作者位次 #5/10ICLR 2026Poster· Reinforcement Learning / Deep RL
GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning
Han Zhang · Ruibin Zheng · ZEXUAN YI · Zhuo Zhang · Hanyang Peng · HUI WANG · Jiayin Qi · Binxing Fang · Ruifeng Xu · Yue Yu
强化学习与后训练OpenReview