Geodesic
Recursive self-tuning control of finite Markov chains
Applicationes Mathematicae, Tome 24 (1997) no. 2, pp. 169-188.

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

A recursive self-tuning control scheme for finite Markov chains is proposed wherein the unknown parameter is estimated by a stochastic approximation scheme for maximizing the log-likelihood function and the control is obtained via a relative value iteration algorithm. The analysis uses the asymptotic o.d.e.s associated with these.
DOI : 10.4064/am-24-2-169-188
Keywords: controlled Markov chains, stochastic approximation, relative value iteration, self-tuning control, adaptive control

Vivek Borkar 1

1 
@article{10_4064_am_24_2_169_188,
     author = {Vivek Borkar},
     title = {Recursive self-tuning control of finite {Markov} chains},
     journal = {Applicationes Mathematicae},
     pages = {169--188},
     publisher = {mathdoc},
     volume = {24},
     number = {2},
     year = {1997},
     doi = {10.4064/am-24-2-169-188},
     zbl = {0951.93537},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.4064/am-24-2-169-188/}
}
TY  - JOUR
AU  - Vivek Borkar
TI  - Recursive self-tuning control of finite Markov chains
JO  - Applicationes Mathematicae
PY  - 1997
SP  - 169
EP  - 188
VL  - 24
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.4064/am-24-2-169-188/
DO  - 10.4064/am-24-2-169-188
LA  - en
ID  - 10_4064_am_24_2_169_188
ER  - 
%0 Journal Article
%A Vivek Borkar
%T Recursive self-tuning control of finite Markov chains
%J Applicationes Mathematicae
%D 1997
%P 169-188
%V 24
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.4064/am-24-2-169-188/
%R 10.4064/am-24-2-169-188
%G en
%F 10_4064_am_24_2_169_188
Vivek Borkar. Recursive self-tuning control of finite Markov chains. Applicationes Mathematicae, Tome 24 (1997) no. 2, pp. 169-188. doi : 10.4064/am-24-2-169-188. http://geodesic.mathdoc.fr/articles/10.4064/am-24-2-169-188/

Cité par Sources :