Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/27948
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Silva, F. | - |
dc.contributor.author | Urbano, P. | - |
dc.contributor.author | Christensen, A. L. | - |
dc.contributor.editor | Pavón, J., Duque-Méndez, N. D., and Fuentes-Fernández, R. | - |
dc.date.accessioned | 2023-02-16T16:07:40Z | - |
dc.date.available | 2023-02-16T16:07:40Z | - |
dc.date.issued | 2012 | - |
dc.identifier.citation | Silva, F., Urbano, P., Christensen, A.L. (2012). Adaptation of robot behaviour through online evolution and neuromodulated learning. In J. Pavón, N. D. Duque-Méndez, & R. Fuentes-Fernández (Eds.) Advances in Artificial Intelligence – IBERAMIA 2012. Lecture Notes in Computer Science (vol. 7637, pp. 300-309). Springer. https://doi.org/10.1007/978-3-642-34654-5_31 | - |
dc.identifier.isbn | 978-3-642-34654-5 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10071/27948 | - |
dc.description.abstract | We propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. We combine online evolution of weights and network topology with neuromodulated learning. We demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic concurrent foraging task. In this task, scattered food items periodically change their nutritive value or become poisonous. Our results show that when neuromodulated learning is employed, neural controllers are synthesised faster than by evolution alone. We demonstrate that the online evolutionary process is capable of generating controllers well adapted to the periodic task changes. An analysis of the evolved networks shows that they are characterised by specialised modulatory neurons that exclusively regulate the output neurons. | eng |
dc.language.iso | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Advances in Artificial Intelligence – IBERAMIA 2012. Lecture Notes in Computer Science | - |
dc.rights | openAccess | - |
dc.subject | Neural networks | eng |
dc.subject | Online Adaptation | eng |
dc.subject | Neuroevolution | eng |
dc.subject | Neuromodulated learning | eng |
dc.subject | odNEAT | eng |
dc.title | Adaptation of robot behaviour through online evolution and neuromodulated learning | eng |
dc.type | conferenceObject | - |
dc.event.title | 13th Ibero-American Conference on Advancesin Artificial Intelligence, IBERAMIA 2012 | - |
dc.event.type | Conferência | pt |
dc.event.location | Cartagena de Indias, Colombia | eng |
dc.event.date | 2012 | - |
dc.pagination | 300 - 309 | - |
dc.peerreviewed | yes | - |
dc.volume | 7637 | - |
dc.date.updated | 2023-02-16T16:07:00Z | - |
dc.description.version | info:eu-repo/semantics/acceptedVersion | - |
dc.identifier.doi | 10.1007/978-3-642-34654-5_31 | - |
dc.subject.fos | Domínio/Área Científica::Ciências Naturais::Matemáticas | por |
dc.subject.fos | Domínio/Área Científica::Ciências Naturais::Ciências da Computação e da Informação | por |
iscte.identifier.ciencia | https://ciencia.iscte-iul.pt/id/ci-pub-11719 | - |
iscte.alternateIdentifiers.wos | WOS:WOS:000314227700031 | - |
iscte.alternateIdentifiers.scopus | 2-s2.0-84906673217 | - |
Aparece nas coleções: | IT-CRI - Comunicações a conferências internacionais |
Ficheiros deste registo:
Ficheiro | Tamanho | Formato | |
---|---|---|---|
conferenceobject_11719.pdf | 318,87 kB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.