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...

Celý popis

Podrobná bibliografia

Vydané v:	Operations research Ročník 70; číslo 3; s. 1428
Hlavní autori:	Li, Xiaocheng, Zhong, Huaiyang, Brandeau, Margaret L
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States 01.05.2022
Predmet:	Markov Decision Process Dynamic Programming Risk Measure Quantile Medical Decision Making
ISSN:	0030-364X
On-line prístup:	Zistit podrobnosti o prístupe
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!