Teoriâ veroâtnostej i ee primeneniâ, Tome 23 (1978) no. 2, pp. 313-330
Citer cet article
E. A. Faǐnberg. The existence of a stationary $\varepsilon$-optimal policy for a finite Markov chain. Teoriâ veroâtnostej i ee primeneniâ, Tome 23 (1978) no. 2, pp. 313-330. http://geodesic.mathdoc.fr/item/TVP_1978_23_2_a5/
@article{TVP_1978_23_2_a5,
author = {E. A. Faǐnberg},
title = {The existence of a~stationary $\varepsilon$-optimal policy for a~finite {Markov} chain},
journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
pages = {313--330},
year = {1978},
volume = {23},
number = {2},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/TVP_1978_23_2_a5/}
}
TY - JOUR
AU - E. A. Faǐnberg
TI - The existence of a stationary $\varepsilon$-optimal policy for a finite Markov chain
JO - Teoriâ veroâtnostej i ee primeneniâ
PY - 1978
SP - 313
EP - 330
VL - 23
IS - 2
UR - http://geodesic.mathdoc.fr/item/TVP_1978_23_2_a5/
LA - ru
ID - TVP_1978_23_2_a5
ER -
%0 Journal Article
%A E. A. Faǐnberg
%T The existence of a stationary $\varepsilon$-optimal policy for a finite Markov chain
%J Teoriâ veroâtnostej i ee primeneniâ
%D 1978
%P 313-330
%V 23
%N 2
%U http://geodesic.mathdoc.fr/item/TVP_1978_23_2_a5/
%G ru
%F TVP_1978_23_2_a5
The existence of a stationary average reward $\varepsilon$-optimal policy is proved for discrete time Markov decision chains with finitely many states, compact sets of actions, continuous transition functions and upper semicontinuous reward functions.
