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
  • [21] ON MULTI-ARMED BANDITS AND DEBT COLLECTION
    Czekaj, Lukasz
    Biegus, Tomasz
    Kitlowski, Robert
    Tomasik, Pawel
    36TH ANNUAL EUROPEAN SIMULATION AND MODELLING CONFERENCE, ESM 2022, 2022, : 137 - 141
  • [22] Visualizations for interrogations of multi-armed bandits
    Keaton, Timothy J.
    Sabbaghi, Arman
    STAT, 2019, 8 (01):
  • [23] Multi-armed bandits with dependent arms
    Singh, Rahul
    Liu, Fang
    Sun, Yin
    Shroff, Ness
    MACHINE LEARNING, 2024, 113 (01) : 45 - 71
  • [24] On Kernelized Multi-Armed Bandits with Constraints
    Zhou, Xingyu
    Ji, Bo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [25] Multi-Armed Bandits in Metric Spaces
    Kleinberg, Robert
    Slivkins, Aleksandrs
    Upfal, Eli
    STOC'08: PROCEEDINGS OF THE 2008 ACM INTERNATIONAL SYMPOSIUM ON THEORY OF COMPUTING, 2008, : 681 - +
  • [26] Multi-Armed Bandits With Costly Probes
    Elumar, Eray Can
    Tekin, Cem
    Yagan, Osman
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2025, 71 (01) : 618 - 643
  • [27] Multi-armed bandits with episode context
    Christopher D. Rosin
    Annals of Mathematics and Artificial Intelligence, 2011, 61 : 203 - 230
  • [28] MULTI-ARMED BANDITS AND THE GITTINS INDEX
    WHITTLE, P
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1980, 42 (02): : 143 - 149
  • [29] Multi-armed bandits with switching penalties
    Asawa, M
    Teneketzis, D
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1996, 41 (03) : 328 - 348
  • [30] On Optimal Foraging and Multi-armed Bandits
    Srivastava, Vaibhav
    Reverdy, Paul
    Leonard, Naomi E.
    2013 51ST ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2013, : 494 - 499