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

Cite this

Wal, van der, J. (1981). Nearly optimal stationary strategies for the total reward Markov decision process. In G. Fandel, D. Fischer, H. C. Pfohl, K. P. Schuster, & J. Schwarze (Eds.), DGOR: Papers of the Annual Meeting/Vorträge der Jahrestagung (pp. 501-501). (Operations Research Proceedings (ORP); Vol. 1980). Berlin: Springer. https://doi.org/10.1007/978-3-642-68118-9_94
Wal, van der, J. / Nearly optimal stationary strategies for the total reward Markov decision process. DGOR: Papers of the Annual Meeting/Vorträge der Jahrestagung. editor / G. Fandel ; D. Fischer ; H.C. Pfohl ; K.P. Schuster ; J. Schwarze. Berlin : Springer, 1981. pp. 501-501 (Operations Research Proceedings (ORP)).
@inproceedings{21a0b0f62da840048bdd9b92183128e1,
title = "Nearly optimal stationary strategies for the total reward Markov decision process",
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.",
author = "{Wal, van der}, J.",
year = "1981",
doi = "10.1007/978-3-642-68118-9_94",
language = "English",
isbn = "3-540-10801-7",
series = "Operations Research Proceedings (ORP)",
publisher = "Springer",
pages = "501--501",
editor = "G. Fandel and D. Fischer and H.C. Pfohl and K.P. Schuster and J. Schwarze",
booktitle = "DGOR",
address = "Germany",

}

Wal, van der, J 1981, Nearly optimal stationary strategies for the total reward Markov decision process. in G Fandel, D Fischer, HC Pfohl, KP Schuster & J Schwarze (eds), DGOR: Papers of the Annual Meeting/Vorträge der Jahrestagung. Operations Research Proceedings (ORP), vol. 1980, Springer, Berlin, pp. 501-501, 9th Annual Meeting of DGOR, Essen, Germany, 24/09/80. https://doi.org/10.1007/978-3-642-68118-9_94

Nearly optimal stationary strategies for the total reward Markov decision process. / Wal, van der, J.

DGOR: Papers of the Annual Meeting/Vorträge der Jahrestagung. ed. / G. Fandel; D. Fischer; H.C. Pfohl; K.P. Schuster; J. Schwarze. Berlin : Springer, 1981. p. 501-501 (Operations Research Proceedings (ORP); Vol. 1980).

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

TY - GEN

T1 - Nearly optimal stationary strategies for the total reward Markov decision process

AU - Wal, van der, J.

PY - 1981

Y1 - 1981

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-68118-9_94

DO - 10.1007/978-3-642-68118-9_94

M3 - Conference contribution

SN - 3-540-10801-7

SN - 978-3-540-10801-6

T3 - Operations Research Proceedings (ORP)

SP - 501

EP - 501

BT - DGOR

A2 - Fandel, G.

A2 - Fischer, D.

A2 - Pfohl, H.C.

A2 - Schuster, K.P.

A2 - Schwarze, J.

PB - Springer

CY - Berlin

ER -

Wal, van der J. Nearly optimal stationary strategies for the total reward Markov decision process. In Fandel G, Fischer D, Pfohl HC, Schuster KP, Schwarze J, editors, DGOR: Papers of the Annual Meeting/Vorträge der Jahrestagung. Berlin: Springer. 1981. p. 501-501. (Operations Research Proceedings (ORP)). https://doi.org/10.1007/978-3-642-68118-9_94