Reinforcement learning
Policies learned through trial and reward.
- Stable-Baselines3Open source
Reliable PyTorch implementations of RL algorithms.
- CleanRLOpen source
Single-file, research-friendly deep RL implementations.
- Isaac LabOpen source
GPU-accelerated robot learning framework built on NVIDIA Isaac Sim.
- RSL RLOpen source
Fast and simple PPO implementation for legged robot learning.
- Humanoid-GymOpen source
RL for humanoid locomotion with zero-shot sim-to-real transfer.
- Walk These WaysOpen source
Robust quadruped locomotion via multiplicity of behavior.
