Epsilon-Optimal Policies for Average-Cost Separable MDPs with Perturbations

Abstract

We study a class of infinite-horizon average-cost Markov Decision Processes (MDPs) whose reward and transition structures are nearly separable. For the totally separable baseline (that is, with no perturbation), we derive an explicit stationary decision rule that is exactly average-optimal. We then show that under an epsilon-perturbation of the separable structure, this policy remains epsilon-optimal, meaning that the loss in the average reward is of order O(epsilon).