Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/96699
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Campo DC | Valor | Lengua/Idioma |
---|---|---|
dc.contributor.author | Agostini, Alejandro | - |
dc.contributor.author | Celaya, Enric | - |
dc.date.accessioned | 2014-05-14T11:08:20Z | - |
dc.date.available | 2014-05-14T11:08:20Z | - |
dc.date.issued | 2011 | - |
dc.identifier | isbn: 978-1-57735-514-4 | - |
dc.identifier.citation | International Joint Conference on Artificial Intelligence 2: 1146-1151 (2011) | - |
dc.identifier.uri | http://hdl.handle.net/10261/96699 | - |
dc.description | Trabajo presentado al 22nd IJCAI celebrado en Barcelona del 16 al 22 de julio de 2011. | - |
dc.description.abstract | In this work we propose an approach for generalization in continuous domain Reinforcement Learning that, instead of using a single function approximator, tries many different function approximators in parallel, each one defined in a different region of the domain. Associated with each approximator is a relevance function that locally quantifies the quality of its approximation, so that, at each input point, the approximator with highest relevance can be selected. The relevance function is defined using parametric estimations of the variance of the q-values and the density of samples in the input space, which are used to quantify the accuracy and the confidence in the approximation, respectively. These parametric estimations are obtained from a probability density distribution represented as a Gaussian Mixture Model embedded in the input-output space of each approximator. In our experiments, the proposed approach required a lesser number of experiences for learning and produced more stable convergence profiles than when using a single function approximator. | - |
dc.description.sponsorship | This research was partially supported by Consolider Ingenio 2010, project CSD2007-00018. | - |
dc.publisher | AAAI Press | - |
dc.relation.isversionof | Postprint | - |
dc.rights | openAccess | - |
dc.title | A competitive strategy for function approximation in Q-learning | - |
dc.type | comunicación de congreso | - |
dc.relation.publisherversion | http://ijcai.org/papers11/contents.php | - |
dc.date.updated | 2014-05-14T11:08:20Z | - |
dc.description.version | Peer Reviewed | - |
dc.language.rfc3066 | eng | - |
dc.type.coar | http://purl.org/coar/resource_type/c_5794 | es_ES |
item.openairetype | comunicación de congreso | - |
item.grantfulltext | open | - |
item.cerifentitytype | Publications | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.fulltext | With Fulltext | - |
Aparece en las colecciones: | (IRII) Libros y partes de libros |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
A competitive strategy.pdf | 335,34 kB | Unknown | Visualizar/Abrir |
CORE Recommender
Page view(s)
255
checked on 23-abr-2024
Download(s)
93
checked on 23-abr-2024
Google ScholarTM
Check
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.