Rolling horizon procedures in Semi-Markov Games: The Discounted Case

We study the properties of the rolling horizon and the approximate rolling horizon procedures for the case of two-person zero-sum discounted semi-Markov games with infinite horizon, when the state space is a borelian set and the action spaces are considered compact. Under suitable conditions, we pro...

Descripción completa

Detalles Bibliográficos
Autores: Della Vecchia, Eugenio Martín, Di Marco, Silvia Cristina, Jean Marie, Alain
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2014
País:Argentina
Institución:Consejo Nacional de Investigaciones Científicas y Técnicas
Repositorio:CONICET Digital (CONICET)
Idioma:inglés
OAI Identifier:oai:ri.conicet.gov.ar:11336/29974
Acceso en línea:http://hdl.handle.net/11336/29974
Access Level:acceso abierto
Palabra clave:Semi-Markov games
Rolling horizon procedures
https://purl.org/becyt/ford/1.1
https://purl.org/becyt/ford/1
id AR_503cfda6422877efba99f3fd93bb0bcd
oai_identifier_str oai:ri.conicet.gov.ar:11336/29974
network_acronym_str AR
network_name_str Argentina
repository_id_str
spelling Rolling horizon procedures in Semi-Markov Games: The Discounted CaseDella Vecchia, Eugenio MartínDi Marco, Silvia CristinaJean Marie, AlainSemi-Markov gamesRolling horizon procedureshttps://purl.org/becyt/ford/1.1https://purl.org/becyt/ford/1We study the properties of the rolling horizon and the approximate rolling horizon procedures for the case of two-person zero-sum discounted semi-Markov games with infinite horizon, when the state space is a borelian set and the action spaces are considered compact. Under suitable conditions, we prove that the equilibrium is the unique solution of a dynamic programming equation, and we prove bounds which imply the convergence of the procedures when the horizon length tends to infinity. The approach is based on the formalism for Semi-Markov games developed by Luque-Vásquez in [11], together with extensions of the results of Hernández-Lerma and Lasserre [4] for Markov Decision Processes and Chang and Marcus [2] for Markov Games, both in discrete time. In this way we generalize the results on the rolling horizon and approximate rolling horizon procedures previously obtained for discrete-time problemsFil: Della Vecchia, Eugenio Martín. Universidad Nacional de Rosario; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Di Marco, Silvia Cristina. Universidad Nacional de Rosario; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Jean Marie, Alain. Université Montpellier II; FranciaInstitut National de Recherche en Informatique et en Automatique2014-05info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/29974Della Vecchia, Eugenio Martín; Di Marco, Silvia Cristina; Jean Marie, Alain; Rolling horizon procedures in Semi-Markov Games: The Discounted Case; Institut National de Recherche en Informatique et en Automatique; Rapports de Recherche, Institut National de Recherche en Informatique et en Automatique; 8019; 5-2014; 1-230249-6399CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://hal.inria.fr/hal-00720351info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2024-05-08T14:15:45Zoai:ri.conicet.gov.ar:11336/29974instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982024-05-08 14:15:45.929CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Rolling horizon procedures in Semi-Markov Games: The Discounted Case
title Rolling horizon procedures in Semi-Markov Games: The Discounted Case
spellingShingle Rolling horizon procedures in Semi-Markov Games: The Discounted Case
Della Vecchia, Eugenio Martín
Semi-Markov games
Rolling horizon procedures
https://purl.org/becyt/ford/1.1
https://purl.org/becyt/ford/1
title_short Rolling horizon procedures in Semi-Markov Games: The Discounted Case
title_full Rolling horizon procedures in Semi-Markov Games: The Discounted Case
title_fullStr Rolling horizon procedures in Semi-Markov Games: The Discounted Case
title_full_unstemmed Rolling horizon procedures in Semi-Markov Games: The Discounted Case
title_sort Rolling horizon procedures in Semi-Markov Games: The Discounted Case
dc.creator.none.fl_str_mv Della Vecchia, Eugenio Martín
Di Marco, Silvia Cristina
Jean Marie, Alain
author Della Vecchia, Eugenio Martín
author_facet Della Vecchia, Eugenio Martín
Di Marco, Silvia Cristina
Jean Marie, Alain
author_role author
author2 Di Marco, Silvia Cristina
Jean Marie, Alain
author2_role author
author
dc.subject.none.fl_str_mv Semi-Markov games
Rolling horizon procedures
https://purl.org/becyt/ford/1.1
https://purl.org/becyt/ford/1
topic Semi-Markov games
Rolling horizon procedures
https://purl.org/becyt/ford/1.1
https://purl.org/becyt/ford/1
description We study the properties of the rolling horizon and the approximate rolling horizon procedures for the case of two-person zero-sum discounted semi-Markov games with infinite horizon, when the state space is a borelian set and the action spaces are considered compact. Under suitable conditions, we prove that the equilibrium is the unique solution of a dynamic programming equation, and we prove bounds which imply the convergence of the procedures when the horizon length tends to infinity. The approach is based on the formalism for Semi-Markov games developed by Luque-Vásquez in [11], together with extensions of the results of Hernández-Lerma and Lasserre [4] for Markov Decision Processes and Chang and Marcus [2] for Markov Games, both in discrete time. In this way we generalize the results on the rolling horizon and approximate rolling horizon procedures previously obtained for discrete-time problems
publishDate 2014
dc.date.none.fl_str_mv 2014-05
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/29974
Della Vecchia, Eugenio Martín; Di Marco, Silvia Cristina; Jean Marie, Alain; Rolling horizon procedures in Semi-Markov Games: The Discounted Case; Institut National de Recherche en Informatique et en Automatique; Rapports de Recherche, Institut National de Recherche en Informatique et en Automatique; 8019; 5-2014; 1-23
0249-6399
CONICET Digital
CONICET
url http://hdl.handle.net/11336/29974
identifier_str_mv Della Vecchia, Eugenio Martín; Di Marco, Silvia Cristina; Jean Marie, Alain; Rolling horizon procedures in Semi-Markov Games: The Discounted Case; Institut National de Recherche en Informatique et en Automatique; Rapports de Recherche, Institut National de Recherche en Informatique et en Automatique; 8019; 5-2014; 1-23
0249-6399
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://hal.inria.fr/hal-00720351
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institut National de Recherche en Informatique et en Automatique
publisher.none.fl_str_mv Institut National de Recherche en Informatique et en Automatique
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1799196130812100608
score 15,811543

Similares en LA Referencia