Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles

Author:

Golowich Noah1ORCID,Moitra Ankur1ORCID,Rohatgi Dhruv1ORCID

Affiliation:

1. Massachusetts Institute of Technology, Cambridge, USA

Funder

Fannie and John Hertz Foundation Fellowship

NSF GRFP Fellowship

Microsoft Trustworthy AI Grant

ONR Young Investigator Award

David and Lucile Packard Foundation

DOD NDSEG Fellowship

Publisher

ACM

Reference54 articles.

1. Yasin Abbasi-Yadkori, David Pal, and Csaba Szepesvari. 2012. Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits. In Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, Neil D. Lawrence and Mark Girolami (Eds.) (Proceedings of Machine Learning Research, Vol. 22). PMLR, La Palma, Canary Islands. 1–9.

2. Mohammad Gheshlaghi Azar, Ian Osband, and Rémi Munos. 2017. Minimax Regret Bounds for Reinforcement Learning. In Proceedings of the 34th International Conference on Machine Learning - Volume 70 (ICML’17). JMLR.org, 263–272.

3. James Bagnell, Sham M Kakade, Jeff Schneider, and Andrew Ng. 2003. Policy search by dynamic programming. Advances in neural information processing systems, 16 (2003).

4. Square-root lasso: pivotal recovery of sparse signals via conic programming

5. Simultaneous analysis of Lasso and Dantzig selector

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles;Proceedings of the 56th Annual ACM Symposium on Theory of Computing;2024-06-10

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3