Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity

Résumé

The bootstrap problem is often recognized as one of the main challenges of evolutionary robotics: if all individuals from the first randomly generated population perform equally poorly, the evolutionary process won't generate any interesting solution. To overcome this lack of fitness gradient, we propose to efficiently explore behaviors until the evolutionary process finds an individual with a non-minimal fitness. To that aim, we introduce an original diversity-preservation mechanism, called behavioral diversity, that relies on a distance between behaviors (instead of genotypes or phenotypes) and multi-objective evolutionary optimization. This approach has been successfully tested and compared to a recently published incremental evolution method (multi-subgoal evolution) on the evolution of a neuro-controller for a light-seeking mobile robot. Results obtained with these two approaches are qualitatively similar although the introduced one is less directed than multi-subgoal evolution.
Fichier principal
Vignette du fichier
mouret.pdf (272.39 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00473147 , version 1 (14-04-2010)

Identifiants

  • HAL Id : hal-00473147 , version 1

Citer

Jean-Baptiste Mouret, Stéphane Doncieux. Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity. Eleventh conference on Congress on Evolutionary Computation (CEC'09), 2009, Trondheim, Norway. pp.1161--1168. ⟨hal-00473147⟩
118 Consultations
652 Téléchargements

Partager

Gmail Facebook X LinkedIn More