An experimental study of adaptive control for evolutionary algorithms


Autoria(s): Di Tollo, Giacomo; Lardeux, Frédéric; Maturana, Jorge; Saubion, Frédéric
Contribuinte(s)

Laboratoire d'Etudes et de Recherche en Informatique d'Angers (LERIA) ; Université d'Angers (UA)

Data(s)

2015

Resumo

International audience

<p>In this paper, we investigate how adaptive operator selection techniques are able to efficiently manage the balance between exploration and exploitation in an evolutionary algorithm, when solving combinatorial optimization problems. We introduce new high level reactive search strategies based on a generic algorithm's controller that is able to schedule the basic variation operators of the evolutionary algorithm, according to the observed state of the search. Our experiments on SAT instances show that reactive search strategies improve the performance of the solving algorithm.</p>

Identificador

hal-01392219

https://hal.archives-ouvertes.fr/hal-01392219

DOI : 10.1016/j.asoc.2015.06.016

OKINA : ua13400

Idioma(s)

en

Publicador

HAL CCSD

Elsevier

Relação

info:eu-repo/semantics/altIdentifier/doi/10.1016/j.asoc.2015.06.016

Fonte

ISSN: 1568-4946

Applied Soft Computing

https://hal.archives-ouvertes.fr/hal-01392219

Applied Soft Computing, Elsevier, 2015, 35, pp.359-372. <http://www.sciencedirect.com/science/article/pii/S1568494615003658>. <10.1016/j.asoc.2015.06.016>

http://www.sciencedirect.com/science/article/pii/S1568494615003658

Palavras-Chave #adaptive operator selection #Algorithms #Design experimentation #evolutionary algorithms #Measurement #Performance #[INFO] Computer Science [cs]
Tipo

info:eu-repo/semantics/article

Journal articles