Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
Author:
Affiliation:
1. Institute de Mathématiques de Toulouse (IMT): Université Paul Sabatier—The French National Research Center (CNRS), 31062 Toulouse, France
2. HEC Paris Management Research Group (GREGHEC): HEC Paris—CNRS, 78351 Jouy-en-Josas, France
Publisher
Institute for Operations Research and the Management Sciences (INFORMS)
Subject
Management Science and Operations Research,Computer Science Applications,General Mathematics
Reference22 articles.
1. UCB revisited: Improved regret bounds for the stochastic multi-armed bandit problem
2. The Nonstochastic Multiarmed Bandit Problem
3. Bubeck S (2010) Bandits games and clustering foundations. PhD thesis, Université Lille 1, Villeneuve-d’Ascq, France.
Cited by 67 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. Finite-Time Identification of Linear Systems: Fundamental Limits and Optimal Algorithms;IEEE Transactions on Automatic Control;2023-05
2. Adaptive Sequential Experiments with Unknown Information Arrival Processes;Manufacturing & Service Operations Management;2022-09
3. Sequential Multi-Hypothesis Testing in Multi-Armed Bandit Problems: An Approach for Asymptotic Optimality;IEEE Transactions on Information Theory;2022-07
4. Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach;IEEE INFOCOM 2022 - IEEE Conference on Computer Communications;2022-05-02
5. Learning and data-driven optimization in queues with strategic customers;Queueing Systems;2022-04
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