Quantile Markov Decision Processes

The goal of a traditional Markov decision process (MDP) is to maximize expected cumulative reward over a defined horizon (possibly infinite). In many applications, however, a decision maker may be interested in optimizing a specific quantile of the cumulative reward instead of its expectation. In th...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Operations research Jg. 70; H. 3; S. 1428
Hauptverfasser:	Li, Xiaocheng, Zhong, Huaiyang, Brandeau, Margaret L
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States 01.05.2022
Schlagworte:	Markov Decision Process Dynamic Programming Risk Measure Quantile Medical Decision Making
ISSN:	0030-364X
Online-Zugang:	Weitere Angaben
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!