Geodesic
Empirical approximation in Markov games under unbounded payoff: discounted and average criteria
Kybernetika, Tome 53 (2017) no. 4, pp. 694-716

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

This work deals with a class of discrete-time zero-sum Markov games whose state process $\left\{ x_{t}\right\} $ evolves according to the equation $ x_{t+1}=F(x_{t},a_{t},b_{t},\xi _{t}),$ where $a_{t}$ and $b_{t}$ represent the actions of player 1 and 2, respectively, and $\left\{ \xi _{t}\right\} $ is a sequence of independent and identically distributed random variables with unknown distribution $\theta$. Assuming possibly unbounded payoff, and using the empirical distribution to estimate $\theta$, we introduce approximation schemes for the value of the game as well as for optimal strategies considering both, discounted and average criteria.
DOI : 10.14736/kyb-2017-4-0694
Classification : 62G07, 91A15
Keywords: Markov games; empirical estimation; discounted and average criteria 
@article{10_14736_kyb_2017_4_0694,
     author = {Luque-V\'asquez, Fernando and Minj\'arez-Sosa, J. Adolfo},
     title = {Empirical approximation in {Markov} games under unbounded payoff: discounted and average criteria},
     journal = {Kybernetika},
     pages = {694--716},
     publisher = {mathdoc},
     volume = {53},
     number = {4},
     year = {2017},
     doi = {10.14736/kyb-2017-4-0694},
     mrnumber = {3730259},
     zbl = {06819631},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2017-4-0694/}
}
TY  - JOUR
AU  - Luque-Vásquez, Fernando
AU  - Minjárez-Sosa, J. Adolfo
TI  - Empirical approximation in Markov games under unbounded payoff: discounted and average criteria
JO  - Kybernetika
PY  - 2017
SP  - 694
EP  - 716
VL  - 53
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2017-4-0694/
DO  - 10.14736/kyb-2017-4-0694
LA  - en
ID  - 10_14736_kyb_2017_4_0694
ER  - 
%0 Journal Article
%A Luque-Vásquez, Fernando
%A Minjárez-Sosa, J. Adolfo
%T Empirical approximation in Markov games under unbounded payoff: discounted and average criteria
%J Kybernetika
%D 2017
%P 694-716
%V 53
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2017-4-0694/
%R 10.14736/kyb-2017-4-0694
%G en
%F 10_14736_kyb_2017_4_0694
Luque-Vásquez, Fernando; Minjárez-Sosa, J. Adolfo. Empirical approximation in Markov games under unbounded payoff: discounted and average criteria. Kybernetika, Tome 53 (2017) no. 4, pp. 694-716. doi: 10.14736/kyb-2017-4-0694

Cité par Sources :