Geodesic
Optimal stationary policies inrisk-sensitive dynamic programs with finite state spaceand nonnegative rewards
Applicationes Mathematicae, Tome 27 (2000) no. 2, pp. 167-185

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

This work concerns controlled Markov chains with finite state space and nonnegative rewards; it is assumed that the controller has a constant risk-sensitivity, and that the performance ofa control policy is measured by a risk-sensitive expected total-reward criterion. The existence of optimal stationary policies isstudied within this context, and the main resultestablishes the optimalityof a stationary policy achieving the supremum in the correspondingoptimality equation, whenever the associated Markov chain hasa unique positive recurrent class. Two explicit examples are providedto show that, if such an additional condition fails, an optimal stationarypolicy cannot be generally guaranteed. The results of this note, which consider both the risk-seeking and the risk-averse cases, answer an extended version of a question recently posed in Puterman (1994).
DOI : 10.4064/am-27-2-167-185
Keywords: unichain property, Markov decision processes, risk-sensitive optimality equation, risk-sensitive expected total- reward criterion

Rolando Cavazos-Cadena 1 ; Raúl Montes-de-Oca 1

1 
@article{10_4064_am_27_2_167_185,
     author = {Rolando Cavazos-Cadena and Ra\'ul Montes-de-Oca},
     title = {Optimal stationary policies inrisk-sensitive dynamic programs with finite state spaceand nonnegative rewards},
     journal = {Applicationes Mathematicae},
     pages = {167--185},
     publisher = {mathdoc},
     volume = {27},
     number = {2},
     year = {2000},
     doi = {10.4064/am-27-2-167-185},
     zbl = {1006.93070},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.4064/am-27-2-167-185/}
}
TY  - JOUR
AU  - Rolando Cavazos-Cadena
AU  - Raúl Montes-de-Oca
TI  - Optimal stationary policies inrisk-sensitive dynamic programs with finite state spaceand nonnegative rewards
JO  - Applicationes Mathematicae
PY  - 2000
SP  - 167
EP  - 185
VL  - 27
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.4064/am-27-2-167-185/
DO  - 10.4064/am-27-2-167-185
LA  - en
ID  - 10_4064_am_27_2_167_185
ER  - 
%0 Journal Article
%A Rolando Cavazos-Cadena
%A Raúl Montes-de-Oca
%T Optimal stationary policies inrisk-sensitive dynamic programs with finite state spaceand nonnegative rewards
%J Applicationes Mathematicae
%D 2000
%P 167-185
%V 27
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.4064/am-27-2-167-185/
%R 10.4064/am-27-2-167-185
%G en
%F 10_4064_am_27_2_167_185
Rolando Cavazos-Cadena; Raúl Montes-de-Oca. Optimal stationary policies inrisk-sensitive dynamic programs with finite state spaceand nonnegative rewards. Applicationes Mathematicae, Tome 27 (2000) no. 2, pp. 167-185. doi: 10.4064/am-27-2-167-185

Cité par Sources :