": 0.03234584257006645, "terrain_level_mean": 3.259033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353759765625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.997551918029785]} {"step": 49660, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49660, "total_transitions": 203407360, "num_steps_per_env": 1, "wm_loss": 0.40658095479011536, "actor_loss": -8.732463836669922, "critic_loss": 0.03251132369041443, "reward": 0.07080624252557755, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24837879836559296, 0.157080739736557, 0.2531444728374481], "policy_updates": 49560, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11021.520051561001, "contact_bce": 0.3065877854824066, "contact_force_loss": 0.03185934200882912, "terrain_level_mean": 3.259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.991999626159668]} {"step": 49670, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49670, "total_transitions": 203448320, "num_steps_per_env": 1, "wm_loss": 0.39616504311561584, "actor_loss": -8.682729721069336, "critic_loss": 0.02448398247361183, "reward": 0.07053770124912262, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2482452541589737, 0.15860916674137115, 0.25136756896972656], "policy_updates": 49570, "skipped_updates": 0, "invalid_env_resets": 119, "elapsed_s": 11025.044505866, "contact_bce": 0.30976584553718567, "contact_force_loss": 0.031439486891031265, "terrain_level_mean": 3.259521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3564453125, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.991999626159668]} RECOVERY reset 1 invalid environments; first IDs=[1188] {"step": 49680, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49680, "total_transitions": 203489280, "num_steps_per_env": 1, "wm_loss": 0.3782278299331665, "actor_loss": -8.711063385009766, "critic_loss": 0.025467226281762123, "reward": 0.07108213752508163, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24517056345939636, 0.1583935022354126, 0.2533596456050873], "policy_updates": 49580, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11028.584604447, "contact_bce": 0.3068103492259979, "contact_force_loss": 0.03146723285317421, "terrain_level_mean": 3.259033203125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.356201171875, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.991999626159668]} {"step": 49690, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49690, "total_transitions": 203530240, "num_steps_per_env": 1, "wm_loss": 0.39984896779060364, "actor_loss": -8.707609176635742, "critic_loss": 0.024919886142015457, "reward": 0.07099824398756027, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2492067962884903, 0.1587524116039276, 0.2530185878276825], "policy_updates": 49590, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11032.115208376, "contact_bce": 0.3076200783252716, "contact_force_loss": 0.031656939536333084, "terrain_level_mean": 3.2578125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355712890625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.991999626159668]} {"step": 49700, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49700, "total_transitions": 203571200, "num_steps_per_env": 1, "wm_loss": 0.3954086899757385, "actor_loss": -8.755439758300781, "critic_loss": 0.030701089650392532, "reward": 0.07117331773042679, "falls": 5, "interval_steps": 10, "velocity_mae": [0.2517043352127075, 0.16105318069458008, 0.2509404718875885], "policy_updates": 49600, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11035.652353561001, "contact_bce": 0.3032786548137665, "contact_force_loss": 0.03125912323594093, "terrain_level_mean": 3.258544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.9992828369140625]} {"step": 49710, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49710, "total_transitions": 203612160, "num_steps_per_env": 1, "wm_loss": 0.4114960730075836, "actor_loss": -8.721217155456543, "critic_loss": 0.025881314650177956, "reward": 0.07065578550100327, "falls": 10, "interval_steps": 10, "velocity_mae": [0.2495386153459549, 0.1625184565782547, 0.2511034607887268], "policy_updates": 49610, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11039.174943163001, "contact_bce": 0.30698055028915405, "contact_force_loss": 0.032227423042058945, "terrain_level_mean": 3.257080078125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349853515625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.9992828369140625]} {"step": 49720, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49720, "total_transitions": 203653120, "num_steps_per_env": 1, "wm_loss": 0.3901048004627228, "actor_loss": -8.773164749145508, "critic_loss": 0.02726527489721775, "reward": 0.07099775224924088, "falls": 5, "interval_steps": 10, "velocity_mae": [0.24568559229373932, 0.15992426872253418, 0.25245827436447144], "policy_updates": 49620, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11042.704782982, "contact_bce": 0.30993399024009705, "contact_force_loss": 0.03152904659509659, "terrain_level_mean": 3.257568359375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.347412109375, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.9992828369140625]} {"step": 49730, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49730, "total_transitions": 203694080, "num_steps_per_env": 1, "wm_loss": 0.40128380060195923, "actor_loss": -8.700172424316406, "critic_loss": 0.03020351193845272, "reward": 0.07102162390947342, "falls": 3, "interval_steps": 10, "velocity_mae": [0.24649269878864288, 0.1587195098400116, 0.2521161437034607], "policy_updates": 49630, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11046.224887658, "contact_bce": 0.30765166878700256, "contact_force_loss": 0.031466882675886154, "terrain_level_mean": 3.258056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3505859375, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.9992828369140625]} {"step": 49740, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49740, "total_transitions": 203735040, "num_steps_per_env": 1, "wm_loss": 0.39839357137680054, "actor_loss": -8.689483642578125, "critic_loss": 0.0356251560151577, "reward": 0.0707939937710762, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24942204356193542, 0.16017568111419678, 0.24996167421340942], "policy_updates": 49640, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11049.734810954, "contact_bce": 0.3102138340473175, "contact_force_loss": 0.03169786185026169, "terrain_level_mean": 3.258544921875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.9992828369140625]} {"step": 49750, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49750, "total_transitions": 203776000, "num_steps_per_env": 1, "wm_loss": 0.3958847224712372, "actor_loss": -8.71285629272461, "critic_loss": 0.03416609391570091, "reward": 0.07059629261493683, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2497616708278656, 0.16023336350917816, 0.2532283663749695], "policy_updates": 49650, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11053.243226243001, "contact_bce": 0.30611398816108704, "contact_force_loss": 0.031158970668911934, "terrain_level_mean": 3.258056640625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35400390625, "command_abs_max": [1.9986796379089355, 0.9975863695144653, 2.9992828369140625]} {"step": 49760, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49760, "total_transitions": 203816960, "num_steps_per_env": 1, "wm_loss": 0.40236955881118774, "actor_loss": -8.769472122192383, "critic_loss": 0.021053247153759003, "reward": 0.07047492265701294, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2497190237045288, 0.1601729542016983, 0.25528594851493835], "policy_updates": 49660, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11056.760856848001, "contact_bce": 0.30693456530570984, "contact_force_loss": 0.03204037621617317, "terrain_level_mean": 3.2587890625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3544921875, "command_abs_max": [1.9986796379089355, 0.9977898001670837, 2.9992828369140625]} {"step": 49770, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49770, "total_transitions": 203857920, "num_steps_per_env": 1, "wm_loss": 0.3580457866191864, "actor_loss": -8.738883972167969, "critic_loss": 0.03188079223036766, "reward": 0.07049151510000229, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24986392259597778, 0.16084635257720947, 0.2535862624645233], "policy_updates": 49670, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11060.275345944001, "contact_bce": 0.3052639067173004, "contact_force_loss": 0.031538091599941254, "terrain_level_mean": 3.260009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.355224609375, "command_abs_max": [1.9981138706207275, 0.9977898001670837, 2.9992828369140625]} {"step": 49780, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49780, "total_transitions": 203898880, "num_steps_per_env": 1, "wm_loss": 0.38311314582824707, "actor_loss": -8.759439468383789, "critic_loss": 0.018971160054206848, "reward": 0.0712408721446991, "falls": 8, "interval_steps": 10, "velocity_mae": [0.24540898203849792, 0.15995466709136963, 0.250364750623703], "policy_updates": 49680, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11063.790952993, "contact_bce": 0.306151807308197, "contact_force_loss": 0.03238937631249428, "terrain_level_mean": 3.259765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.354736328125, "command_abs_max": [1.9981138706207275, 0.9977898001670837, 2.9992828369140625]} {"step": 49790, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49790, "total_transitions": 203939840, "num_steps_per_env": 1, "wm_loss": 0.3737194240093231, "actor_loss": -8.76158332824707, "critic_loss": 0.03020344488322735, "reward": 0.07111787796020508, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2423514574766159, 0.1609218716621399, 0.24836575984954834], "policy_updates": 49690, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11067.311059649, "contact_bce": 0.3100278675556183, "contact_force_loss": 0.031619854271411896, "terrain_level_mean": 3.260009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358642578125, "command_abs_max": [1.9981138706207275, 0.9977898001670837, 2.9992828369140625]} {"step": 49800, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49800, "total_transitions": 203980800, "num_steps_per_env": 1, "wm_loss": 0.38210633397102356, "actor_loss": -8.728357315063477, "critic_loss": 0.03273544833064079, "reward": 0.07108532637357712, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2458590865135193, 0.1602972149848938, 0.25158658623695374], "policy_updates": 49700, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11070.821296187001, "contact_bce": 0.3097584843635559, "contact_force_loss": 0.031866706907749176, "terrain_level_mean": 3.2607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.358154296875, "command_abs_max": [1.9975299835205078, 0.9977898001670837, 2.9992828369140625]} {"step": 49810, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49810, "total_transitions": 204021760, "num_steps_per_env": 1, "wm_loss": 0.41521650552749634, "actor_loss": -8.678586959838867, "critic_loss": 0.027763864025473595, "reward": 0.0711122676730156, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24874234199523926, 0.15926502645015717, 0.2525864541530609], "policy_updates": 49710, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11074.332908685, "contact_bce": 0.31272992491722107, "contact_force_loss": 0.031777191907167435, "terrain_level_mean": 3.26123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.352783203125, "command_abs_max": [1.9975299835205078, 0.9977898001670837, 2.9992828369140625]} {"step": 49820, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49820, "total_transitions": 204062720, "num_steps_per_env": 1, "wm_loss": 0.3668696880340576, "actor_loss": -8.726165771484375, "critic_loss": 0.025646362453699112, "reward": 0.07108818739652634, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2496463507413864, 0.15948554873466492, 0.2535867691040039], "policy_updates": 49720, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11077.845769638001, "contact_bce": 0.3044638931751251, "contact_force_loss": 0.03078129142522812, "terrain_level_mean": 3.261474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.9975299835205078, 0.9977898001670837, 2.9992828369140625]} {"step": 49830, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49830, "total_transitions": 204103680, "num_steps_per_env": 1, "wm_loss": 0.40080714225769043, "actor_loss": -8.737486839294434, "critic_loss": 0.025549501180648804, "reward": 0.07078976929187775, "falls": 6, "interval_steps": 10, "velocity_mae": [0.25153928995132446, 0.1598566770553589, 0.253911554813385], "policy_updates": 49730, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11081.369008556001, "contact_bce": 0.3135964274406433, "contact_force_loss": 0.03164128214120865, "terrain_level_mean": 3.260986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35595703125, "command_abs_max": [1.9975299835205078, 0.9977898001670837, 2.9992828369140625]} {"step": 49840, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49840, "total_transitions": 204144640, "num_steps_per_env": 1, "wm_loss": 0.39141935110092163, "actor_loss": -8.67445182800293, "critic_loss": 0.02793850377202034, "reward": 0.07104494422674179, "falls": 6, "interval_steps": 10, "velocity_mae": [0.2516845762729645, 0.16037890315055847, 0.2455153465270996], "policy_updates": 49740, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11084.882686056, "contact_bce": 0.30784091353416443, "contact_force_loss": 0.031004372984170914, "terrain_level_mean": 3.26123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.9975299835205078, 0.9977898001670837, 2.9992828369140625]} {"step": 49850, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49850, "total_transitions": 204185600, "num_steps_per_env": 1, "wm_loss": 0.39381998777389526, "actor_loss": -8.749139785766602, "critic_loss": 0.024946531280875206, "reward": 0.07101549953222275, "falls": 7, "interval_steps": 10, "velocity_mae": [0.24944210052490234, 0.1573246717453003, 0.2502397894859314], "policy_updates": 49750, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11088.396237684, "contact_bce": 0.3139890730381012, "contact_force_loss": 0.03133917227387428, "terrain_level_mean": 3.260986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.351806640625, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49860, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49860, "total_transitions": 204226560, "num_steps_per_env": 1, "wm_loss": 0.3927893042564392, "actor_loss": -8.69028091430664, "critic_loss": 0.02636154368519783, "reward": 0.07155720144510269, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24214062094688416, 0.155668705701828, 0.2501389980316162], "policy_updates": 49760, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11091.92162567, "contact_bce": 0.3019729256629944, "contact_force_loss": 0.030904289335012436, "terrain_level_mean": 3.26123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349365234375, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49870, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49870, "total_transitions": 204267520, "num_steps_per_env": 1, "wm_loss": 0.40119245648384094, "actor_loss": -8.714186668395996, "critic_loss": 0.025497088208794594, "reward": 0.07140912115573883, "falls": 4, "interval_steps": 10, "velocity_mae": [0.2442321479320526, 0.15663041174411774, 0.2546234428882599], "policy_updates": 49770, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11095.445696154, "contact_bce": 0.3098902106285095, "contact_force_loss": 0.03185352310538292, "terrain_level_mean": 3.2607421875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.349609375, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49880, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49880, "total_transitions": 204308480, "num_steps_per_env": 1, "wm_loss": 0.3894149363040924, "actor_loss": -8.707684516906738, "critic_loss": 0.031963542103767395, "reward": 0.07142236083745956, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24953874945640564, 0.15720808506011963, 0.2568497061729431], "policy_updates": 49780, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11098.967739813, "contact_bce": 0.30995380878448486, "contact_force_loss": 0.03130773454904556, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3486328125, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49890, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49890, "total_transitions": 204349440, "num_steps_per_env": 1, "wm_loss": 0.4179180860519409, "actor_loss": -8.716675758361816, "critic_loss": 0.02558496966958046, "reward": 0.07132831960916519, "falls": 1, "interval_steps": 10, "velocity_mae": [0.24935781955718994, 0.15692278742790222, 0.2527832090854645], "policy_updates": 49790, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11102.488363523, "contact_bce": 0.3047851324081421, "contact_force_loss": 0.03134946897625923, "terrain_level_mean": 3.260986328125, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3515625, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49900, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49900, "total_transitions": 204390400, "num_steps_per_env": 1, "wm_loss": 0.3896399438381195, "actor_loss": -8.718696594238281, "critic_loss": 0.023827988654375076, "reward": 0.07109900563955307, "falls": 8, "interval_steps": 10, "velocity_mae": [0.25077444314956665, 0.15516625344753265, 0.25369325280189514], "policy_updates": 49800, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11106.024847186001, "contact_bce": 0.3073262572288513, "contact_force_loss": 0.031574323773384094, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35107421875, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49910, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49910, "total_transitions": 204431360, "num_steps_per_env": 1, "wm_loss": 0.4016917943954468, "actor_loss": -8.728238105773926, "critic_loss": 0.028419315814971924, "reward": 0.07128047198057175, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24981693923473358, 0.15352025628089905, 0.2553425133228302], "policy_updates": 49810, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11109.552657056001, "contact_bce": 0.3077990412712097, "contact_force_loss": 0.03188323602080345, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.350341796875, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49920, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49920, "total_transitions": 204472320, "num_steps_per_env": 1, "wm_loss": 0.40712958574295044, "actor_loss": -8.718421936035156, "critic_loss": 0.026540637016296387, "reward": 0.07123968005180359, "falls": 2, "interval_steps": 10, "velocity_mae": [0.24966250360012054, 0.1570347100496292, 0.25042903423309326], "policy_updates": 49820, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11113.071662598, "contact_bce": 0.3108852803707123, "contact_force_loss": 0.03159388154745102, "terrain_level_mean": 3.26123046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.348388671875, "command_abs_max": [1.9989352226257324, 0.9979754686355591, 2.9992828369140625]} {"step": 49930, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49930, "total_transitions": 204513280, "num_steps_per_env": 1, "wm_loss": 0.425046443939209, "actor_loss": -8.712114334106445, "critic_loss": 0.023346079513430595, "reward": 0.07103358954191208, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2511466145515442, 0.15747441351413727, 0.25397974252700806], "policy_updates": 49830, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11116.587317115, "contact_bce": 0.30699461698532104, "contact_force_loss": 0.03187672793865204, "terrain_level_mean": 3.261474609375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34814453125, "command_abs_max": [1.9989352226257324, 0.9979754686355591, 2.9992828369140625]} {"step": 49940, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49940, "total_transitions": 204554240, "num_steps_per_env": 1, "wm_loss": 0.38220638036727905, "actor_loss": -8.658956527709961, "critic_loss": 0.036822427064180374, "reward": 0.07103248685598373, "falls": 11, "interval_steps": 10, "velocity_mae": [0.2523346543312073, 0.15608422458171844, 0.2559962868690491], "policy_updates": 49840, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11120.098228604, "contact_bce": 0.31259438395500183, "contact_force_loss": 0.0319705493748188, "terrain_level_mean": 3.260498046875, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.3525390625, "command_abs_max": [1.9989352226257324, 0.9979754686355591, 2.9992828369140625]} {"step": 49950, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49950, "total_transitions": 204595200, "num_steps_per_env": 1, "wm_loss": 0.38025203347206116, "actor_loss": -8.734837532043457, "critic_loss": 0.023768708109855652, "reward": 0.07107533514499664, "falls": 3, "interval_steps": 10, "velocity_mae": [0.2516796588897705, 0.15708954632282257, 0.25428375601768494], "policy_updates": 49850, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11123.624266114, "contact_bce": 0.3089231252670288, "contact_force_loss": 0.031709689646959305, "terrain_level_mean": 3.260009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35302734375, "command_abs_max": [1.9989352226257324, 0.9979754686355591, 2.9992828369140625]} {"step": 49960, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49960, "total_transitions": 204636160, "num_steps_per_env": 1, "wm_loss": 0.3983805179595947, "actor_loss": -8.708301544189453, "critic_loss": 0.023865951225161552, "reward": 0.0706491693854332, "falls": 4, "interval_steps": 10, "velocity_mae": [0.25408563017845154, 0.15854115784168243, 0.25572648644447327], "policy_updates": 49860, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11127.1459235, "contact_bce": 0.3068126440048218, "contact_force_loss": 0.03247822821140289, "terrain_level_mean": 3.26025390625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.353271484375, "command_abs_max": [1.9989352226257324, 0.9979754686355591, 2.9992828369140625]} {"step": 49970, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49970, "total_transitions": 204677120, "num_steps_per_env": 1, "wm_loss": 0.39252668619155884, "actor_loss": -8.745102882385254, "critic_loss": 0.028987431898713112, "reward": 0.07067064940929413, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2538957893848419, 0.15732534229755402, 0.2514655888080597], "policy_updates": 49870, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11130.668611998, "contact_bce": 0.3039766550064087, "contact_force_loss": 0.031528424471616745, "terrain_level_mean": 3.25927734375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35498046875, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49980, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49980, "total_transitions": 204718080, "num_steps_per_env": 1, "wm_loss": 0.3877331614494324, "actor_loss": -8.690896987915039, "critic_loss": 0.029520124197006226, "reward": 0.07103347033262253, "falls": 6, "interval_steps": 10, "velocity_mae": [0.24854716658592224, 0.1536509096622467, 0.25119540095329285], "policy_updates": 49880, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11134.191181286, "contact_bce": 0.30310410261154175, "contact_force_loss": 0.0313740074634552, "terrain_level_mean": 3.259521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35205078125, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 49990, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 49990, "total_transitions": 204759040, "num_steps_per_env": 1, "wm_loss": 0.38850468397140503, "actor_loss": -8.680500030517578, "critic_loss": 0.03492328152060509, "reward": 0.07081657648086548, "falls": 4, "interval_steps": 10, "velocity_mae": [0.24764837324619293, 0.152267724275589, 0.2518332302570343], "policy_updates": 49890, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11137.712006557, "contact_bce": 0.30857905745506287, "contact_force_loss": 0.03240996226668358, "terrain_level_mean": 3.260009765625, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.35009765625, "command_abs_max": [1.9989352226257324, 0.9977898001670837, 2.9992828369140625]} {"step": 50000, "actor_lr": 1.8e-06, "archive_windows": 100000, "env_steps": 50000, "total_transitions": 204800000, "num_steps_per_env": 1, "wm_loss": 0.3964875340461731, "actor_loss": -8.712970733642578, "critic_loss": 0.023709772154688835, "reward": 0.07063455134630203, "falls": 7, "interval_steps": 10, "velocity_mae": [0.2501400411128998, 0.15224096179008484, 0.2536126673221588], "policy_updates": 49900, "skipped_updates": 0, "invalid_env_resets": 120, "elapsed_s": 11141.232798002, "contact_bce": 0.30595290660858154, "contact_force_loss": 0.03146994113922119, "terrain_level_mean": 3.259521484375, "terrain_level_max": 5, "command_stage": 4, "command_ranges": [[-2.0, 2.0], [-1.0, 1.0], [-3.0, 3.0]], "command_negative_vx_fraction": 0.34765625, "command_abs_max": [1.9989352226257324, 0.9978711605072021, 2.9992828369140625]} +---------------------------------+ | Base Environment | +------------------------+--------+ | Property | Value | +------------------------+--------+ | Number of environments | 1 | | Environment device | cuda:0 | | Environment seed | None | | Physics step-size | 0.005 | | Environment step-size | 0.02 | +------------------------+--------+ [INFO] contains 1 active terms. +-------------------------------------+ | Active Event Terms in Mode: 'reset' | +--------+----------------------------+ | Index | Name | +--------+----------------------------+ | 0 | reset_base | | 1 | reset_robot_joints | +--------+----------------------------+ [INFO] contains 1 active terms. +----------------------------------------+ | Active Command Terms | +-------+-------+------------------------+ | Index | Name | Type | +-------+-------+------------------------+ | 0 | twist | UniformVelocityCommand | +-------+-------+------------------------+ [INFO] contains 2 active terms. +---------------------------------+ | Active Action Terms (shape: 16) | +-------+-----------+-------------+ | Index | Name | Dimension | +-------+-----------+-------------+ | 0 | joint_pos | 12 | | 1 | wheel_vel | 4 | +-------+-----------+-------------+ [INFO] contains 1 groups. +------------------------------------------------------------+ | Active Observation Terms in Group: 'actor' (shape: (265,)) | +--------+-------------------------+-------------------------+ | Index | Name | Shape | +--------+-------------------------+-------------------------+ | 0 | base_ang_vel | (15,) ← 5×(3,) | | 1 | projected_gravity | (15,) ← 5×(3,) | | 2 | joint_pos | (60,) ← 5×(12,) | | 3 | joint_vel | (60,) ← 5×(12,) | | 4 | wheel_vel | (20,) ← 5×(4,) | | 5 | actions | (80,) ← 5×(16,) | | 6 | command | (15,) ← 5×(3,) | +--------+-------------------------+-------------------------+ [INFO] contains 3 active terms. +--------------------------------+ | Active Termination Terms | +-------+-------------+----------+ | Index | Name | Time Out | +-------+-------------+----------+ | 0 | time_out | True | | 1 | fell_over | False | | 2 | course_exit | True | +-------+-------------+----------+ [INFO] contains 0 active terms. +-----------------------+ | Active Reward Terms | +-------+------+--------+ | Index | Name | Weight | +-------+------+--------+ +-------+------+--------+ [INFO] (inactive) [INFO] (inactive) [INFO] (inactive) S10 video saved: logs/s10_terrain_v4_50k_full/videos/iteration_050000.mp4 S10 training complete: logs/s10_terrain_v4_50k_full