The generation of successive approximation methods for Markov decision processes by using stopping times

J.A.E.E. van Nunen; J. Wessels

The generation of successive approximation methods for Markov decision processes by using stopping times

J.A.E.E. van Nunen, J. Wessels

Stochastics

Research output: Book/Report › Report › Academic

40 Downloads (Pure)

Abstract

In this paper we will consider several variants of the standard successive approximation technique for Markov decision processes. It will be shown how these variants can be generated by stopping times. Furthermore it will be demonstrated how this class of techniques can be extended to a class of value oriented techniques. This latter class contains as extreme elements several variants of Howard's policy iteration method. For all methods presented extrapolations are given in the form of MacQueen's upper and lower bounds.

Original language	English
Place of Publication	Eindhoven
Publisher	Technische Hogeschool Eindhoven
Number of pages	13
Publication status	Published - 1976

Publication series

Name	Memorandum COSOR
Volume	7622
ISSN (Print)	0926-4493

Fingerprint

Cite this

van Nunen, J. A. E. E., & Wessels, J. (1976). The generation of successive approximation methods for Markov decision processes by using stopping times. (Memorandum COSOR; Vol. 7622). Eindhoven: Technische Hogeschool Eindhoven.

@book{c42d3c5b018b47ccbc11ba0290b38528,

title = "The generation of successive approximation methods for Markov decision processes by using stopping times",

abstract = "In this paper we will consider several variants of the standard successive approximation technique for Markov decision processes. It will be shown how these variants can be generated by stopping times. Furthermore it will be demonstrated how this class of techniques can be extended to a class of value oriented techniques. This latter class contains as extreme elements several variants of Howard's policy iteration method. For all methods presented extrapolations are given in the form of MacQueen's upper and lower bounds.",

author = "{van Nunen}, J.A.E.E. and J. Wessels",

year = "1976",

language = "English",

series = "Memorandum COSOR",

publisher = "Technische Hogeschool Eindhoven",

}

TY - BOOK

T1 - The generation of successive approximation methods for Markov decision processes by using stopping times

AU - van Nunen, J.A.E.E.

AU - Wessels, J.

PY - 1976

Y1 - 1976

N2 - In this paper we will consider several variants of the standard successive approximation technique for Markov decision processes. It will be shown how these variants can be generated by stopping times. Furthermore it will be demonstrated how this class of techniques can be extended to a class of value oriented techniques. This latter class contains as extreme elements several variants of Howard's policy iteration method. For all methods presented extrapolations are given in the form of MacQueen's upper and lower bounds.

AB - In this paper we will consider several variants of the standard successive approximation technique for Markov decision processes. It will be shown how these variants can be generated by stopping times. Furthermore it will be demonstrated how this class of techniques can be extended to a class of value oriented techniques. This latter class contains as extreme elements several variants of Howard's policy iteration method. For all methods presented extrapolations are given in the form of MacQueen's upper and lower bounds.

M3 - Report

T3 - Memorandum COSOR

BT - The generation of successive approximation methods for Markov decision processes by using stopping times

PB - Technische Hogeschool Eindhoven

CY - Eindhoven

ER -

Access to Document

339649Final published version, 420 KB