Approximation and estimation in Markov control processes under a discounted criterion
Kybernetika, Tome 40 (2004) no. 6, p. [681]
Voir la notice de l'article provenant de la source Czech Digital Mathematics Library
We consider a class of discrete-time Markov control processes with Borel state and action spaces, and $\Re ^{k}$-valued i.i.d. disturbances with unknown density $\rho .$ Supposing possibly unbounded costs, we combine suitable density estimation methods of $\rho $ with approximation procedures of the optimal cost function, to show the existence of a sequence $\lbrace \hat{f}_{t}\rbrace $ of minimizers converging to an optimal stationary policy $f_{\infty }.$
Classification :
90B05, 90B30, 90C40, 93E10
Keywords: Markov control processes; density estimation; discounted cost criterion
Keywords: Markov control processes; density estimation; discounted cost criterion
@article{KYB_2004__40_6_a2,
author = {Minj\'arez-Sosa, J. Adolfo},
title = {Approximation and estimation in {Markov} control processes under a discounted criterion},
journal = {Kybernetika},
pages = {[681]},
publisher = {mathdoc},
volume = {40},
number = {6},
year = {2004},
mrnumber = {2120390},
zbl = {1249.93163},
language = {en},
url = {http://geodesic.mathdoc.fr/item/KYB_2004__40_6_a2/}
}
Minjárez-Sosa, J. Adolfo. Approximation and estimation in Markov control processes under a discounted criterion. Kybernetika, Tome 40 (2004) no. 6, p. [681]. http://geodesic.mathdoc.fr/item/KYB_2004__40_6_a2/