An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit
This addresses coordination challenges in multi-agent systems, offering a novel solution for scenarios with unknown collision dynamics.
The paper tackles the problem of information sharing and cooperation in Multi-Player Multi-Armed Bandits with unknown collision rewards, proposing the first algorithm that achieves logarithmic regret for this setting.
We study the problem of information sharing and cooperation in Multi-Player Multi-Armed bandits. We propose the first algorithm that achieves logarithmic regret for this problem when the collision reward is unknown. Our results are based on two innovations. First, we show that a simple modification to a successive elimination strategy can be used to allow the players to estimate their suboptimality gaps, up to constant factors, in the absence of collisions. Second, we leverage the first result to design a communication protocol that successfully uses the small reward of collisions to coordinate among players, while preserving meaningful instance-dependent logarithmic regret guarantees.