一作ICLR 2026Poster· Reinforcement Learning / Everything Else
Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends
Chaorui Yao · Yanxi Chen · Yuchang Sun · Yushuo Chen · Wenhao Zhang · Xuchen Pan · Yaliang Li · Bolin Ding
强化学习与后训练OpenReview