A novel individually rational objective in multi-agent multi-armed bandits: Algorithms and regret bounds

We study a two-player stochastic multi-armed bandit (MAB) problem with different expected rewards for each player, a generalisation of two-player general sum repeated games to stochastic rewards. Our aim is to find the egalitarian bargaining solution (EBS) for the repeated game, which can lead to mu...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Vol. 2020-May; p. 1395
Main Authors: Tossou, Aristide, Dimitrakakis, Christos, Rzepecki, Jaroslaw, Hofmann, K.
Format: Conference Proceeding
Language:English
Published: 2020
Subjects:
Egalitarian bargaining solution
Individual rationality
Multi-armed bandits
Safety
ISSN:1558-2914, 1548-8403
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We study a two-player stochastic multi-armed bandit (MAB) problem with different expected rewards for each player, a generalisation of two-player general sum repeated games to stochastic rewards. Our aim is to find the egalitarian bargaining solution (EBS) for the repeated game, which can lead to much higher rewards than the maximin value of both players. Our main contribution is the derivation of an algorithm, UCRG, that achieves simultaneously for both players, a high-probability regret bound of order Õ ( T2/3) after any T rounds of play. We demonstrate that our upper bound is nearly optimal by proving a lower bound of Ω ( T2/3) for any algorithm. Experiments confirm our theoretical results and the superiority of UCRG compared to the well-known explore-then-commit heuristic.
ISSN:1558-2914
1548-8403
DOI:10.5555/3398761.3398922