Multi-Player Bandits: A Trekking Approach

TL;DR

This paper introduces a trekking approach for multi-player stochastic bandits that reduces collisions and improves regret, applicable in both static and dynamic player scenarios, validated through simulations and real tests.

Contribution

The paper proposes a novel trekking algorithm that avoids estimating the number of players, leading to fewer collisions and better regret performance in multi-player bandits.

Findings

Guarantees constant regret in static scenarios.

Achieves sub-linear regret in dynamic scenarios.

Validated through simulations and real test-bed experiments.

Abstract

We study stochastic multi-armed bandits with many players. The players do not know the number of players, cannot communicate with each other and if multiple players select a common arm they collide and none of them receive any reward. We consider the static scenario, where the number of players remains fixed, and the dynamic scenario, where the players enter and leave at any time. We provide algorithms based on a novel `trekking approach' that guarantees constant regret for the static case and sub-linear regret for the dynamic case with high probability. The trekking approach eliminates the need to estimate the number of players resulting in fewer collisions and improved regret performance compared to the state-of-the-art algorithms. We also develop an epoch-less algorithm that eliminates any requirement of time synchronization across the players provided each player can detect the presence of other players on an arm. We validate our theoretical guarantees using simulation based and real test-bed based experiments.