0449029 20240103210937.720151023235959.9 000358811700008 84938521589 10.1239/jap/1437658607 20 s. P cav_un_epca*02568750021-9002522 (2015)419-440Cambridge University Press Dominated Convergence theorem for the expected average criterion Discrepancy function Kolmogorov inequality Innovations Strong sample-path optimality cav_un_auth*0307645 Cavazos-Cadena R. MX 50 cav_un_auth*0238984 Montes-de-Oca R. MX 25 cav_un_auth*0101196 Sladký Karel Ekonometrie Department of Econometrics E E UTIA-B Department of Econometrics 25 Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2015/E/sladky-0449029.pdf 171396 GA AV ČR CZ cav_un_auth*0307567 This work concerns discrete-time Markov decision chains with denumerable state and compact action sets. Besides standard continuity requirements, the main assumption on the model is that it admits a Lyapunov function m. In this context the average reward criterion is analyzed from the sample-path point of view. The main conclusion is that, if the expected average reward associated to m^2 is finite under any policy, then a stationary policy obtained from the optimality equation in the standard way is sample-path average optimal in a strong sense. 2016 BC 3 RVO:67985556 http://hdl.handle.net/11104/0250631 cav_un_auth*0320900 Universidad Aut onoma Metropolitana, Campus Iztapalapa, Avenida San Rafael Atlixco #186, Colonia Vicentina, M exico 09340, MX S STATISTICS&PROBABILITY 0.864 0.131 999.9 0.00534 0.784 2677 0.724 Q2 0.618 84 Q3 50.157 34.6 Q2 Q2 34.553 2015 84938521589 SCOPUS 000358811700008 WOS cav_un_epca*0256875 Journal of Applied Probability 0021-9002 1475-6072 Roč. 52 č. 2 2015 419 440 Cambridge University Press