作者位次 #7/13ICML 2026Poster· Deep Learning / Foundation Models
From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning
Wenzhe Niu · Wei He · Zongxia Xie · Jinpeng Ou · Huichuan Fan · Yuchen Ge · Yanru Sun · Ziyin Wang · Yizhao Sun · Chengshun Shi · Jiuchong Gao · Jinghua Hao · Renqing He
强化学习与后训练OpenReview