Markov decision processes with unbounded rewards

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

Markov decision processes with unbounded rewards

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

Onderzoeksoutput: Boek/rapport › Rapport › Academic

28 Downloads (Pure)

Samenvatting

Markov decision processes which allow for an unbounded reward structure are considered. Conditions are given which allow successive approximations with a convergence in some strong sense. This "strong" convergence enables the construction of upper and lower bounds. The conditions are weaker than those proposed by Lippman [15], Harrison [5] and Wessels [28] and are in fact a slight generalization of the conditions proposed by Van Nunen [21]. A successive approximation algorithm will be indicated. The conditions will be analysed and compared with those in literature.

Originele taal-2	Engels
Plaats van productie	Eindhoven
Uitgeverij	Technische Hogeschool Eindhoven
Aantal pagina's	24
Status	Gepubliceerd - 1976

Publicatie series

Naam	Memorandum COSOR
Volume	7623
ISSN van geprinte versie	0926-4493

Toegang tot document

339650Definitieve gepubliceerde versie, 651 KB

Vingerafdruk Duik in de onderzoeksthema's van 'Markov decision processes with unbounded rewards'. Samen vormen ze een unieke vingerafdruk.

Citeer dit

@book{a67ad1156c61403eb5c95f99c0a164d2,

title = "Markov decision processes with unbounded rewards",

abstract = "Markov decision processes which allow for an unbounded reward structure are considered. Conditions are given which allow successive approximations with a convergence in some strong sense. This {"}strong{"} convergence enables the construction of upper and lower bounds. The conditions are weaker than those proposed by Lippman [15], Harrison [5] and Wessels [28] and are in fact a slight generalization of the conditions proposed by Van Nunen [21]. A successive approximation algorithm will be indicated. The conditions will be analysed and compared with those in literature.",

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

year = "1976",

language = "English",

series = "Memorandum COSOR",

publisher = "Technische Hogeschool Eindhoven",

}

TY - BOOK

T1 - Markov decision processes with unbounded rewards

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

AU - Wessels, J.

PY - 1976

Y1 - 1976

N2 - Markov decision processes which allow for an unbounded reward structure are considered. Conditions are given which allow successive approximations with a convergence in some strong sense. This "strong" convergence enables the construction of upper and lower bounds. The conditions are weaker than those proposed by Lippman [15], Harrison [5] and Wessels [28] and are in fact a slight generalization of the conditions proposed by Van Nunen [21]. A successive approximation algorithm will be indicated. The conditions will be analysed and compared with those in literature.

AB - Markov decision processes which allow for an unbounded reward structure are considered. Conditions are given which allow successive approximations with a convergence in some strong sense. This "strong" convergence enables the construction of upper and lower bounds. The conditions are weaker than those proposed by Lippman [15], Harrison [5] and Wessels [28] and are in fact a slight generalization of the conditions proposed by Van Nunen [21]. A successive approximation algorithm will be indicated. The conditions will be analysed and compared with those in literature.

M3 - Report

T3 - Memorandum COSOR

BT - Markov decision processes with unbounded rewards

PB - Technische Hogeschool Eindhoven

CY - Eindhoven

ER -