作者位次 #3/10ICML 2026Poster· Reinforcement Learning / Online
GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
Hongze Tan · Zihan Wang · Jianfei Pan · Jinghao Lin · Hao Wang · Yifan Wu · Tao Chen · Zhihang Zheng · Tang · Haihua Yang
强化学习与后训练OpenReview