Back to Search
Start Over
Mean-variance optimality for semi-Markov decision processes under first passage criteria
- Source :
- Kybernetika. :59-81
- Publication Year :
- 2017
- Publisher :
- Institute of Information Theory and Automation, 2017.
-
Abstract
- 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.
- Subjects :
- Class (set theory)
Discounting
Mathematical optimization
010102 general mathematics
Reward-based selection
Partially observable Markov decision process
Variance (accounting)
01 natural sciences
Theoretical Computer Science
010101 applied mathematics
Artificial Intelligence
Control and Systems Engineering
Markov decision process
0101 mathematics
Electrical and Electronic Engineering
First-hitting-time model
Set (psychology)
Software
Information Systems
Mathematics
Subjects
Details
- ISSN :
- 1805949X and 00235954
- Database :
- OpenAIRE
- Journal :
- Kybernetika
- Accession number :
- edsair.doi...........80447d18c898009cbe56108207f492e3