Improving Reinforcement Learning by using Case-Based Heuristics

The original publication is available at www.springerlink.com

Detalles Bibliográficos
Autores: Bianchi, Reinaldo, Ros Espinoza, Raquel, López de Mántaras, Ramón
Tipo de recurso: artículo
Fecha de publicación:2009
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/18069
Acceso en línea:http://hdl.handle.net/10261/18069
Access Level:acceso abierto
Palabra clave:Case-based reasoning
CBR
Reinforcement learning
Case-based heuristically accelerated reinforcement learning
Multiagent learning
id ES_4d359bb4fe826b90bd6db692aa1e7c39
oai_identifier_str oai:digital.csic.es:10261/18069
network_acronym_str ES
network_name_str España
repository_id_str
spelling Improving Reinforcement Learning by using Case-Based HeuristicsBianchi, ReinaldoRos Espinoza, RaquelLópez de Mántaras, RamónCase-based reasoningCBRReinforcement learningCase-based heuristically accelerated reinforcement learningMultiagent learningThe original publication is available at www.springerlink.comThis work presents a new approach that allows the use of cases in a case base as heuristics to speed up Reinforcement Learning algorithms, combining Case Based Reasoning (CBR) and Reinforcement Learning (RL) techniques. This approach, called Case Based Heuristically Accelerated Reinforcement Learning (CB-HARL), builds upon an emerging technique, the Heuristic Accelerated Reinforcement Learning (HARL), in which RL methods are accelerated by making use of heuristic information. CB-HARL is a subset of RL that makes use of a heuristic function derived from a case base, in a Case Based Reasoning manner. An algorithm that incorporates CBR techniques into the Heuristically Accelerated Q–Learning is also proposed. Empirical evaluations were conducted in a simulator for the RoboCup Four-Legged Soccer Competition, and results obtained shows that using CB-HARL, the agents learn faster than using either RL or HARL methods.This work has been partially funded by the FI grant and the BE grant from the AGAUR, the 2005-SGR-00093 project, supported by the Generalitat de Catalunya, the MID-CBR project grant TIN 2006-15140-C03-01 and FEDER funds. Reinaldo Bianchi is supported by CNPq grant 201591/2007-3 and FAPESP grant 2009/01610-1.Peer reviewedSpringer Nature200920092009info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501189739 bytesapplication/pdfhttp://hdl.handle.net/10261/18069reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés10.1007/978-3-642-02998-1_7info:eu-repo/semantics/openAccessoai:digital.csic.es:10261/180692026-05-22T06:33:51Z
dc.title.none.fl_str_mv Improving Reinforcement Learning by using Case-Based Heuristics
title Improving Reinforcement Learning by using Case-Based Heuristics
spellingShingle Improving Reinforcement Learning by using Case-Based Heuristics
Bianchi, Reinaldo
Case-based reasoning
CBR
Reinforcement learning
Case-based heuristically accelerated reinforcement learning
Multiagent learning
title_short Improving Reinforcement Learning by using Case-Based Heuristics
title_full Improving Reinforcement Learning by using Case-Based Heuristics
title_fullStr Improving Reinforcement Learning by using Case-Based Heuristics
title_full_unstemmed Improving Reinforcement Learning by using Case-Based Heuristics
title_sort Improving Reinforcement Learning by using Case-Based Heuristics
dc.creator.none.fl_str_mv Bianchi, Reinaldo
Ros Espinoza, Raquel
López de Mántaras, Ramón
author Bianchi, Reinaldo
author_facet Bianchi, Reinaldo
Ros Espinoza, Raquel
López de Mántaras, Ramón
author_role author
author2 Ros Espinoza, Raquel
López de Mántaras, Ramón
author2_role author
author
dc.subject.none.fl_str_mv Case-based reasoning
CBR
Reinforcement learning
Case-based heuristically accelerated reinforcement learning
Multiagent learning
topic Case-based reasoning
CBR
Reinforcement learning
Case-based heuristically accelerated reinforcement learning
Multiagent learning
description The original publication is available at www.springerlink.com
publishDate 2009
dc.date.none.fl_str_mv 2009
2009
2009
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/18069
url http://hdl.handle.net/10261/18069
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv 10.1007/978-3-642-02998-1_7
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 189739 bytes
application/pdf
dc.publisher.none.fl_str_mv Springer Nature
publisher.none.fl_str_mv Springer Nature
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407677035053056
score 15,812429