Markov decision processes under ambiguity
Banach Center Publications · 2020 · 122 · 25-39
DOI: 10.4064/bc122-2 ↗At a glance
Journal article in Banach Center Publications, 2020. Written by Nicole Bäuerle and 1 co-authors. Cited 6 times so far (Crossref).
Abstract (original language)
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
APA
Bäuerle, N., & Rieder, U. (2020). Markov decision processes under ambiguity. Banach Center Publications, 122, 25-39. https://doi.org/10.4064/bc122-2
Vancouver
Bäuerle N, Rieder U. Markov decision processes under ambiguity. Banach Center Publications. 2020;122:25-39. doi:10.4064/bc122-2
BibTeX
@article{Buerle2020,
author = {Bäuerle, Nicole and Rieder, Ulrich},
title = {Markov decision processes under ambiguity},
journal = {Banach Center Publications},
year = {2020},
volume = {122},
pages = {25--39},
doi = {10.4064/bc122-2}
}
EUVIMED