An Optimal-Control Approach to Infinite-Horizon Restless Bandits: Achieving Asymptotic Optimality with Minimal Assumptions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: YAN, Chen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909139870941184
author YAN, Chen
author_facet YAN, Chen
contents We adopt an optimal-control framework for addressing the undiscounted infinite-horizon discrete-time restless $N$-armed bandit problem. Unlike most studies that rely on constructing policies based on the relaxed single-armed Markov Decision Process (MDP), we propose relaxing the entire bandit MDP as an optimal-control problem through the certainty equivalence control principle. Our main contribution is demonstrating that the reachability of an optimal stationary state within the optimal-control problem is a sufficient condition for the existence of an asymptotically optimal policy. Such a policy can be devised using an "align and steer" strategy. This reachability assumption is less stringent than any prior assumptions imposed on the arm-level MDP, notably the unichain condition is no longer needed. Through numerical examples, we show that employing model predictive control for steering generally results in superior performance compared to other existing policies.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11913
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Optimal-Control Approach to Infinite-Horizon Restless Bandits: Achieving Asymptotic Optimality with Minimal Assumptions
YAN, Chen
Optimization and Control
Dynamical Systems
Probability
93E03, 93E20, 93B03, 93B45, 90C05, 90C40
We adopt an optimal-control framework for addressing the undiscounted infinite-horizon discrete-time restless $N$-armed bandit problem. Unlike most studies that rely on constructing policies based on the relaxed single-armed Markov Decision Process (MDP), we propose relaxing the entire bandit MDP as an optimal-control problem through the certainty equivalence control principle. Our main contribution is demonstrating that the reachability of an optimal stationary state within the optimal-control problem is a sufficient condition for the existence of an asymptotically optimal policy. Such a policy can be devised using an "align and steer" strategy. This reachability assumption is less stringent than any prior assumptions imposed on the arm-level MDP, notably the unichain condition is no longer needed. Through numerical examples, we show that employing model predictive control for steering generally results in superior performance compared to other existing policies.
title An Optimal-Control Approach to Infinite-Horizon Restless Bandits: Achieving Asymptotic Optimality with Minimal Assumptions
topic Optimization and Control
Dynamical Systems
Probability
93E03, 93E20, 93B03, 93B45, 90C05, 90C40
url https://arxiv.org/abs/2403.11913