Geodesic
On adaptive control of a partially observed Markov chain
Applicationes Mathematicae, Tome 22 (1993) no. 2, pp. 165-180.

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

A control problem for a partially observable Markov chain depending on a parameter with long run average cost is studied. Using uniform ergodicity arguments it is shown that, for values of the parameter varying in a compact set, it is possible to consider only a finite number of nearly optimal controls based on the values of actually computable approximate filters. This leads to an algorithm that guarantees nearly selfoptimizing properties without identifiability conditions. The algorithm is based on probing control, whose cost is additionally assumed to be periodically observable.
DOI : 10.4064/am-22-2-165-180
Keywords: uniform ergodicity, long run average cost, filtering process, adaptive control, approximate filter, partially observed systems

Giovanni Di Masi 1 ; Łukasz Stettner 1

1 
@article{10_4064_am_22_2_165_180,
     author = {Giovanni Di Masi and {\L}ukasz Stettner},
     title = {On adaptive control of a partially observed {Markov} chain},
     journal = {Applicationes Mathematicae},
     pages = {165--180},
     publisher = {mathdoc},
     volume = {22},
     number = {2},
     year = {1993},
     doi = {10.4064/am-22-2-165-180},
     zbl = {0808.93070},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.4064/am-22-2-165-180/}
}
TY  - JOUR
AU  - Giovanni Di Masi
AU  - Łukasz Stettner
TI  - On adaptive control of a partially observed Markov chain
JO  - Applicationes Mathematicae
PY  - 1993
SP  - 165
EP  - 180
VL  - 22
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.4064/am-22-2-165-180/
DO  - 10.4064/am-22-2-165-180
LA  - en
ID  - 10_4064_am_22_2_165_180
ER  - 
%0 Journal Article
%A Giovanni Di Masi
%A Łukasz Stettner
%T On adaptive control of a partially observed Markov chain
%J Applicationes Mathematicae
%D 1993
%P 165-180
%V 22
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.4064/am-22-2-165-180/
%R 10.4064/am-22-2-165-180
%G en
%F 10_4064_am_22_2_165_180
Giovanni Di Masi; Łukasz Stettner. On adaptive control of a partially observed Markov chain. Applicationes Mathematicae, Tome 22 (1993) no. 2, pp. 165-180. doi : 10.4064/am-22-2-165-180. http://geodesic.mathdoc.fr/articles/10.4064/am-22-2-165-180/

Cité par Sources :