Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/241699
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE DE ESTADUAL DE CAMPINASpt_BR
dc.typeArtigo de periódicopt_BR
dc.titleA Neuroscience Inspired Gated Learning Action Selection Mechanismpt_BR
dc.contributor.authorRaizerpt_BR
dc.contributor.authorKlaus; Gudwinpt_BR
dc.contributor.authorRicardo R.pt_BR
unicamp.author.emailklaus@dca.fee.unicamp.br; gudwin@dca.fee.unicamp.brpt_BR
unicamp.authorGudwin, Ricardo R.] Univ Estadual Campinas, Sch Elect & Comp Engn, Campinas, SP, Brazilpt_BR
unicamp.author.external[Raizer, Klauspt
dc.subjectComputational Modelspt_BR
dc.subjectReinforcementpt_BR
dc.subjectGangliapt_BR
dc.description.abstractThis paper presents an algorithm for action selection, in the context of intelligent agents, capable of learning from rewards which are sparse in time. Inspiration for the proposed algorithm was drawn from computational neuroscience models of how the human prefrontal cortex (PFC) works. We have observed that this abstraction provides some advantages, such as the representation of solutions as trees, making it human-readable, and turning the learning process into a combinatorial optimization problem. Results for it solving the 1-2-AX working memory task are presented and discussed. We also argue the pros and cons of the proposed algorithm and, finally, address potential future work. (C) 2014 Elsevier B.V. All rights reserved.en
dc.relation.ispartofBIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURESpt_BR
dc.publisher.countryAMSTERDAMpt_BR
dc.publisherELSEVIER SCIENCE BVpt_BR
dc.date.issued2015-JANpt_BR
dc.identifier.citationA Neuroscience Inspired Gated Learning Action Selection Mechanism. Elsevier Science Bv, v. 11, p. 65-74 JAN-2015.pt_BR
dc.language.isoenpt_BR
dc.description.volume11pt_BR
dc.description.firstpage65pt_BR
dc.description.lastpage74pt_BR
dc.rightsembargopt_BR
dc.sourceWOSpt_BR
dc.identifier.issn2212-683Xpt_BR
dc.identifier.wosidWOS:000352744600007pt_BR
dc.identifier.doi10.1016/j.bica.2014.11.016pt_BR
dc.identifier.urlhttp://www.sciencedirect.com/science/article/pii/S2212683X14000796pt_BR
dc.description.sponsorshipConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)pt_BR
dc.description.sponsorshipCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)pt_BR
dc.description.sponsorshipFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)pt_BR
dc.description.sponsorship1Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)pt_BR
dc.description.sponsorship1Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)pt_BR
dc.description.sponsorship1Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)pt_BR
dc.date.available2016-06-07T13:14:42Z-
dc.date.accessioned2016-06-07T13:14:42Z-
dc.description.provenanceMade available in DSpace on 2016-06-07T13:14:42Z (GMT). No. of bitstreams: 1 wos_000352744600007.pdf: 1348105 bytes, checksum: a7db2c35372b01fcd8e0782c8b95f8f5 (MD5) Previous issue date: 2015en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/241699-
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
wos_000352744600007.pdf1.32 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.