A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players

Abstract

We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider the challenging heterogeneous setting, in which different arms may have different means for different players, and propose a new and efficient algorithm that combines the idea of leveraging forced collisions for implicit communication and that of performing matching eliminations. We present a finite-time analysis of our algorithm, giving the first sublinear minimax regret bound for this problem, and prove that if the optimal assignment of players to arms is unique, our algorithm attains the optimal O(ln(T )) regret, solving an open question raised at NeurIPS 2018 by Bistritz and Leshem (2018).
Fichier principal
Vignette du fichier
aistats20.pdf (577.98 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02006069 , version 1 (04-02-2019)
hal-02006069 , version 2 (05-06-2019)
hal-02006069 , version 3 (03-03-2020)

Identifiers

Cite

Etienne Boursier, Emilie Kaufmann, Abbas Mehrabian, Vianney Perchet. A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players. AISTATS 2020 - 23rd International Conference on Artificial Intelligence and Statistics, Aug 2020, Palermo, Italy. ⟨hal-02006069v3⟩
358 View
344 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More