On-Demand Communication for Asynchronous Multi-Agent Bandits

TL;DR

This paper introduces ODC, an on-demand communication protocol for asynchronous multi-agent bandits that adapts to agents' pull times, improving learning efficiency with minimal communication overhead.

Contribution

It proposes a novel, adaptable communication protocol for asynchronous multi-agent bandits that can be integrated into existing algorithms without performance loss.

Findings

ODC reduces communication costs in heterogeneous settings.

Integrated algorithms achieve near-optimal regret.

ODC adapts to agents' pull time heterogeneity.

Abstract

This paper studies a cooperative multi-agent multi-armed stochastic bandit problem where agents operate asynchronously -- agent pull times and rates are unknown, irregular, and heterogeneous -- and face the same instance of a K-armed bandit problem. Agents can share reward information to speed up the learning process at additional communication costs. We propose ODC, an on-demand communication protocol that tailors the communication of each pair of agents based on their empirical pull times. ODC is efficient when the pull times of agents are highly heterogeneous, and its communication complexity depends on the empirical pull times of agents. ODC is a generic protocol that can be integrated into most cooperative bandit algorithms without degrading their performance. We then incorporate ODC into the natural extensions of UCB and AAE algorithms and propose two communication-efficient cooperative algorithms. Our analysis shows that both algorithms are near-optimal in regret.