Average optimality in a Poissonian bandit with switching arms

被引：1
|
作者：
Donchev, DS
Yushkevich, AA
机构：
[1] Higher Inst Food & Flavor Ind, Dept Math, Plovdiv 4002, Bulgaria
[2] Univ N Carolina, Dept Math, Charlotte, NC 28223 USA
来源：
MATHEMATICAL METHODS OF OPERATIONS RESEARCH | 1997年 / 45卷 / 02期
关键词：
two-armed bandit; continuous time; switching arms; average criterion;
D O I：
10.1007/BF01193865
中图分类号：
C93 [管理学]; O22 [运筹学];
学科分类号：
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要：
A symmetric Poissonian two-armed bandit becomes, in terms of a posteriori probabilities, a piecewise deterministic Markov decision process. For the case of the switching arms, only of one which creates rewards, we solve explicitly the average optimality equation and prove that a myopic policy is average optimal.
引用
收藏
页码：265 / 280
页数：16
相关论文
共 50 条
  • [1] Average optimality in a Poissonian bandit with switching arms
    Doncho S. Donchev
    Alexander A. Yushkevich
    Mathematical Methods of Operations Research, 1997, 45 : 265 - 280
  • [2] On the two-armed bandit problem with non-observed poissonian switching of arms
    Donchev, Doncho S.
    Mathematical Methods of Operations Research, 47 (03): : 401 - 422
  • [3] On the two-armed bandit problem with non-observed Poissonian switching of arms
    Donchev, DS
    MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1998, 47 (03) : 401 - 422
  • [4] On the two-armed bandit problem with non-observed Poissonian switching of arms
    Doncho S. Donchev
    Mathematical Methods of Operations Research, 1998, 47 : 401 - 422
  • [5] INFINITE-ARMS BANDIT: OPTIMALITY VIA CONFIDENCE BOUNDS
    Chan, Hock Peng
    Hu, Shouri
    STATISTICA SINICA, 2022, 32 (03) : 1683 - 1699
  • [6] Power-of-2-Arms for Bandit Learning With Switching Costs
    Shi, Ming
    Lin, Xiaojun
    Jiao, Lei
    PROCEEDINGS OF THE 2022 THE TWENTY-THIRD INTERNATIONAL SYMPOSIUM ON THEORY, ALGORITHMIC FOUNDATIONS, AND PROTOCOL DESIGN FOR MOBILE NETWORKS AND MOBILE COMPUTING, MOBIHOC 2022, 2022, : 131 - 140
  • [7] Poissonian Two-Armed Bandit: A New Approach
    Kolnogorov, A., V
    PROBLEMS OF INFORMATION TRANSMISSION, 2022, 58 (02) : 160 - 183
  • [8] Multiple Queries as Bandit Arms
    Li, Cheng
    Resnick, Paul
    Mei, Qiaozhu
    CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2016, : 1089 - 1098
  • [9] Poissonian Two-Armed Bandit: A New Approach
    A. V. Kolnogorov
    Problems of Information Transmission, 2022, 58 : 160 - 183
  • [10] FINITE STATE MULTI-ARMED BANDIT PROBLEMS: SENSITIVE-DISCOUNT, AVERAGE-REWARD AND AVERAGE-OVERTAKING OPTIMALITY
    Katehakis, Michael N.
    Rothblum, Uriel G.
    ANNALS OF APPLIED PROBABILITY, 1996, 6 (03): : 1024 - 1034
12345