Geodesic
Nash {\Large $\epsilon $}-equilibria for stochastic games with total reward functions: an approach through Markov decision processes
Kybernetika, Tome 55 (2019) no. 1, pp. 152-165

Voir la notice de l'article provenant de la source Czech Digital Mathematics Library

The main objective of this paper is to find structural conditions under which a stochastic game between two players with total reward functions has an $\epsilon$-equilibrium. To reach this goal, the results of Markov decision processes are used to find $\epsilon$-optimal strategies for each player and then the correspondence of a better answer as well as a more general version of Kakutani's Fixed Point Theorem to obtain the $\epsilon$-equilibrium mentioned. Moreover, two examples to illustrate the theory developed are presented.
DOI : 10.14736/kyb-2019-1-0152
Classification : 90C40, 91A15, 91A50
Keywords: stochastic games; Nash equilibrium; Markov decision processes; total rewards 
@article{10_14736_kyb_2019_1_0152,
     author = {Gonz\'alez-Padilla, Francisco J. and Montes-de-Oca, Ra\'ul},
     title = {Nash {{\Large} $\epsilon $}-equilibria for stochastic games with total reward functions: an approach through {Markov} decision processes},
     journal = {Kybernetika},
     pages = {152--165},
     publisher = {mathdoc},
     volume = {55},
     number = {1},
     year = {2019},
     doi = {10.14736/kyb-2019-1-0152},
     mrnumber = {3935419},
     zbl = {07088883},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2019-1-0152/}
}
TY  - JOUR
AU  - González-Padilla, Francisco J.
AU  - Montes-de-Oca, Raúl
TI  - Nash {\Large $\epsilon $}-equilibria for stochastic games with total reward functions: an approach through Markov decision processes
JO  - Kybernetika
PY  - 2019
SP  - 152
EP  - 165
VL  - 55
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2019-1-0152/
DO  - 10.14736/kyb-2019-1-0152
LA  - en
ID  - 10_14736_kyb_2019_1_0152
ER  - 
%0 Journal Article
%A González-Padilla, Francisco J.
%A Montes-de-Oca, Raúl
%T Nash {\Large $\epsilon $}-equilibria for stochastic games with total reward functions: an approach through Markov decision processes
%J Kybernetika
%D 2019
%P 152-165
%V 55
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2019-1-0152/
%R 10.14736/kyb-2019-1-0152
%G en
%F 10_14736_kyb_2019_1_0152
González-Padilla, Francisco J.; Montes-de-Oca, Raúl. Nash {\Large $\epsilon $}-equilibria for stochastic games with total reward functions: an approach through Markov decision processes. Kybernetika, Tome 55 (2019) no. 1, pp. 152-165. doi: 10.14736/kyb-2019-1-0152

Cité par Sources :