Dismemberment and Design for Controlling the Replication Variance of Regret for the Multi-Armed Bandit

Author:

Keaton Timothy J.,Sabbaghi ArmanORCID

Publisher

Springer Science and Business Media LLC

Subject

Statistics and Probability

Reference35 articles.

1. Agrawal S, Goyal N (2012) Analysis of Thompson sampling for the multi-armed bandit problem. In: Mannor S, Srebro N, Williamson RC (eds) Proceedings of the 25th annual conference on learning theory, proceedings of machine learning research, vol 23. PMLR, Edinburgh, Scotland, pp 39.1–39.26. http://proceedings.mlr.press/v23/agrawal12.html

2. Agrawal S, Goyal N (2013) Further optimal regret bounds for Thompson sampling. In: Sixteenth international conference on artificial intelligence and statistics (AISTATS). https://www.microsoft.com/en-us/research/publication/further-optimal-regret-bounds-for-thompson-sampling/

3. Allenberg C, Auer P, Györfi L, Ottucsák G (2006) Hannan consistency in on-line learning in case of unbounded losses under partial monitoring. In: Algorithmic learning theory: 17th international conference, ALT 2006, Barcelona, Spain, October 7–10, 2006, proceedings, lecture notes in computer science, pp 229–243. Springer, Berlin. https://books.google.com/books?id=lsmpCAAAQBAJ

4. Audibert JY, Munos R, Szepesvári C (2009) Exploration-exploitation tradeoff using variance estimates in multi-armed bandits. Theor Comput Sci 410(19):1876–1902

5. Auer P, Cesa-Bianchi N, Fischer P (2002) Finite-time analysis of the multiarmed bandit problem. Mach Learn 47(2–3):235–256

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