Distributed multi-player bandits - A game of thrones approach

Ilai Bistritz, Amir Leshem

Research output: Contribution to journalConference articlepeer-review

77 Scopus citations

Abstract

We consider a multi-armed bandit game where N players compete for K arms for T turns. Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed. Performance is measured using the expected sum of regrets, compared to the optimal assignment of arms to players. We assume that each player only knows her actions and the reward she received each turn. Players cannot observe the actions of other players, and no communication between players is possible. We present a distributed algorithm and prove that it achieves an expected sum of regrets of near-Olog2 T. This is the first algorithm to achieve a poly-logarithmic regret in this fully distributed scenario. All other works have assumed that either all players have the same vector of expected rewards or that communication between players is possible.

Original languageAmerican English
Pages (from-to)7211-7221
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2018-December
StatePublished - 2018
Externally publishedYes
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: 2 Dec 20188 Dec 2018

Bibliographical note

Publisher Copyright:
© 2018 Curran Associates Inc.All rights reserved.

Fingerprint

Dive into the research topics of 'Distributed multi-player bandits - A game of thrones approach'. Together they form a unique fingerprint.

Cite this