Asymptotic Optimality for Decentralised Bandits

Conor J. Newton*, Ayalvadi Ganesh, Henry W.J. Reeve

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)peer-review

1 Citation (Scopus)
87 Downloads (Pure)

Abstract

We consider a large number of agents collaborating on a multi-armed bandit problem with a large number of arms. The goal is to minimise the regret of each agent in a communication-constrained setting. We present a decentralised algorithm which builds upon and improves the Gossip-Insert-Eliminate method of Chawla et al. (International conference on artificial intelligence and statistics, pp 3471–3481, 2020). We provide a theoretical analysis of the regret incurred which shows that our algorithm is asymptotically optimal. In fact, our regret guarantee matches the asymptotically optimal rate achievable in the full communication setting. Finally, we present empirical results which support our conclusions.

Original languageEnglish
JournalDynamic Games and Applications
Early online date20 Jun 2022
DOIs
Publication statusPublished - 20 Jun 2022

Bibliographical note

Publisher Copyright:
© 2022, The Author(s).

Fingerprint

Dive into the research topics of 'Asymptotic Optimality for Decentralised Bandits'. Together they form a unique fingerprint.

Cite this