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

Mostrar todas las versiones(2)

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 sol...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Olivera, Javier Hugo, Lanzarini, Laura Cristina
Formato:	Articulo
Lenguaje:	Inglés
Publicado:	2005
Materias:	Ciencias Informáticas Neural nets incremental evolution layered evolution
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/9595 http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Dec05-8.pdf
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-9595
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Neural nets incremental evolution layered evolution
spellingShingle	Ciencias Informáticas Neural nets incremental evolution layered evolution Olivera, Javier Hugo Lanzarini, Laura Cristina Cyclic evolution: a new strategy for improving controllers obtained by layered evolution
topic_facet	Ciencias Informáticas Neural nets incremental evolution layered evolution
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.
format	Articulo Articulo
author	Olivera, Javier Hugo Lanzarini, Laura Cristina
author_facet	Olivera, Javier Hugo Lanzarini, Laura Cristina
author_sort	Olivera, Javier Hugo
title	Cyclic evolution: a new strategy for improving controllers obtained by 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
publishDate	2005
url	http://sedici.unlp.edu.ar/handle/10915/9595 http://journal.info.unlp.edu.ar/wp-content/uploads/JCST-Dec05-8.pdf
work_keys_str_mv	AT oliverajavierhugo cyclicevolutionanewstrategyforimprovingcontrollersobtainedbylayeredevolution AT lanzarinilauracristina cyclicevolutionanewstrategyforimprovingcontrollersobtainedbylayeredevolution
bdutipo_str	Repositorios
_version_	1764820493400014851

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

Ejemplares similares