[ICML 2022] The official implementation of DWBC in "Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"

Train transformer language models with reinforcement learning.

verl: Volcano Engine Reinforcement Learning for LLMs

Implementations and examples of common offline policy evaluation methods in Python.

🙌 OpenHands: Code Less, Make More

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Awesome List for Agentic RL

[NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

Resources for the Enigmata Project.

slime is an LLM post-training framework for RL Scaling.