Generalization over Environments in Reinforcement Learning

Autores
Matt, Andreas; Regensburger, Georg
Año de publicación
2002
Idioma
español castellano
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
In this paper we discuss the problem of reinforcement learning in one environment and applying the policy obtained to other environments. We first state a method to evaluate the utility of a policy. We then propose a general model to apply one policy to different environments and compare them. To illustrate the theory we present examples for an obstacle avoidance behavior in various block world environments.
Sociedad Argentina de Informática e Investigación Operativa
Materia
Ciencias Informáticas
reinforcement learning
policy
obstacle avoidance
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/183169
Acceder
id SEDICI_b81009568640d9a28ecd8a6e546cd599
oai_identifier_str oai:sedici.unlp.edu.ar:10915/183169
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Generalization over Environments in Reinforcement LearningMatt, AndreasRegensburger, GeorgCiencias Informáticasreinforcement learningpolicyobstacle avoidanceIn this paper we discuss the problem of reinforcement learning in one environment and applying the policy obtained to other environments. We first state a method to evaluate the utility of a policy. We then propose a general model to apply one policy to different environments and compare them. To illustrate the theory we present examples for an obstacle avoidance behavior in various block world environments.Sociedad Argentina de Informática e Investigación Operativa2002info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf100-109http://sedici.unlp.edu.ar/handle/10915/183169spainfo:eu-repo/semantics/altIdentifier/issn/1660-1079info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T11:50:02Zoai:sedici.unlp.edu.ar:10915/183169Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 11:50:03.044SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Generalization over Environments in Reinforcement Learning
title Generalization over Environments in Reinforcement Learning
spellingShingle Generalization over Environments in Reinforcement Learning
Matt, Andreas
Ciencias Informáticas
reinforcement learning
policy
obstacle avoidance
title_short Generalization over Environments in Reinforcement Learning
title_full Generalization over Environments in Reinforcement Learning
title_fullStr Generalization over Environments in Reinforcement Learning
title_full_unstemmed Generalization over Environments in Reinforcement Learning
title_sort Generalization over Environments in Reinforcement Learning
dc.creator.none.fl_str_mv Matt, Andreas
Regensburger, Georg
author Matt, Andreas
author_facet Matt, Andreas
Regensburger, Georg
author_role author
author2 Regensburger, Georg
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
reinforcement learning
policy
obstacle avoidance
topic Ciencias Informáticas
reinforcement learning
policy
obstacle avoidance
dc.description.none.fl_txt_mv In this paper we discuss the problem of reinforcement learning in one environment and applying the policy obtained to other environments. We first state a method to evaluate the utility of a policy. We then propose a general model to apply one policy to different environments and compare them. To illustrate the theory we present examples for an obstacle avoidance behavior in various block world environments.
Sociedad Argentina de Informática e Investigación Operativa
description In this paper we discuss the problem of reinforcement learning in one environment and applying the policy obtained to other environments. We first state a method to evaluate the utility of a policy. We then propose a general model to apply one policy to different environments and compare them. To illustrate the theory we present examples for an obstacle avoidance behavior in various block world environments.
publishDate 2002
dc.date.none.fl_str_mv 2002
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/10915/183169
url http://sedici.unlp.edu.ar/handle/10915/183169
dc.language.none.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/issn/1660-1079
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
100-109
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_ 1844616360087257088
score 13.069144

Publicaciones similares