Geodesic
Mean-variance optimality for semi-Markov decision processes under first passage criteria
Kybernetika, Tome 53 (2017) no. 1, pp. 59-81

Voir la notice de l'article provenant de la source Czech Digital Mathematics Library

This paper deals with a first passage mean-variance problem for semi-Markov decision processes in Borel spaces. The goal is to minimize the variance of a total discounted reward up to the system's first entry to some target set, where the optimization is over a class of policies with a prescribed expected first passage reward. The reward rates are assumed to be possibly unbounded, while the discount factor may vary with states of the system and controls. We first develop some suitable conditions for the existence of first passage mean-variance optimal policies and provide a policy improvement algorithm for computing an optimal policy. Then, two examples are included to illustrate our results. At last, we show how the results here are reduced to the cases of discrete-time Markov decision processes and continuous-time Markov decision processes.
DOI : 10.14736/kyb-2017-1-0059
Classification : 60J27, 90C40
Keywords: semi-Markov decision processes; first passage time; unbounded reward rate; minimal variance; mean-variance optimal policy 
@article{10_14736_kyb_2017_1_0059,
     author = {Huang, Xiangxiang and Huang, Yonghui},
     title = {Mean-variance optimality for {semi-Markov} decision processes under first passage criteria},
     journal = {Kybernetika},
     pages = {59--81},
     publisher = {mathdoc},
     volume = {53},
     number = {1},
     year = {2017},
     doi = {10.14736/kyb-2017-1-0059},
     mrnumber = {3638556},
     zbl = {06738594},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2017-1-0059/}
}
TY  - JOUR
AU  - Huang, Xiangxiang
AU  - Huang, Yonghui
TI  - Mean-variance optimality for semi-Markov decision processes under first passage criteria
JO  - Kybernetika
PY  - 2017
SP  - 59
EP  - 81
VL  - 53
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2017-1-0059/
DO  - 10.14736/kyb-2017-1-0059
LA  - en
ID  - 10_14736_kyb_2017_1_0059
ER  - 
%0 Journal Article
%A Huang, Xiangxiang
%A Huang, Yonghui
%T Mean-variance optimality for semi-Markov decision processes under first passage criteria
%J Kybernetika
%D 2017
%P 59-81
%V 53
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2017-1-0059/
%R 10.14736/kyb-2017-1-0059
%G en
%F 10_14736_kyb_2017_1_0059
Huang, Xiangxiang; Huang, Yonghui. Mean-variance optimality for semi-Markov decision processes under first passage criteria. Kybernetika, Tome 53 (2017) no. 1, pp. 59-81. doi: 10.14736/kyb-2017-1-0059

Cité par Sources :