Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption

Published: 21 Sept 2023, Last Modified: 16 Jan 2024NeurIPS 2023 spotlightEveryoneRevisionsBibTeX
Keywords: restless bandits, average reward MDP, simulation-based method, asymptotic optimality
TL;DR: We study the average reward restless bandits, and propose the first asymptotically optimal policy that does not make the uniform global attractor assumption.
Abstract: We study the infinite-horizon restless bandit problem with the average reward criterion, in both discrete-time and continuous-time settings. A fundamental goal is to efficiently compute policies that achieve a diminishing optimality gap as the number of arms, $N$, grows large. Existing results on asymptotic optimality all rely on the uniform global attractor property (UGAP), a complex and challenging-to-verify assumption. In this paper, we propose a general, simulation-based framework, Follow-the-Virtual-Advice, that converts any single-armed policy into a policy for the original $N$-armed problem. This is done by simulating the single-armed policy on each arm and carefully steering the real state towards the simulated state. Our framework can be instantiated to produce a policy with an $O(1/\sqrt{N})$ optimality gap. In the discrete-time setting, our result holds under a simpler synchronization assumption, which covers some problem instances that violate UGAP. More notably, in the continuous-time setting, we do not require \emph{any} additional assumptions beyond the standard unichain condition. In both settings, our work is the first asymptotic optimality result that does not require UGAP.
Submission Number: 9985