Combinatorial Multi-armed Bandits for Resource Allocation

被引:1
|
作者
Zuo, Jinhang [1 ]
Joe-Wong, Carlee [1 ]
机构
[1] Carnegie Mellon Univ, Dept Elect & Comp Engn, Pittsburgh, PA 15213 USA
关键词
Multi-armed Bandits; Resource Allocation; OPTIMIZATION;
D O I
10.1109/CISS50987.2021.9400228
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We study the sequential resource allocation problem where a decision maker repeatedly allocates budgets between resources. Motivating examples include allocating limited computing time or wireless spectrum bands to multiple users (i.e., resources). At each timestep, the decision maker should distribute its available budgets among different resources to maximize the expected reward, or equivalently to minimize the cumulative regret. In doing so, the decision maker should learn the value of the resources allocated for each user from feedback on each user's received reward. For example, users may send messages of different urgency over wireless spectrum bands; the reward generated by allocating spectrum to a user then depends on the message's urgency. We assume each user's reward follows a random process that is initially unknown. We design combinatorial multi-armed bandit algorithms to solve this problem with discrete or continuous budgets. We prove the proposed algorithms achieve logarithmic regrets under semi-bandit feedback.
引用
收藏
页数:4
相关论文
共 50 条
  • [31] Active Learning in Multi-armed Bandits
    Antos, Andras
    Grover, Varun
    Szepesvari, Csaba
    ALGORITHMIC LEARNING THEORY, PROCEEDINGS, 2008, 5254 : 287 - +
  • [32] Multi-Armed Bandits with Cost Subsidy
    Sinha, Deeksha
    Sankararama, Karthik Abinav
    Kazerouni, Abbas
    Avadhanula, Vashist
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130
  • [33] Multi-Armed Bandits With Correlated Arms
    Gupta, Samarth
    Chaudhari, Shreyas
    Joshi, Gauri
    Yagan, Osman
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2021, 67 (10) : 6711 - 6732
  • [34] Batched Multi-armed Bandits Problem
    Gao, Zijun
    Han, Yanjun
    Ren, Zhimei
    Zhou, Zhengqing
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [35] Are Multi-Armed Bandits Susceptible to Peeking?
    Loecher, Markus
    ZAGREB INTERNATIONAL REVIEW OF ECONOMICS & BUSINESS, 2018, 21 (01): : 95 - 104
  • [36] Secure Outsourcing of Multi-Armed Bandits
    Ciucanu, Radu
    Lafourcade, Pascal
    Lombard-Platet, Marius
    Soare, Marta
    2020 IEEE 19TH INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS (TRUSTCOM 2020), 2020, : 202 - 209
  • [37] Decentralized Exploration in Multi-Armed Bandits
    Feraud, Raphael
    Alami, Reda
    Laroche, Romain
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [38] Multi-armed bandits with episode context
    Rosin, Christopher D.
    ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 2011, 61 (03) : 203 - 230
  • [39] Introduction to Multi-Armed Bandits Preface
    Slivkins, Aleksandrs
    FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2019, 12 (1-2): : 1 - 286
  • [40] Federated Multi-armed Bandits with Personalization
    Shi, Chengshuai
    Shen, Cong
    Yang, Jing
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130