Markov Decision Processes under Ambiguity
Optimization and Control
2021-07-21 v1 Statistics Theory
Statistics Theory
Abstract
We consider statistical Markov Decision Processes where the decision maker is risk averse against model ambiguity. The latter is given by an unknown parameter which influences the transition law and the cost functions. Risk aversion is either measured by the entropic risk measure or by the Average Value at Risk. We show how to solve these kind of problems using a general minimax theorem. Under some continuity and compactness assumptions we prove the existence of an optimal (deterministic) policy and discuss its computation. We illustrate our results using an example from statistical decision theory.
Cite
@article{arxiv.1907.02347,
title = {Markov Decision Processes under Ambiguity},
author = {Nicole Bäuerle and Ulrich Rieder},
journal= {arXiv preprint arXiv:1907.02347},
year = {2021}
}