Geodesic
An approach for determining the optimal strategies for an average Markov decision problem with finite state and action spaces
Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica, no. 1 (2018), pp. 34-49

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

The average reward Markov decision problem with finite state and action spaces is considered and an approach for determining the optimal pure and mixed stationary strategies for this problem is proposed. We show that the considered problem can be formulated in terms of stationary strategies where the objective function is quasi-monotonic (i.e. it is quasi-convex and quasi-concave) on the feasible set of stationary strategies. Using such a quasi-monotonic programming model with linear constraints we ground algorithms for determining the optimal pure and mixed stationary strategies for the average Markov decision problem. 
@article{BASM_2018_1_a3,
     author = {Dmitrii Lozovanu and Stefan Pickl},
     title = {An approach for determining the optimal strategies for an average {Markov} decision problem with finite state and action spaces},
     journal = {Buletinul Academiei de \c{S}tiin\c{t}e a Republicii Moldova. Matematica},
     pages = {34--49},
     publisher = {mathdoc},
     number = {1},
     year = {2018},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/BASM_2018_1_a3/}
}
TY  - JOUR
AU  - Dmitrii Lozovanu
AU  - Stefan Pickl
TI  - An approach for determining the optimal strategies for an average Markov decision problem with finite state and action spaces
JO  - Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica
PY  - 2018
SP  - 34
EP  - 49
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/BASM_2018_1_a3/
LA  - en
ID  - BASM_2018_1_a3
ER  - 
%0 Journal Article
%A Dmitrii Lozovanu
%A Stefan Pickl
%T An approach for determining the optimal strategies for an average Markov decision problem with finite state and action spaces
%J Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica
%D 2018
%P 34-49
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/BASM_2018_1_a3/
%G en
%F BASM_2018_1_a3
Dmitrii Lozovanu; Stefan Pickl. An approach for determining the optimal strategies for an average Markov decision problem with finite state and action spaces. Buletinul Academiei de Ştiinţe a Republicii Moldova. Matematica, no. 1 (2018), pp. 34-49. http://geodesic.mathdoc.fr/item/BASM_2018_1_a3/