Cyclic evolution: a new strategy for improving controllers obtained by layered evolution

Autores
Olivera, Javier Hugo; Lanzarini, Laura Cristina
Año de publicación
2005
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Complex control tasks may be solved by dividing them into a more specific and more easily handled subtasks hierarchy. Several authors have demonstrated that the incremental layered evolution paradigm allows obtaining controllers capable of solving this type of tasks. In this direction, different solutions combining Incremental Evolution with Evolving Neural Networks have been developed in order to provide an adaptive mechanism minimizing the previous knowledge necessary to obtain a good performance giving place to controllers made up of several networks. This paper is focused on the presentation of a new mechanism, called Cyclic Evolution, which allows improving controllers based on neural networks obtained through layered evolution. Its performance is based on continuing the cyclic improvement of each of the networks making up the controller within the whole domain of the problem. The proposed method of this paper has been used to solve the Keepaway game with successful results compared to other solutions recently proposed. Finally, some conclusions are included together with some future lines of work.
Facultad de Informática
Materia
Ciencias Informáticas
Neural nets
incremental evolution
layered evolution
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc/3.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/9595

id SEDICI_820844a5cb4f9cc5509805cb579f868d
oai_identifier_str oai:sedici.unlp.edu.ar:10915/9595
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Cyclic evolution: a new strategy for improving controllers obtained by layered evolutionOlivera, Javier HugoLanzarini, Laura CristinaCiencias InformáticasNeural netsincremental evolutionlayered evolutionComplex control tasks may be solved by dividing them into a more specific and more easily handled subtasks hierarchy. Several authors have demonstrated that the incremental layered evolution paradigm allows obtaining controllers capable of solving this type of tasks. In this direction, different solutions combining Incremental Evolution with Evolving Neural Networks have been developed in order to provide an adaptive mechanism minimizing the previous knowledge necessary to obtain a good performance giving place to controllers made up of several networks. This paper is focused on the presentation of a new mechanism, called Cyclic Evolution, which allows improving controllers based on neural networks obtained through layered evolution. Its performance is based on continuing the cyclic improvement of each of the networks making up the controller within the whole domain of the problem. The proposed method of this paper has been used to solve the Keepaway game with successful results compared to other solutions recently proposed. Finally, some conclusions are included together with some future lines of work.Facultad de Informática2005-12info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionArticulohttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdf211-217http://sedici.unlp.edu.ar/handle/10915/9595enginfo:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Dec05-8.pdfinfo:eu-repo/semantics/altIdentifier/issn/1666-6038info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc/3.0/Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T10:50:44Zoai:sedici.unlp.edu.ar:10915/9595Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 10:50:45.057SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
title Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
spellingShingle Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
Olivera, Javier Hugo
Ciencias Informáticas
Neural nets
incremental evolution
layered evolution
title_short Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
title_full Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
title_fullStr Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
title_full_unstemmed Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
title_sort Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
dc.creator.none.fl_str_mv Olivera, Javier Hugo
Lanzarini, Laura Cristina
author Olivera, Javier Hugo
author_facet Olivera, Javier Hugo
Lanzarini, Laura Cristina
author_role author
author2 Lanzarini, Laura Cristina
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
Neural nets
incremental evolution
layered evolution
topic Ciencias Informáticas
Neural nets
incremental evolution
layered evolution
dc.description.none.fl_txt_mv Complex control tasks may be solved by dividing them into a more specific and more easily handled subtasks hierarchy. Several authors have demonstrated that the incremental layered evolution paradigm allows obtaining controllers capable of solving this type of tasks. In this direction, different solutions combining Incremental Evolution with Evolving Neural Networks have been developed in order to provide an adaptive mechanism minimizing the previous knowledge necessary to obtain a good performance giving place to controllers made up of several networks. This paper is focused on the presentation of a new mechanism, called Cyclic Evolution, which allows improving controllers based on neural networks obtained through layered evolution. Its performance is based on continuing the cyclic improvement of each of the networks making up the controller within the whole domain of the problem. The proposed method of this paper has been used to solve the Keepaway game with successful results compared to other solutions recently proposed. Finally, some conclusions are included together with some future lines of work.
Facultad de Informática
description Complex control tasks may be solved by dividing them into a more specific and more easily handled subtasks hierarchy. Several authors have demonstrated that the incremental layered evolution paradigm allows obtaining controllers capable of solving this type of tasks. In this direction, different solutions combining Incremental Evolution with Evolving Neural Networks have been developed in order to provide an adaptive mechanism minimizing the previous knowledge necessary to obtain a good performance giving place to controllers made up of several networks. This paper is focused on the presentation of a new mechanism, called Cyclic Evolution, which allows improving controllers based on neural networks obtained through layered evolution. Its performance is based on continuing the cyclic improvement of each of the networks making up the controller within the whole domain of the problem. The proposed method of this paper has been used to solve the Keepaway game with successful results compared to other solutions recently proposed. Finally, some conclusions are included together with some future lines of work.
publishDate 2005
dc.date.none.fl_str_mv 2005-12
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Articulo
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/9595
url http://sedici.unlp.edu.ar/handle/10915/9595
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Dec05-8.pdf
info:eu-repo/semantics/altIdentifier/issn/1666-6038
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc/3.0/
Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc/3.0/
Creative Commons Attribution-NonCommercial 3.0 Unported (CC BY-NC 3.0)
dc.format.none.fl_str_mv application/pdf
211-217
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844615758364016640
score 13.070432