WooooDyy/BAPO

Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping" by Zhiheng Xi et al.

语言：Python · GitHub 星标：96 · Fork：6

话题：llm · reasoning · rl · rlvr

在 GitHub 上查看原仓库