Average optimal stationary policies and linear programming in countable space Markov decision processes

Average optimal stationary policies in countable space Markov decision processes and optimal solutions of an associated infinite dimensional linear program are discussed. Using the theory of linear programming in abstract spaces, sufficient conditions for the existence of optimal solutions are prese...

Full description

Saved in:
Bibliographic Details
Published in:IEEE Conference on Decision and Control pp. 3325 - 3327 vol.4
Main Author: Lasserre, J.B.
Format: Conference Proceeding
Language:English
Published: IEEE 1992
Subjects:
Linear programming
Space stations
Sufficient conditions
ISBN:9780780308725, 0780308727
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Average optimal stationary policies in countable space Markov decision processes and optimal solutions of an associated infinite dimensional linear program are discussed. Using the theory of linear programming in abstract spaces, sufficient conditions for the existence of optimal solutions are presented, and some previous ones are interpreted.< >
ISBN:9780780308725
0780308727
DOI:10.1109/CDC.1992.371023