arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Machine Learning · 会议 · Machine Learning

2026-01-29 至 2026-01-29 共收录 2
2601.20116 2026-01-29 cs.LG

In-Context Reinforcement Learning From Suboptimal Historical Data

基于次优历史数据的上下文强化学习

Juncheng Dong, Moyang Guo, Ethan X. Fang, Zhuoran Yang, Vahid Tarokh

机构 * Department of Electrical and Computer Engineering, Duke University, Durham, US(电气与计算机工程系,杜克大学,达勒姆,美国) Department of Biostatistics and Bioinformatics, Duke University, Durham, US(生物统计学与生物信息学系,杜克大学,达勒姆,美国) Department of Statistics and Data Science, Yale University, New Haven, US(统计学与数据科学系,耶鲁大学,新 Haven,美国)

AI总结 DIT框架通过结合价值函数估计和加权最大似然估计,有效提升在次优历史数据下的强化学习性能。

Comments Accepted to Forty-Second International Conference on Machine Learning (ICML2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10792 2026-01-29 cs.LG

A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments

一种通用的物理增强状态空间模型用于复杂环境中的长期动态预测

Yuchen Wang, Hongjue Zhao, Haohong Lin, Enze Xu, Lifang He, Huajie Shao

机构 * University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Carnegie Mellon University(卡内基梅隆大学) Lehigh University(莱特大学)

AI总结 本文提出Phy-SSM,一种结合物理知识的状态空间模型,用于复杂环境中的长期动态预测,通过整合部分物理知识提升模型泛化能力与预测性能。

Comments 8 pages, 6 figures, accepted in ICML 2025

Journal ref Proceedings of the 42nd International Conference on Machine Learning (ICML 2025), Proceedings of Machine Learning Research 267:65708-65737, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏