Geodesic
First passage risk probability optimality for continuous time Markov decision processes
Kybernetika, Tome 55 (2019) no. 1, pp. 114-133 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

In this paper, we study continuous time Markov decision processes (CTMDPs) with a denumerable state space, a Borel action space, unbounded transition rates and nonnegative reward function. The optimality criterion to be considered is the first passage risk probability criterion. To ensure the non-explosion of the state processes, we first introduce a so-called drift condition, which is weaker than the well known regular condition for semi-Markov decision processes (SMDPs). Furthermore, under some suitable conditions, by value iteration recursive approximation technique, we establish the optimality equation, obtain the uniqueness of the value function and the existence of optimal policies. Finally, two examples are used to illustrate our results.
In this paper, we study continuous time Markov decision processes (CTMDPs) with a denumerable state space, a Borel action space, unbounded transition rates and nonnegative reward function. The optimality criterion to be considered is the first passage risk probability criterion. To ensure the non-explosion of the state processes, we first introduce a so-called drift condition, which is weaker than the well known regular condition for semi-Markov decision processes (SMDPs). Furthermore, under some suitable conditions, by value iteration recursive approximation technique, we establish the optimality equation, obtain the uniqueness of the value function and the existence of optimal policies. Finally, two examples are used to illustrate our results.
DOI : 10.14736/kyb-2019-1-0114
Classification : 60E20, 90C40
Keywords: continuous time Markov decision processes; first passage time; risk probability criterion; optimal policy 
@article{10_14736_kyb_2019_1_0114,
     author = {Huo, Haifeng and Wen, Xian},
     title = {First passage risk probability optimality for continuous time {Markov} decision processes},
     journal = {Kybernetika},
     pages = {114--133},
     year = {2019},
     volume = {55},
     number = {1},
     doi = {10.14736/kyb-2019-1-0114},
     mrnumber = {3935417},
     zbl = {07088881},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2019-1-0114/}
}
TY  - JOUR
AU  - Huo, Haifeng
AU  - Wen, Xian
TI  - First passage risk probability optimality for continuous time Markov decision processes
JO  - Kybernetika
PY  - 2019
SP  - 114
EP  - 133
VL  - 55
IS  - 1
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2019-1-0114/
DO  - 10.14736/kyb-2019-1-0114
LA  - en
ID  - 10_14736_kyb_2019_1_0114
ER  - 
%0 Journal Article
%A Huo, Haifeng
%A Wen, Xian
%T First passage risk probability optimality for continuous time Markov decision processes
%J Kybernetika
%D 2019
%P 114-133
%V 55
%N 1
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2019-1-0114/
%R 10.14736/kyb-2019-1-0114
%G en
%F 10_14736_kyb_2019_1_0114
Huo, Haifeng; Wen, Xian. First passage risk probability optimality for continuous time Markov decision processes. Kybernetika, Tome 55 (2019) no. 1, pp. 114-133. doi: 10.14736/kyb-2019-1-0114

Cité par Sources :