OpenRLHF
by OpenRLHF (organization)
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL) (description from the project’s GitHub page)
Repository facts
- Stars
- 10,095
- Forks
- 1,049
- Open issues and pull requests
- 403
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- OpenRLHF · Organization
- Created
- Jul 30, 2023
- Last push
- Oct 5, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 4,338: PKU-Alignment/safe-rlhf
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
1,620 starsPythonApache-2.0Last push Nov 24, 2025
Rank 6,932: whitecircle/halo
Halo is an open-source framework built by White Circle for training large language and multimodal models
825 starsPythonOther licenseLast push Oct 15, 2026
Rank 6,829: tatsu-lab/alpaca_farm
A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.
844 starsPythonApache-2.0Last push Jul 1, 2024
Rank 772: vwxyzjn/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
10,572 starsPythonOther licenseLast push Apr 20, 2026
Rank 2,021: ikostrikov/pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored a…
3,907 starsPythonMITLast push May 29, 2022
Rank 3,175: nikhilbarhate99/PPO-PyTorch
Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
2,384 starsPythonMITLast push Jul 9, 2024