Non-randomized policies for constrained Markov decision processes

This paper addresses constrained Markov decision processes, with expected discounted total cost criteria, which are controlled by non-randomized policies. A dynamic programming approach is used to construct optimal policies. The convergence of the series of finite horizon value functions to the infinite horizon value function is also shown. A simple example illustrating an application is presented. Copyright Springer-Verlag 2007

MoreLess

Year of publication:	2007
Authors:	Chen, Richard ; Feinberg, Eugene
Published in:	Computational Statistics. - Springer. - Vol. 66.2007, 1, p. 165-179
Publisher:	Springer
Subject:	Constrained Markov \| Decision processes \| Dynamic programming \| Non-randomized policies

More details

Extent:	text/html
Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10010847733