Game of thrones: Fully distributed learning for multiplayer bandits

Ilai Bistritz, Amir Leshem

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

We consider an N-player multiarmed bandit game in which each player chooses one out of M arms for T turns. Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed or Markovian. When two or more players choose the same arm, they all receive zero reward. Performance is measured using the expected sum of regrets compared with optimal assignment of arms to players that maximizes the sum of expected rewards. We assume that each player only knows that player’s own actions and the reward that player 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-O(logT). This is the first algorithm to achieve a near order optimal 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)159-178
Number of pages20
JournalMathematics of Operations Research
Volume46
Issue number1
DOIs
StatePublished - Feb 2021
Externally publishedYes

Bibliographical note

Publisher Copyright:
Copyright: © 2020 INFORMS.

Keywords

  • Game theory
  • Multiagent learning
  • Multiarmed bandits
  • Resource allocation

Fingerprint

Dive into the research topics of 'Game of thrones: Fully distributed learning for multiplayer bandits'. Together they form a unique fingerprint.

Cite this