How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
β¨ Getting Started β’ π Introduction π§ Usage β’ π Evaluation β’ π Citation β’ π» Acknowledgement β’ π Star History
The main features of prime-rl/prime are: Critic-Based Algorithms, Dense Reward Optimization, Policy Optimization.
Open-source alternatives to prime-rl/prime include: thudm/treerl β Implementation for ACL'25 paper TreeRL: LLM Reinforcement Learning with On-Policy Tree Search. The implementation isβ¦ yangzhch6/treerpo β ```bash conda create -n rllm python=3.10 -y conda activate rllm. multimodal-art-projection/treepo β This is the official implementation of TreePO algorithm. ruc-nlpir/arpo β [ICLR 2026] Agentic Reinforced Policy Optimization (ARPO). trademaster-ntu/trademaster β TradeMaster is a reinforcement learning trading framework and algorithmic trading simulator designed for designing andβ¦ chenxinan-fdu/polaris β π A PO st-training recipe for scaling R L on A dvanced R eason I ng model S π.
ICLR 2026 Agentic Reinforced Policy Optimization (ARPO)
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