A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning

Autores
Barsce, Juan Cruz; Palombarini, Jorge Andrés; Martínez, Ernesto Carlos
Año de publicación
2019
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an approach that uses Bayesian optimization to perform a two-step optimization is proposed: first, categorical RL structure hyper-parameters are taken as binary variables and optimized with an acquisition function tailored for such variables. Then, at a lower level of abstraction, solution-level hyper-parameters are optimized by resorting to the expected improvement acquisition function, while using the best categorical hyper-parameters found in the optimization at theupper-level of abstraction. This two-tier approach is validated in a simulated control task. Results obtained are promising and open the way formore user-independent applications of reinforcement learning.
Fil: Barsce, Juan Cruz. Universidad Tecnologica Nacional. Facultad Regional Villa Maria; Argentina
Fil: Palombarini, Jorge Andrés. Universidad Tecnologica Nacional. Facultad Regional Villa Maria; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Centro de Investigaciones y Transferencia de Villa María. Universidad Nacional de Villa María. Centro de Investigaciones y Transferencia de Villa María; Argentina
Fil: Martínez, Ernesto Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina
XX Simposio Argentino de Inteligencia Artificial
Salta
Argentina
Sociedad Argentina de Informática
Materia
AUTONOMOUS LEARNING
BAYESIAN OPTIMIZATION
DEEP LEARNING
REINFORCEMENT LEARNING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/182932

id CONICETDig_880332495c829a447afe95e9b8f0e2d7
oai_identifier_str oai:ri.conicet.gov.ar:11336/182932
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learningBarsce, Juan CruzPalombarini, Jorge AndrésMartínez, Ernesto CarlosAUTONOMOUS LEARNINGBAYESIAN OPTIMIZATIONDEEP LEARNINGREINFORCEMENT LEARNINGhttps://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an approach that uses Bayesian optimization to perform a two-step optimization is proposed: first, categorical RL structure hyper-parameters are taken as binary variables and optimized with an acquisition function tailored for such variables. Then, at a lower level of abstraction, solution-level hyper-parameters are optimized by resorting to the expected improvement acquisition function, while using the best categorical hyper-parameters found in the optimization at theupper-level of abstraction. This two-tier approach is validated in a simulated control task. Results obtained are promising and open the way formore user-independent applications of reinforcement learning.Fil: Barsce, Juan Cruz. Universidad Tecnologica Nacional. Facultad Regional Villa Maria; ArgentinaFil: Palombarini, Jorge Andrés. Universidad Tecnologica Nacional. Facultad Regional Villa Maria; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Centro de Investigaciones y Transferencia de Villa María. Universidad Nacional de Villa María. Centro de Investigaciones y Transferencia de Villa María; ArgentinaFil: Martínez, Ernesto Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; ArgentinaXX Simposio Argentino de Inteligencia ArtificialSaltaArgentinaSociedad Argentina de InformáticaSociedad Argentina de Informática e Investigación Operativa2019info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectSimposioJournalhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/182932A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning; XX Simposio Argentino de Inteligencia Artificial; Salta; Argentina; 2019; 32-382451-7585CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/http://sedici.unlp.edu.ar/handle/10915/87851Nacionalinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-15T15:12:18Zoai:ri.conicet.gov.ar:11336/182932instacron: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:34982025-10-15 15:12:19.18CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
title A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
spellingShingle A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
Barsce, Juan Cruz
AUTONOMOUS LEARNING
BAYESIAN OPTIMIZATION
DEEP LEARNING
REINFORCEMENT LEARNING
title_short A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
title_full A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
title_fullStr A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
title_full_unstemmed A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
title_sort A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning
dc.creator.none.fl_str_mv Barsce, Juan Cruz
Palombarini, Jorge Andrés
Martínez, Ernesto Carlos
author Barsce, Juan Cruz
author_facet Barsce, Juan Cruz
Palombarini, Jorge Andrés
Martínez, Ernesto Carlos
author_role author
author2 Palombarini, Jorge Andrés
Martínez, Ernesto Carlos
author2_role author
author
dc.subject.none.fl_str_mv AUTONOMOUS LEARNING
BAYESIAN OPTIMIZATION
DEEP LEARNING
REINFORCEMENT LEARNING
topic AUTONOMOUS LEARNING
BAYESIAN OPTIMIZATION
DEEP LEARNING
REINFORCEMENT LEARNING
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an approach that uses Bayesian optimization to perform a two-step optimization is proposed: first, categorical RL structure hyper-parameters are taken as binary variables and optimized with an acquisition function tailored for such variables. Then, at a lower level of abstraction, solution-level hyper-parameters are optimized by resorting to the expected improvement acquisition function, while using the best categorical hyper-parameters found in the optimization at theupper-level of abstraction. This two-tier approach is validated in a simulated control task. Results obtained are promising and open the way formore user-independent applications of reinforcement learning.
Fil: Barsce, Juan Cruz. Universidad Tecnologica Nacional. Facultad Regional Villa Maria; Argentina
Fil: Palombarini, Jorge Andrés. Universidad Tecnologica Nacional. Facultad Regional Villa Maria; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Córdoba. Centro de Investigaciones y Transferencia de Villa María. Universidad Nacional de Villa María. Centro de Investigaciones y Transferencia de Villa María; Argentina
Fil: Martínez, Ernesto Carlos. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Desarrollo y Diseño. Universidad Tecnológica Nacional. Facultad Regional Santa Fe. Instituto de Desarrollo y Diseño; Argentina
XX Simposio Argentino de Inteligencia Artificial
Salta
Argentina
Sociedad Argentina de Informática
description Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an approach that uses Bayesian optimization to perform a two-step optimization is proposed: first, categorical RL structure hyper-parameters are taken as binary variables and optimized with an acquisition function tailored for such variables. Then, at a lower level of abstraction, solution-level hyper-parameters are optimized by resorting to the expected improvement acquisition function, while using the best categorical hyper-parameters found in the optimization at theupper-level of abstraction. This two-tier approach is validated in a simulated control task. Results obtained are promising and open the way formore user-independent applications of reinforcement learning.
publishDate 2019
dc.date.none.fl_str_mv 2019
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/conferenceObject
Simposio
Journal
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
status_str publishedVersion
format conferenceObject
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/182932
A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning; XX Simposio Argentino de Inteligencia Artificial; Salta; Argentina; 2019; 32-38
2451-7585
CONICET Digital
CONICET
url http://hdl.handle.net/11336/182932
identifier_str_mv A hierarchical two-tier approach to hyper-parameter optimization in reinforcement learning; XX Simposio Argentino de Inteligencia Artificial; Salta; Argentina; 2019; 32-38
2451-7585
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://sedici.unlp.edu.ar/handle/10915/87851
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
application/pdf
dc.coverage.none.fl_str_mv Nacional
dc.publisher.none.fl_str_mv Sociedad Argentina de Informática e Investigación Operativa
publisher.none.fl_str_mv Sociedad Argentina de Informática e Investigación Operativa
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
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_ 1846083271307296768
score 12.891075