Nearly optimal stationary strategies for the total reward Markov decision process

J. Wal, van der

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Consider a Markov decision process with countable state space S and finite action space A. If in state i∈S action a∈A is taken then we get an immediate reward r(i,a) and the system makes a transition to state j with probability p(i,a,j). We assume Σj∈Sp(i,a,j)=1.
Original languageEnglish
Title of host publicationDGOR
Subtitle of host publicationPapers of the Annual Meeting/Vorträge der Jahrestagung
EditorsG. Fandel, D. Fischer, H.C. Pfohl, K.P. Schuster, J. Schwarze
Place of PublicationBerlin
PublisherSpringer
Chapter94
Pages501-501
Number of pages1
ISBN (Electronic)978-3-642-68118-9
ISBN (Print)3-540-10801-7, 978-3-540-10801-6
DOIs
Publication statusPublished - 1981
Event9th Annual Meeting of DGOR - Essen, Germany
Duration: 24 Sep 198026 Sep 1980

Publication series

NameOperations Research Proceedings (ORP)
Volume1980

Conference

Conference9th Annual Meeting of DGOR
CountryGermany
CityEssen
Period24/09/8026/09/80

Fingerprint Dive into the research topics of 'Nearly optimal stationary strategies for the total reward Markov decision process'. Together they form a unique fingerprint.

Cite this