feat: huoyi M20 smooth/bridge training and stability docs

Current code snapshot: smooth/bridge task configs, smooth random terrain, roll/pitch stability rewards, M20 URDF updates, eval profile and stability training documentation.
2026-11-02 16:41:07 +08:00
commit 07027e8fde
91 changed files with 13047 additions and 0 deletions
@@ -0,0 +1,71 @@
+# Copyright (c) 2025 Deep Robotics
+# SPDX-License-Identifier: BSD 3-Clause
+
+"""checkpoint 解析与策略加载（IsaacLab + RSL-RL）。"""
+
+from __future__ import annotations
+
+import os
+from typing import Any
+
+import gymnasium as gym
+
+from isaaclab.envs import (
+    DirectMARLEnv,
+    DirectMARLEnvCfg,
+    DirectRLEnvCfg,
+    ManagerBasedRLEnvCfg,
+    multi_agent_to_single_agent,
+)
+from isaaclab_tasks.utils import get_checkpoint_path
+from isaaclab_rl.rsl_rl import RslRlVecEnvWrapper
+
+
+def resolve_checkpoint(
+    log_root_path: str,
+    load_run: str | None = None,
+    checkpoint: str | None = None,
+) -> str:
+    """解析出 checkpoint 的绝对路径。
+
+    允许 ``load_run`` / ``checkpoint`` 传绝对路径或带目录的相对路径，从而跨实验目录
+    取权重（例如从 Stage 1 的目录里取权重来评估），否则回退到 IsaacLab 的按名查找。
+    """
+    if checkpoint is not None:
+        checkpoint_path = os.path.expanduser(checkpoint)
+        if os.path.isabs(checkpoint_path) or os.path.dirname(checkpoint_path):
+            checkpoint_path = os.path.abspath(checkpoint_path)
+            if not os.path.isfile(checkpoint_path):
+                raise FileNotFoundError(f"找不到 checkpoint：{checkpoint_path}")
+            return checkpoint_path
+
+    if load_run is not None:
+        run_path = os.path.expanduser(load_run)
+        if os.path.isabs(run_path) or os.path.dirname(run_path):
+            run_path = os.path.abspath(run_path)
+            if not os.path.isdir(run_path):
+                raise FileNotFoundError(f"找不到运行目录：{run_path}")
+            return get_checkpoint_path(os.path.dirname(run_path), os.path.basename(run_path), checkpoint)
+
+    return get_checkpoint_path(log_root_path, load_run, checkpoint)
+
+
+def make_env(
+    task: str,
+    env_cfg: ManagerBasedRLEnvCfg | DirectRLEnvCfg | DirectMARLEnvCfg,
+    clip_actions: float | None = None,
+):
+    """按已配置好的 ``env_cfg`` 建环境，并包成 RSL-RL 的向量环境。"""
+    env = gym.make(task, cfg=env_cfg)
+    if isinstance(env.unwrapped, DirectMARLEnv):
+        env = multi_agent_to_single_agent(env)
+    return RslRlVecEnvWrapper(env, clip_actions=clip_actions)
+
+
+def load_policy(env, agent_cfg: Any, resume_path: str, device: str | None = None):
+    """加载 checkpoint 并返回推理策略。"""
+    from rsl_rl.runners import OnPolicyRunner
+
+    runner = OnPolicyRunner(env, agent_cfg.to_dict(), log_dir=None, device=device or agent_cfg.device)
+    runner.load(resume_path)
+    return runner.get_inference_policy(device=device or env.unwrapped.device)