Vector-valued Markov decision processes and the systems of linear inequalities

For a vector-valued Markov decision process, we characterize optimal (deterministic) stationary policies by systems of linear inequalities and present an algorithm for finding all optimal stationary policies from among all randomized, history-remembering ones. The algorithm consists of improving the policies and of checking the optimality of a policy by solving the associated system of linear inequalities via Fourier elimination.

MoreLess

Year of publication:	1995
Authors:	Wakuta, Kazuyoshi
Published in:	Stochastic Processes and their Applications. - Elsevier, ISSN 0304-4149. - Vol. 56.1995, 1, p. 159-169
Publisher:	Elsevier
Keywords:	Dynamic programming Markov decision process Multiobjective Linear inequalities Fourier elimination

More details

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

Persistent link: https://www.econbiz.de/10008872832