Bibliografie
Journal Article
A Counterexample on Sample-Path Optimality in Stable Markov Decision Chains with the Average Reward Criterion
, ,
: Journal of Optimization Theory and Applications vol.163, 2 (2014), p. 674-684
: 012/300/02, PSF Organization, 171396, CONACYT (México) and ASCR (Czech Republic)
: Strong sample-path optimality, Lyapunov function condition, Stationary policy, Expected average reward criterion
: http://library.utia.cas.cz/separaty/2014/E/sladky-0432661.pdf
(eng): 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.
: BB