作者位次 #4/7ICML 2026Poster
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
Zhicheng Cai · Xinyuan Guo · Hanlin Wu · Mingxuan Wang · Wei-Ying Ma · Ya-Qin Zhang · Hao Zhou
强化学习与后训练OpenReview