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. 2401.10383
13
0

Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis

18 January 2024
Phevos Paschalidis
Runyu Zhang
Na Li
ArXivPDFHTML
Abstract

In this paper, we formulate the multi-agent graph bandit problem as a multi-agent extension of the graph bandit problem introduced by Zhang, Johansson, and Li [CISS 57, 1-6 (2023)]. In our formulation, NNN cooperative agents travel on a connected graph GGG with KKK nodes. Upon arrival at each node, agents observe a random reward drawn from a node-dependent probability distribution. The reward of the system is modeled as a weighted sum of the rewards the agents observe, where the weights capture some transformation of the reward associated with multiple agents sampling the same node at the same time. We propose an Upper Confidence Bound (UCB)-based learning algorithm, Multi-G-UCB, and prove that its expected regret over TTT steps is bounded by O(γNlog⁡(T)[KT+DK])O(\gamma N\log(T)[\sqrt{KT} + DK])O(γNlog(T)[KT​+DK]), where DDD is the diameter of graph GGG and γ\gammaγ a boundedness parameter associated with the weight functions. Lastly, we numerically test our algorithm by comparing it to alternative methods.

View on arXiv
Comments on this paper