Dynamic programming for variable discounted Markov decision problems

Autores
Della Vecchia, Eugenio; Di Marco, Silvia; Vidal, Fernando
Año de publicación
2014
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
We study the existence of optimal strategies and value function of non stationary Markov decision processes under variable discounted criteria, when the action space is assumed to be Borel and the action space to be compact. With this new way of defining the value of a policy, we show existence of Markov deterministic optimal policies in the finite-horizon case, and a recursive method to obtain such ones. For the infinite horizon problem we characterize the value function and show existence of stationary deterministic policies. The approach presented is based on the use of adequate dynamic programming operators.
Sociedad Argentina de Informática e Investigación Operativa (SADIO)
Materia
Ciencias Informáticas
Markov decision processes
variable discount factor
Programming Environments
Decision problems
dynamic programming
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by/3.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/41704

id SEDICI_7feb224f81c8bf5ed84394fb74a99a15
oai_identifier_str oai:sedici.unlp.edu.ar:10915/41704
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Dynamic programming for variable discounted Markov decision problemsDella Vecchia, EugenioDi Marco, SilviaVidal, FernandoCiencias InformáticasMarkov decision processesvariable discount factorProgramming EnvironmentsDecision problemsdynamic programmingWe study the existence of optimal strategies and value function of non stationary Markov decision processes under variable discounted criteria, when the action space is assumed to be Borel and the action space to be compact. With this new way of defining the value of a policy, we show existence of Markov deterministic optimal policies in the finite-horizon case, and a recursive method to obtain such ones. For the infinite horizon problem we characterize the value function and show existence of stationary deterministic policies. The approach presented is based on the use of adequate dynamic programming operators.Sociedad Argentina de Informática e Investigación Operativa (SADIO)2014-09info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf50-62http://sedici.unlp.edu.ar/handle/10915/41704enginfo:eu-repo/semantics/altIdentifier/url/http://43jaiio.sadio.org.ar/proceedings/SIO/17.pdfinfo:eu-repo/semantics/altIdentifier/issn/1850-2865info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/3.0/Creative Commons Attribution 3.0 Unported (CC BY 3.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-03T10:33:54Zoai:sedici.unlp.edu.ar:10915/41704Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-03 10:33:55.101SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Dynamic programming for variable discounted Markov decision problems
title Dynamic programming for variable discounted Markov decision problems
spellingShingle Dynamic programming for variable discounted Markov decision problems
Della Vecchia, Eugenio
Ciencias Informáticas
Markov decision processes
variable discount factor
Programming Environments
Decision problems
dynamic programming
title_short Dynamic programming for variable discounted Markov decision problems
title_full Dynamic programming for variable discounted Markov decision problems
title_fullStr Dynamic programming for variable discounted Markov decision problems
title_full_unstemmed Dynamic programming for variable discounted Markov decision problems
title_sort Dynamic programming for variable discounted Markov decision problems
dc.creator.none.fl_str_mv Della Vecchia, Eugenio
Di Marco, Silvia
Vidal, Fernando
author Della Vecchia, Eugenio
author_facet Della Vecchia, Eugenio
Di Marco, Silvia
Vidal, Fernando
author_role author
author2 Di Marco, Silvia
Vidal, Fernando
author2_role author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Markov decision processes
variable discount factor
Programming Environments
Decision problems
dynamic programming
topic Ciencias Informáticas
Markov decision processes
variable discount factor
Programming Environments
Decision problems
dynamic programming
dc.description.none.fl_txt_mv We study the existence of optimal strategies and value function of non stationary Markov decision processes under variable discounted criteria, when the action space is assumed to be Borel and the action space to be compact. With this new way of defining the value of a policy, we show existence of Markov deterministic optimal policies in the finite-horizon case, and a recursive method to obtain such ones. For the infinite horizon problem we characterize the value function and show existence of stationary deterministic policies. The approach presented is based on the use of adequate dynamic programming operators.
Sociedad Argentina de Informática e Investigación Operativa (SADIO)
description We study the existence of optimal strategies and value function of non stationary Markov decision processes under variable discounted criteria, when the action space is assumed to be Borel and the action space to be compact. With this new way of defining the value of a policy, we show existence of Markov deterministic optimal policies in the finite-horizon case, and a recursive method to obtain such ones. For the infinite horizon problem we characterize the value function and show existence of stationary deterministic policies. The approach presented is based on the use of adequate dynamic programming operators.
publishDate 2014
dc.date.none.fl_str_mv 2014-09
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/41704
url http://sedici.unlp.edu.ar/handle/10915/41704
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://43jaiio.sadio.org.ar/proceedings/SIO/17.pdf
info:eu-repo/semantics/altIdentifier/issn/1850-2865
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by/3.0/
Creative Commons Attribution 3.0 Unported (CC BY 3.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/3.0/
Creative Commons Attribution 3.0 Unported (CC BY 3.0)
dc.format.none.fl_str_mv application/pdf
50-62
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1842260187740635136
score 13.13397