%0 Journal Article
%A Hernández-Lerma, Onésimo
%T Approximation and adaptive control of Markov processes: Average reward criterion
%J Kybernetika
%D 1987
%P 265-288
%V 23
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/KYB_1987__23_4_a0/
%G en
%F KYB_1987__23_4_a0