Semi-Offline Reinforcement Learning for Optimized Text Generation 文章

ArXiv CS.CL2026-06-05NEWSen作者: Changyu Chen, Xiting Wang, Yiqiao Jin, Victor Ye Dong, Li Dong, Jie Cao, Yi Liu, Rui Yan
查看原文 →
关系图谱

Semi-Offline Reinforcement Learning for Optimized Text Generation · 相关技术

相关技术

semi-offline RLoffline RLonline RLreinforcement learning