Abstract.
In this paper we consider a singularly perturbed Markov decision process with finitely many states and actions and the limiting expected average reward criterion. We make no assumptions about the underlying ergodic structure. We present algorithms for the computation of a uniformly optimal deterministic control, that is, a control which is optimal for all values of the perturbation parameter that are sufficiently small. Our algorithms are based on Jeroslow's Asymptotic Linear Programming.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Manuscript received: July 1997/final version received: July 1998
Rights and permissions
About this article
Cite this article
Altman, E., Avrachenkov, K. & Filar, J. Asymptotic linear programming and policy improvement for singularly perturbed Markov decision processes. Mathematical Methods of OR 49, 97–109 (1999). https://doi.org/10.1007/s001860050015
Issue Date:
DOI: https://doi.org/10.1007/s001860050015