Risk-sensitive Markov decision problems under model uncertainty: finite time horizon case
Optimization and Control
2021-04-15 v1
Abstract
In this paper we study a class of risk-sensitive Markovian control problems in discrete time subject to model uncertainty. We consider a risk-sensitive discounted cost criterion with finite time horizon. The used methodology is the one of adaptive robust control combined with machine learning.
Cite
@article{arxiv.2104.06915,
title = {Risk-sensitive Markov decision problems under model uncertainty: finite time horizon case},
author = {Tomasz R. Bielecki and Tao Chen and Igor Cialenco},
journal= {arXiv preprint arXiv:2104.06915},
year = {2021}
}
Comments
arXiv admin note: text overlap with arXiv:2002.02604