Libraries & frameworks
rlinf
rlinf/rlinf
A scalable open-source RL infrastructure for embodied and agentic AI, spanning simulators, VLA models, and distributed training.
Topics
Related projects
RAGEN2.8kA research RL framework for training reasoning LLM agents with multi-turn optimization, diagnostics and built-in environments.
agent-lightning18.9kA lightweight RL framework for training AI agents directly with their real harnesses and environments.
humanoid-motion-intelligence704A curated Chinese knowledge base on humanoid motion intelligence, indexing paper reviews, open-source projects, datasets, simulation tools and career resources.
ml-agents19.9kUnity's open toolkit for training intelligent game agents with deep reinforcement and imitation learning through Python and Unity APIs.
cleanrl10.7kHigh-quality single-file deep RL library covering PPO, DQN and SAC, focused on readability and reproducible experiment management.
oumi9.4kAn open platform for end-to-end foundation-model training, evaluation and deployment across text and vision models.