arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Together AI

2025-09-04 至 2025-09-04 共收录 1
2509.02737 2025-09-04 cs.LG

Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient

Zhongzhu Zhou, Yibo Yang, Ziyan Chen, Fengxiang Bie, Haojun Xia, Xiaoxia Wu, Robert Wu, Ben Athiwaratkun, Bernard Ghanem, Shuaiwen Leon Song

机构 * University of Sydney(悉尼大学) King Abdullah University of Science and Technology(卡普兰·阿卜杜勒·阿齐兹科学与技术大学) Together AI

Comments 18 pages, 4 figures, 2 tables; includes supplementary material; preprint

详情

展开后加载摘要…

URL PDF HTML 收藏