Geodesic
Adaptive control of discrete time Markov processes by the large deviations method
Applicationes Mathematicae, Tome 27 (2000) no. 3, pp. 265-285.

Voir la notice de l'article provenant de la source Institute of Mathematics Polish Academy of Sciences

Some discrete time controlled Markov processes in a locally compact metric space whose transition operators depend on an unknown parameter are described. The adaptive controls are constructed using the large deviations of empirical distributions which are uniform in the parameter that takes values in a compact set. The adaptive procedure uses a finite family of continuous, almost optimal controls. Using the large deviations property it is shown that an adaptive control which is a fixed almost optimal control after a finite time is almost optimal with probability nearly 1.
DOI : 10.4064/am-27-3-265-285
Keywords: discrete time controlled Markov processes, adaptive control, large deviations

T. Duncan 1 ; B. Pasik-Duncan 1 ; Łukasz Stettner 1

1 
@article{10_4064_am_27_3_265_285,
     author = {T. Duncan and B. Pasik-Duncan and {\L}ukasz Stettner},
     title = {Adaptive control of discrete time {Markov} processes by the large deviations method},
     journal = {Applicationes Mathematicae},
     pages = {265--285},
     publisher = {mathdoc},
     volume = {27},
     number = {3},
     year = {2000},
     doi = {10.4064/am-27-3-265-285},
     zbl = {1006.93071},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.4064/am-27-3-265-285/}
}
TY  - JOUR
AU  - T. Duncan
AU  - B. Pasik-Duncan
AU  - Łukasz Stettner
TI  - Adaptive control of discrete time Markov processes by the large deviations method
JO  - Applicationes Mathematicae
PY  - 2000
SP  - 265
EP  - 285
VL  - 27
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.4064/am-27-3-265-285/
DO  - 10.4064/am-27-3-265-285
LA  - en
ID  - 10_4064_am_27_3_265_285
ER  - 
%0 Journal Article
%A T. Duncan
%A B. Pasik-Duncan
%A Łukasz Stettner
%T Adaptive control of discrete time Markov processes by the large deviations method
%J Applicationes Mathematicae
%D 2000
%P 265-285
%V 27
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.4064/am-27-3-265-285/
%R 10.4064/am-27-3-265-285
%G en
%F 10_4064_am_27_3_265_285
T. Duncan; B. Pasik-Duncan; Łukasz Stettner. Adaptive control of discrete time Markov processes by the large deviations method. Applicationes Mathematicae, Tome 27 (2000) no. 3, pp. 265-285. doi : 10.4064/am-27-3-265-285. http://geodesic.mathdoc.fr/articles/10.4064/am-27-3-265-285/

Cité par Sources :