alibaba

alibaba/ROLL

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

1.9K stars 118 forks 1.9K watchers Python Apache License 2.0
agentic rlhf rlvr
View on GitHub Website
1 Open Issue Need Help Last updated: Sep 13, 2025

Open Issues Need Help

View All on GitHub
Enhanced RL Environment: A Proposed Design for LLM/VLM Scenarios 2 months ago
enhancement good first issue
alibaba/ROLL
1.9K

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Python
#agentic#rlhf#rlvr