A Counterexample on Sample-Path Optimality in Stable Markov Decision Chains with the Average Reward Criterion

0432661 - ÚTIA 2015 RIV US eng J - Journal Article
Cavazos-Cadena, R. - Montes-de-Oca, R. - Sladký, Karel
A Counterexample on Sample-Path Optimality in Stable Markov Decision Chains with the Average Reward Criterion.
Journal of Optimization Theory and Applications. Roč. 163, č. 2 (2014), s. 674-684. ISSN 0022-3239. E-ISSN 1573-2878
Grant - others:PSF Organization(US) 012/300/02; CONACYT (México) and ASCR (Czech Republic)(MX) 171396
Institutional support: RVO:67985556
Keywords : Strong sample-path optimality * Lyapunov function condition * Stationary policy * Expected average reward criterion
Subject RIV: BB - Applied Statistics, Operational Research
Impact factor: 1.509, year: 2014
http://library.utia.cas.cz/separaty/2014/E/sladky-0432661.pdf

This note deals with Markov decision chains evolving on a denumerable state space. Under standard continuity compactness requirements, an explicit example is provided to show that, with respect to a strong sample-path average reward criterion, the Lyapunov function condition does not ensure the existence of an optimal stationary policy.
Permanent Link: http://hdl.handle.net/11104/0237102