2021/11/22 by Jingxuan Zhu, Zhu, Jingxuan, Ethan Mulle +5 · 1 citation
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Age of Information Optimization #Cognitive Radio Networks and Spectrum Sensing #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2111.10933
openalex publication_date 2021/11/22 · openalex created_date 2021/12/06 · openalex updated_date 2026/07/28
This paper studies a decentralized homogeneous multi-armed bandit problem in a multi-agent network. The problem is simultaneously solved by N agents assuming they face a common set of M arms and share the same arms' reward distributions. Each agent can receive information only from its neighbors, where the neighbor relationships among the agents are described by a fixed graph. Two fully decentralized upper confidence bound (UCB) algorithms are proposed for undirected graphs, respectively based on the classic algorithm and the state-of-the-art Kullback-Leibler upper confidence bound (KL-UCB) algorithm. The proposed decentralized UCB1 and KL-UCB algorithms permit each agent in the network to achieve a better logarithmic asymptotic regret than their single-agent counterparts, provided that the agent has at least one neighbor, and the more neighbors an agent has, the better regret it will have, meaning that the sum is more than its component parts. The same algorithm design framework is also extended to directed graphs through the design of a variant of the decentralized UCB1 algorithm, which outperforms the single-agent UCB1 algorithm.