Successive approximation methods for Markov games

J. Wal, van der; J. Wessels

Successive approximation methods for Markov games

J. Wal, van der
, J. Wessels

Stochastic Operations Research

Onderzoeksoutput: Boek/rapport › Rapport › Academic

116 Downloads (Pure)

Samenvatting

In this paper an overview will be presented of the applicability of successive approximation methods for Markov games. The larger part of the paper will be devoted to two-person zero-sum Markov games with the total expected reward criterion. The analysis will include policy-iteration algorithms. Finally there are sections on the average-reward case and on the nonzero-sum case.

Originele taal-2	Engels
Plaats van productie	Eindhoven
Uitgeverij	Technische Hogeschool Eindhoven
Aantal pagina's	19
Status	Gepubliceerd - 1976

Publicatie series

Naam	Memorandum COSOR
Volume	7618
ISSN van geprinte versie	0926-4493

Toegang tot document

339647Definitieve gepubliceerde versie, 590 KB

Citeer dit

@book{43b0634012cf4466b044bd2d2d88d6e4,

title = "Successive approximation methods for Markov games",

abstract = "In this paper an overview will be presented of the applicability of successive approximation methods for Markov games. The larger part of the paper will be devoted to two-person zero-sum Markov games with the total expected reward criterion. The analysis will include policy-iteration algorithms. Finally there are sections on the average-reward case and on the nonzero-sum case.",

author = "\{Wal, van der\}, J. and J. Wessels",

year = "1976",

language = "English",

series = "Memorandum COSOR",

publisher = "Technische Hogeschool Eindhoven",

}

TY - BOOK

T1 - Successive approximation methods for Markov games

AU - Wal, van der, J.

AU - Wessels, J.

PY - 1976

Y1 - 1976

N2 - In this paper an overview will be presented of the applicability of successive approximation methods for Markov games. The larger part of the paper will be devoted to two-person zero-sum Markov games with the total expected reward criterion. The analysis will include policy-iteration algorithms. Finally there are sections on the average-reward case and on the nonzero-sum case.

AB - In this paper an overview will be presented of the applicability of successive approximation methods for Markov games. The larger part of the paper will be devoted to two-person zero-sum Markov games with the total expected reward criterion. The analysis will include policy-iteration algorithms. Finally there are sections on the average-reward case and on the nonzero-sum case.

M3 - Report

T3 - Memorandum COSOR

BT - Successive approximation methods for Markov games

PB - Technische Hogeschool Eindhoven

CY - Eindhoven

ER -

Successive approximation methods for Markov games

Samenvatting

Publicatie series

Toegang tot document

Vingerafdruk

Citeer dit