Note on stability estimation in average Markov control processes
Kybernetika, Tome 51 (2015) no. 4, pp. 629-638
Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

We study the stability of average optimal control of general discrete-time Markov processes. Under certain ergodicity and Lipschitz conditions the stability index is bounded by a constant times the Prokhorov distance between distributions of random vectors determinating the “original and the perturbated” control processes.
We study the stability of average optimal control of general discrete-time Markov processes. Under certain ergodicity and Lipschitz conditions the stability index is bounded by a constant times the Prokhorov distance between distributions of random vectors determinating the “original and the perturbated” control processes.
DOI : 10.14736/kyb-2015-4-0629
Classification : 90C40, 93E20
Keywords: discrete-time Markov control processes; average criterion; stability index; Prokhorov metric
@article{10_14736_kyb_2015_4_0629,
     author = {Mart{\'\i}nez S\'anchez, Jaime and Zaitseva, Elena},
     title = {Note on stability estimation in average {Markov} control processes},
     journal = {Kybernetika},
     pages = {629--638},
     year = {2015},
     volume = {51},
     number = {4},
     doi = {10.14736/kyb-2015-4-0629},
     mrnumber = {3423190},
     zbl = {06537775},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2015-4-0629/}
}
TY  - JOUR
AU  - Martínez Sánchez, Jaime
AU  - Zaitseva, Elena
TI  - Note on stability estimation in average Markov control processes
JO  - Kybernetika
PY  - 2015
SP  - 629
EP  - 638
VL  - 51
IS  - 4
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2015-4-0629/
DO  - 10.14736/kyb-2015-4-0629
LA  - en
ID  - 10_14736_kyb_2015_4_0629
ER  - 
%0 Journal Article
%A Martínez Sánchez, Jaime
%A Zaitseva, Elena
%T Note on stability estimation in average Markov control processes
%J Kybernetika
%D 2015
%P 629-638
%V 51
%N 4
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2015-4-0629/
%R 10.14736/kyb-2015-4-0629
%G en
%F 10_14736_kyb_2015_4_0629
Martínez Sánchez, Jaime; Zaitseva, Elena. Note on stability estimation in average Markov control processes. Kybernetika, Tome 51 (2015) no. 4, pp. 629-638. doi: 10.14736/kyb-2015-4-0629

[1] Arapostathis, A., Borkar, V. S., Fernández-Gaucherand, E., Ghosh, M. K., Marcus, S. I.: Discrete-time controlled Markov processes with average cost criterion: A survey. SIAM J. Control and Optimization 31 (1993), 282-344. | DOI | MR | Zbl

[2] Dudley, R. M.: Real Analysis and Probability. Wadsworth and Brooks/Cole, Pacific Grove 1989. | DOI | MR | Zbl

[3] Dudley, R. M.: The speed of mean Glivenko-Cantelly convergence. Ann. Math. Stat. 40 (1969), 40-50. | DOI | MR

[4] Dynkin, E. B., Yushkevich, A. A.: Controlled Markov Processes. Springer-Verlag, New York 1979. | DOI | MR

[5] Gordienko, E., Lemus-Rodríguez, E., Montes-de-Oca, R.: Average cost Markov control processes: stability with respect to the Kantorovich metric. Math. Methods Oper. Res. 70 (2009), 13-33. | DOI | MR | Zbl

[6] Gordienko, E. I.: Stability estimates for controlled Markov chains with a minorant. J. Soviet. Math. 40 (1988), 481-486. | DOI | MR | Zbl

[7] Gordienko, E. I., Yushkevich, A. A.: Stability estimates in the problem of average optimal switching of a Markov Chain. Math. Methods Oper. Res. 57 (2003), 345-365. | MR | Zbl

[8] Hernández-Lerma, O.: Adaptive Markov Control Processes. Springer-Verlag, New York 1989. | DOI | MR | Zbl

[9] Montes-de-Oca, R., Salem-Silva, F.: Estimates for perturbations of average Markov decision processes with a minimal state and upper bounded by stochastically ordered Markov chains. Kybernetika 41 (2005), 757-772. | MR | Zbl

[10] Rachev, S. T., Rüschendorf, L.: Mass Transportation Problem, Vol. II: Applications. Springer, New York 1998. | MR

[11] Vega-Amaya, O.: The average cost optimality equation: a fixed point approach. Bol. Soc. Math. Mexicana 9 (2003), 185-195. | MR | Zbl

Cité par Sources :