OpenRLHF
ActiveDescription
OpenRLHF is a high-performance agentic RL framework based on Ray and vLLM, offering PPO, DAPO, and REINFORCE++ algorithms for large-scale training of agents and vision-language models.
Related Projects
ART
9.4k · Python
ART (Agent Reinforcement Trainer) trains multi-step agents for real-world tasks using GRPO reinforcement learning, enabling on-the-job training for models like Qwen, Llama, and more.
reinforcement-learningagent-trainingGRPO +3
AgentScope
25.0k · Python
Open-source multi-agent framework from Alibaba, enabling the construction of observable and interpretable agents with rich distributed capabilities.
agent-frameworkmulti-agentdistributed +2
Pearl
3.0k · Jupyter Notebook
A production-ready Reinforcement Learning AI Agent Library from Meta with comprehensive algorithm implementations.
reinforcement-learningmetaproduction +2
Agent Lightning
17.2k · Python
Agent Lightning is Microsoft's open-source training framework for AI agents, using reinforcement learning to enhance agent capabilities.
agent-trainingreinforcement-learningllm +2