Optimal stationary policies in the vector-valued Markov decision process

In this paper we are concerned with the vector-valued Markov decision process and consider the characterization of optimal stationary policies among the set of all (randomized, history-dependent) policies. Using the scalarization technique developed for the vector maximizing problem in the nonlinear programming, we present a necessary condition and a (different) sufficient condition for a stationary policy to be optimal among the set of all policies.

MoreLess

Year of publication:	1992
Authors:	Wakuta, Kazuyoshi
Published in:	Stochastic Processes and their Applications. - Elsevier, ISSN 0304-4149. - Vol. 42.1992, 1, p. 149-156
Publisher:	Elsevier
Keywords:	dynamic programming Markov decision process multiobjective proper efficiency

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10008872823