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.

source/rl_training/setup.py

@@ -0,0 +1,55 @@
+# Copyright (c) 2025 Deep Robotics
+# SPDX-License-Identifier: BSD 3-Clause
+# 
+# # Copyright (c) 2024-2025 Ziqi Fan
+# SPDX-License-Identifier: Apache-2.0
+
+"""Installation script for the 'rl_training' python package."""
+
+import os
+import toml
+
+from setuptools import setup
+
+# Obtain the extension data from the extension.toml file
+EXTENSION_PATH = os.path.dirname(os.path.realpath(__file__))
+# Read the extension.toml file
+EXTENSION_TOML_DATA = toml.load(os.path.join(EXTENSION_PATH, "config", "extension.toml"))
+
+# Minimum dependencies required prior to installation
+INSTALL_REQUIRES = [
+    # base
+    "psutil",
+    "colorama",
+    "xacrodoc",
+    # amp
+    "numpy",
+    "pandas",
+    "pinocchio",
+    # rl
+    "cusrl[all]",
+]
+
+# Installation operation
+setup(
+    name="rl_training",
+    packages=["rl_training"],
+    author=EXTENSION_TOML_DATA["package"]["author"],
+    maintainer=EXTENSION_TOML_DATA["package"]["maintainer"],
+    url=EXTENSION_TOML_DATA["package"]["repository"],
+    version=EXTENSION_TOML_DATA["package"]["version"],
+    description=EXTENSION_TOML_DATA["package"]["description"],
+    keywords=EXTENSION_TOML_DATA["package"]["keywords"],
+    install_requires=INSTALL_REQUIRES,
+    license="Apache License 2.0",
+    include_package_data=True,
+    python_requires=">=3.10",
+    classifiers=[
+        "Natural Language :: English",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Isaac Sim :: 4.5.0",
+        "Isaac Sim :: 5.0.0",
+    ],
+    zip_safe=False,
+)