Asynchronous Multi-Agent Bandits: Fully Distributed <i>vs</i> . Leader-Coordinated Algorithms

We study the cooperative asynchronous multi-agent multi-armed bandits problem, where each agent's active (arm pulling) decision rounds are asynchronous. That is, in each round, only a subset of agents is active to pull arms, and this subset is unknown and time-varying. We consider two models of multi-agent cooperation, fully distributed and leader-coordinated, and propose algorithms for both models that attain near-optimal regret and communications bounds, both of which are almost as good as their synchronous counterparts. The fully distributed algorithm relies on a novel communication policy consisting of accuracy adaptive and on-demand components, and successive arm elimination for decision-making. For leader-coordinated algorithms, a single leader explores arms and recommends them to other agents (followers) to exploit. As agents' active rounds are unknown, a competent leader must be chosen dynamically. We propose a variant of the Tsallis-INF algorithm with low switches to choose such a leader sequence. Lastly, we report numerical simulations of our new asynchronous algorithms with other known baselines.