Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/18069
COMPARTIR / EXPORTAR:
SHARE CORE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Campo DC | Valor | Lengua/Idioma |
---|---|---|
dc.contributor.author | Bianchi, Reinaldo | - |
dc.contributor.author | Ros, Raquel | - |
dc.contributor.author | López de Mántaras, Ramón | - |
dc.date.accessioned | 2009-10-26T14:38:00Z | - |
dc.date.available | 2009-10-26T14:38:00Z | - |
dc.date.issued | 2009 | - |
dc.identifier.citation | Case-Based Reasoning Research and Development, 8th International Conference on Case-Based Reasoning, ICCBR 2009 Seattle, WA, USA, July 20-23, 2009 Proceedings. Lecture Notes in Artificial Intelligence, Vol. 5650, p.p.: 75-89, Springer Verlag, 2009 | en_US |
dc.identifier.isbn | 978-3-642-02997-4 | - |
dc.identifier.uri | http://hdl.handle.net/10261/18069 | - |
dc.description | The original publication is available at www.springerlink.com | en_US |
dc.description.abstract | This 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. | en_US |
dc.description.sponsorship | 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. | en_US |
dc.format.extent | 189739 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.language.iso | eng | en_US |
dc.publisher | Springer Nature | en_US |
dc.rights | openAccess | en_US |
dc.subject | Case-based reasoning | en_US |
dc.subject | CBR | en_US |
dc.subject | Reinforcement learning | en_US |
dc.subject | Case-based heuristically accelerated reinforcement learning | en_US |
dc.subject | Multiagent learning | en_US |
dc.title | Improving Reinforcement Learning by using Case-Based Heuristics | en_US |
dc.type | artículo | en_US |
dc.identifier.doi | 10.1007/978-3-642-02998-1_7 | - |
dc.description.peerreviewed | Peer reviewed | en_US |
dc.relation.publisherversion | 10.1007/978-3-642-02998-1_7 | en_US |
dc.type.coar | http://purl.org/coar/resource_type/c_6501 | es_ES |
item.fulltext | With Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.cerifentitytype | Publications | - |
item.openairetype | artículo | - |
item.grantfulltext | open | - |
item.languageiso639-1 | en | - |
Aparece en las colecciones: | (IIIA) Comunicaciones congresos |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
ICCBR09_LNAI5650_Bi_Ro_RLM.pdf | 185,29 kB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
SCOPUSTM
Citations
34
checked on 16-abr-2024
Page view(s)
309
checked on 23-abr-2024
Download(s)
351
checked on 23-abr-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.