Some Experiments on the Influence of Problem Hardness in Morphological Development Based Learning of Neural Controllers

UDC.coleccionInvestigaciónes_ES
UDC.conferenceTitleHybrid Artificial Intelligent Systems (HAIS 2020)es_ES
UDC.departamentoCiencias da Computación e Tecnoloxías da Informaciónes_ES
UDC.endPage373es_ES
UDC.grupoInvGrupo Integrado de Enxeñaría (GII)es_ES
UDC.institutoCentroCITENI - Centro de Investigación en Tecnoloxías Navais e Industriaises_ES
UDC.startPage362es_ES
UDC.volumeLNCS 12344es_ES
dc.contributor.authorNaya-Varela, M.
dc.contributor.authorDuro, Richard J.
dc.contributor.authorFaíña, Andrés
dc.date.accessioned2024-09-30T13:23:51Z
dc.date.available2024-09-30T13:23:51Z
dc.date.issued2020
dc.descriptionThis version of the conference paper has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use (https://www.springernature.com/gp/open-science/policies/accepted-manuscript-terms), but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-030-61705-9_30.es_ES
dc.descriptionIncluded in 'Hybrid Artificial Intelligent Systems', the 15th International Conference, HAIS 2020, Gijón, Spain, November 11-13, 2020, Proceedings.es_ES
dc.description.abstract[Abstract]: Natural beings undergo a morphological development process of their bodies while they are learning and adapting to the environments they face from infancy to adulthood. In fact, this is the period where the most important learning processes, those that will support learning as adults, will take place. However, in artificial systems, this interaction between morphological development and learning, and its possible advantages, have seldom been considered. In this line, this paper seeks to provide some insights into how morphological development can be harnessed in order to facilitate learning in embodied systems facing tasks or domains that are hard to learn. In particular, here we will concentrate on whether morphological development can really provide any advantage when learning complex tasks and whether its relevance towards learning increases as tasks become harder. To this end, we present the results of some initial experiments on the application of morphological development to learning to walk in three cases, that of a quadruped, a hexapod and that of an octopod. These results seem to confirm that as task learning difficulty increases the application of morphological development to learning becomes more advantageous.es_ES
dc.description.sponsorshipThis work has been partially funded by the Ministerio de Ciencia, Innovación y Universidades of Spain/FEDER (grant RTI2018-101114-B-I00), Xunta de Galicia and FEDER (grant ED431C 2017/12) and M. Naya-Varela is very grateful for the support of the UDC-Inditex 2019 grant for international mobility. We also want to thank CESGA (Centro de Supercomputación de Galicia. https://www.cesga.es/) for the possibility of using its resources.es_ES
dc.description.sponsorshipXunta de Galicia; ED431C 2017/12es_ES
dc.identifier.citationNaya-Varela, M., Faina, A., Duro, R.J. (2020). Some Experiments on the Influence of Problem Hardness in Morphological Development Based Learning of Neural Controllers. In: de la Cal, E.A., Villar Flecha, J.R., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2020. Lecture Notes in Computer Science(), vol 12344. Springer, Cham. https://doi.org/10.1007/978-3-030-61705-9_30es_ES
dc.identifier.doi10.1007/978-3-030-61705-9_30
dc.identifier.isbn978-3-030-61704-2
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/2183/39308
dc.language.isoenges_ES
dc.publisherSpringeres_ES
dc.relation.ispartofseriesLecture Notes in Computer Science (LNCS), including its subseries Lecture Notes in Artificial Intelligence (LNAI) and Lecture Notes in Bioinformatics (LNBI)es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-101114-B-I00/ES/ ARQUITECTURA COGNITIVA PARA ROBOTS CON ADAPTACION DE COMPORTAMIENTO AUTONOMAMENTE MOTIVADAes_ES
dc.relation.urihttps://doi.org/10.1007/978-3-030-61705-9_30es_ES
dc.rights©2020 Springer International Publishing AG. Subject to Springer Nature’s AM terms of use (https://www.springernature.com/gp/open-science/policies/accepted-manuscript-terms).es_ES
dc.rights.accessRightsopen accesses_ES
dc.subjectCognitive roboticses_ES
dc.subjectMorphological development (MD)es_ES
dc.subjectQuadrupedal walkinges_ES
dc.subjectHexapod walkinges_ES
dc.subjectOctopod walkinges_ES
dc.titleSome Experiments on the Influence of Problem Hardness in Morphological Development Based Learning of Neural Controllerses_ES
dc.typeconference outputes_ES
dspace.entity.typePublication
relation.isAuthorOfPublicationa3082627-8669-4257-8e06-9d5155b5bb31
relation.isAuthorOfPublication85df8d3f-49d3-4327-811d-e8038cead7dd
relation.isAuthorOfPublication.latestForDiscoverya3082627-8669-4257-8e06-9d5155b5bb31

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Naya_Varela_Martin_2020_Some_Experiments_on_the_Influence_of_Problem_Hardness_in_Morphological_Development_Based_Learning_of_Neural_Controllers.pdf
Size:
851.9 KB
Format:
Adobe Portable Document Format
Description: