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
  • [1] Network Defense Resource Allocation Scheme with Multi-armed Bandits
    Huang, Ning
    Feng, Xue-cai
    Zhang, Rui
    Yang, Xiu-gui
    Xia, Hui
    WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS (WASA 2022), PT I, 2022, 13471 : 326 - 337
  • [2] Combinatorial Pure Exploration of Multi-Armed Bandits
    Chen, Shouyuan
    Lin, Tian
    King, Irwin
    Lyu, Michael R.
    Chen, Wei
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), 2014, 27
  • [3] Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Bandits
    Li, Dexun
    Varakantham, Pradeep
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, VOL 180, 2022, 180 : 1158 - 1167
  • [4] Networked Stochastic Multi-Armed Bandits with Combinatorial Strategies
    Tang, Shaojie
    Zhou, Yaqin
    Han, Kai
    Zhang, Zhao
    Yuan, Jing
    Wu, Weili
    2017 IEEE 37TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2017), 2017, : 786 - 793
  • [5] A Differentially Private Approach for Budgeted Combinatorial Multi-Armed Bandits
    Wang, Hengzhi
    Cui, Laizhong
    Wang, En
    Liu, Jiangchuan
    IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, 2025, 22 (01) : 424 - 439
  • [6] Combinatorial Multi-Armed Bandits with Concave Rewards and Fairness Constraints
    Xu, Huanle
    Liu, Yang
    Lau, Wing Cheong
    Li, Rui
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2554 - 2560
  • [7] On Kernelized Multi-armed Bandits
    Chowdhury, Sayak Ray
    Gopalan, Aditya
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
  • [8] Multi-armed Bandits with Compensation
    Wang, Siwei
    Huang, Longbo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [9] Regional Multi-Armed Bandits
    Wang, Zhiyang
    Zhou, Ruida
    Shen, Cong
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 84, 2018, 84
  • [10] Federated Multi-Armed Bandits
    Shi, Chengshuai
    Shen, Cong
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 9603 - 9611