ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2306.04498
11
1

Fair Multi-Agent Bandits

7 June 2023
Amir Leshem
    FedML
    FaML
ArXivPDFHTML
Abstract

In this paper, we study the problem of fair multi-agent multi-arm bandit learning when agents do not communicate with each other, except collision information, provided to agents accessing the same arm simultaneously. We provide an algorithm with regret O(N3log⁡BΔf(log⁡T)log⁡T)O\left(N^3 \log \frac{B}{\Delta} f(\log T) \log T \right)O(N3logΔB​f(logT)logT) (assuming bounded rewards, with unknown bound), where f(t)f(t)f(t) is any function diverging to infinity with ttt. This significantly improves previous results which had the same upper bound on the regret of order O(f(log⁡T)log⁡T)O(f(\log T) \log T )O(f(logT)logT) but an exponential dependence on the number of agents. The result is attained by using a distributed auction algorithm to learn the sample-optimal matching and a novel order-statistics-based regret analysis. Simulation results present the dependence of the regret on log⁡T\log TlogT.

View on arXiv
Comments on this paper