Convergence of Controlled Models for Continuous-Time Markov Decision Processes with Constrained Average Criteria

Convergence of Controlled Models for Continuous-Time Markov Decision Processes with Constrained Average Criteria

Year:    2019

Author:    Wenzhao Zhang, Xianzhu Xiong

Annals of Applied Mathematics, Vol. 35 (2019), Iss. 4 : pp. 449–464

Abstract

This paper attempts to study the convergence of optimal values and optimal policies of continuous-time Markov decision processes (CTMDP for short) under the constrained average criteria. For a given original model $\mathcal{M}$$∞$ of CTMDP with denumerable states and a sequence {$\mathcal{M}$$n$} of CTMDP with finite states, we give a new convergence condition to ensure that the optimal values and optimal policies of {$\mathcal{M}$$n$} converge to the optimal value and optimal policy of $\mathcal{M}$$∞$ as the state space $S$$n$ of $\mathcal{M}$$n$ converges to the state space $S$$∞$ of $\mathcal{M}$$∞$, respectively. The transition rates and cost/reward functions of $\mathcal{M}$$∞$ are allowed to be unbounded. Our approach can be viewed as a combination method of linear program and Lagrange multipliers.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/2019-AAM-18090

Annals of Applied Mathematics, Vol. 35 (2019), Iss. 4 : pp. 449–464

Published online:    2019-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    16

Keywords:    continuous-time Markov decision processes optimal value optimal policies constrained average criteria occupation measures.

Author Details

Wenzhao Zhang

Xianzhu Xiong