Tag: reinforcement-learning
23 results
TensorTrade
Reinforcement learning framework for trading agents
Learning Humanoid Walking
Training humanoid locomotion with RL
Humanoid-Gym
RL for humanoids with zero-shot sim-to-real
HIL-SERL
Human-in-the-loop RL for dexterous manipulation
TWIST2 MJLab
MJLab task package for Unitree G1 motion tracking
Isaac Lab
Unified framework for robot learning
LeRobot
End-to-end learning for real-world robotics
OpenArm
Fully open-source humanoid arm
DreamerV3
Mastering diverse domains through world models
DreamerV2
Mastering Atari with discrete world models
Gym-Anything
Turn any software into an agent environment
Open Duck Motion Generator
Reference motion generator for Open Duck
Kinesis
RL motion imitation for musculoskeletal control
MetaClaw
An agent that learns and evolves as you talk
Agent0
Self-evolving agents from zero data
AgentGym-RL
Multi-turn RL for long-horizon LLM agents
TorchTrade
Modular RL framework for algorithmic trading
TextArena
Competitive text games for LLM evaluation and RL
IGPO
Information gain policy optimization for search agents
OpenClaw-RL
Train an agent simply by talking to it