Geodesic
Markov decision processes with arbitrary real-valued criteria
Teoriâ veroâtnostej i ee primeneniâ, Tome 27 (1982) no. 3, pp. 456-473 
E. A. Faǐnberg. Markov decision processes with arbitrary real-valued criteria. Teoriâ veroâtnostej i ee primeneniâ, Tome 27 (1982) no. 3, pp. 456-473. http://geodesic.mathdoc.fr/item/TVP_1982_27_3_a4/
@article{TVP_1982_27_3_a4,
     author = {E. A. Faǐnberg},
     title = {Markov decision processes with arbitrary real-valued criteria},
     journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
     pages = {456--473},
     year = {1982},
     volume = {27},
     number = {3},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/TVP_1982_27_3_a4/}
}
TY  - JOUR
AU  - E. A. Faǐnberg
TI  - Markov decision processes with arbitrary real-valued criteria
JO  - Teoriâ veroâtnostej i ee primeneniâ
PY  - 1982
SP  - 456
EP  - 473
VL  - 27
IS  - 3
UR  - http://geodesic.mathdoc.fr/item/TVP_1982_27_3_a4/
LA  - ru
ID  - TVP_1982_27_3_a4
ER  - 
%0 Journal Article
%A E. A. Faǐnberg
%T Markov decision processes with arbitrary real-valued criteria
%J Teoriâ veroâtnostej i ee primeneniâ
%D 1982
%P 456-473
%V 27
%N 3
%U http://geodesic.mathdoc.fr/item/TVP_1982_27_3_a4/
%G ru
%F TVP_1982_27_3_a4

Voir la notice de l'article provenant de la source Math-Net.Ru

We consider discrete time infinite horizon non-stationary Markov decision models with Borel state and action spaces. A criterion is a real-valued function defined on the space of strategic measures. We obtain general results and then use them to study the following criterions and their combinations: the expected total reward criterion, the expected utility criterion, the expected average criterion, the asymptotic reward criterion.