Open Access
Translator Disclaimer
2013 Nonuniqueness versus Uniqueness of Optimal Policies in Convex Discounted Markov Decision Processes
Raúl Montes-de-Oca, Enrique Lemus-Rodríguez, Francisco Sergio Salem-Silva
J. Appl. Math. 2013: 1-5 (2013). DOI: 10.1155/2013/271279

Abstract

From the classical point of view, it is important to determine if in a Markov decision process (MDP), besides their existence, the uniqueness of the optimal policies is guaranteed. It is well known that uniqueness does not always hold in optimization problems (for instance, in linear programming). On the other hand, in such problems it is possible for a slight perturbation of the functional cost to restore the uniqueness. In this paper, it is proved that the value functions of an MDP and its cost perturbed version stay close, under adequate conditions, which in some sense is a priority. We are interested in the stability of Markov decision processes with respect to the perturbations of the cost-as-you-go function.

Citation

Download Citation

Raúl Montes-de-Oca. Enrique Lemus-Rodríguez. Francisco Sergio Salem-Silva. "Nonuniqueness versus Uniqueness of Optimal Policies in Convex Discounted Markov Decision Processes." J. Appl. Math. 2013 1 - 5, 2013. https://doi.org/10.1155/2013/271279

Information

Published: 2013
First available in Project Euclid: 14 March 2014

zbMATH: 1266.90113
MathSciNet: MR3039713
Digital Object Identifier: 10.1155/2013/271279

Rights: Copyright © 2013 Hindawi

JOURNAL ARTICLE
5 PAGES


SHARE
Vol.2013 • 2013
Back to Top