✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History
Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is based on OpenRLHF
This is the official implementation of TreePO algorithm.
```bash conda create -n rllm python=3.10 -y conda activate rllm
[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)
The main features of ruc-nlpir/arpo are: Dense Reward Optimization, Policy Optimization, Tool Optimization.
Open-source alternatives to ruc-nlpir/arpo include: thudm/treerl — Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation is… yangzhch6/treerpo — ```bash conda create -n rllm python=3.10 -y conda activate rllm. multimodal-art-projection/treepo — This is the official implementation of TreePO algorithm. prime-rl/prime — ✨ Getting Started • 📖 Introduction 🔧 Usage • 📃 Evaluation • 🎈 Citation • 🌻 Acknowledgement • 📈 Star History. trademaster-ntu/trademaster — TradeMaster is a reinforcement learning trading framework and algorithmic trading simulator designed for designing and… chanliang/eepo.