Repository Index

Multi-Joint dynamics with Contact. A general purpose physics simulator.

• robotics
• physics
• mujoco

An elegant PyTorch deep reinforcement learning library.

• pytorch
• policy-gradient
• dqn
• double-dqn

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

• reinforcement-learning
• multiagent-reinforcement-learning
• self-play
• imitation-learning

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

• reinforcement-learning
• parallel-processing
• cpp17
• pybind11

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

• reinforcement-learning
• python
• deep-learning
• gym

Reproduction of SuperMimic (arXiv:2610.28480): learned differentiable world model + BPTT policy for G1 humanoid motion tracking, on mjlab/MuJoCo Warp

SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.

• amd
• motrixsim
• mujoco
• rocm

Teaching materials for a future Foundation of Embodied AI course, with Chinese and English tutorials on robot dynamics, Isaac Sim, Isaac Lab, MuJoCo, robot learning, ROS 2, camera calibration, PPO, SAC, Flow Matching, GR00T, and SONIC.

Transformer-SRU LiDAR navigation for Unitree G1: Isaac Lab training, MuJoCo validation, and ROS 2 deployment.