Environment-driven Embodied Evolution in a Population of Autonomous Agents

Nicolas Bredeche 1, 2 Jean-Marc Montanier 1, 2
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : This paper is concerned with a fixed-size population of autonomous agents facing unknown, possibly changing, environments. The motivation is to design an embodied evolutionary algorithm that can cope with the implicit fitness function hidden in the environment so as to provide adaptation in the long run at the level of the population. The resulting algorithm, termed Minimal Environment-driven Distributed Evolutionary Adaptation (mEDEA), is shown to be both efficient in unknown environment and robust with regards to abrupt, unpredicted, and possibly lethal changes in the environment.
Type de document :
Communication dans un congrès
Parallel Problem Solving From Nature, Sep 2010, Krakow, Poland. pp.290-299, 2010
Liste complète des métadonnées

https://hal.inria.fr/inria-00506771
Contributeur : Nicolas Bredeche <>
Soumis le : mercredi 28 juillet 2010 - 21:21:37
Dernière modification le : jeudi 5 avril 2018 - 12:30:12
Document(s) archivé(s) le : jeudi 30 juin 2011 - 13:20:08

Fichier

PPSN2010_camerareadyFINAL2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00506771, version 1

Collections

Citation

Nicolas Bredeche, Jean-Marc Montanier. Environment-driven Embodied Evolution in a Population of Autonomous Agents. Parallel Problem Solving From Nature, Sep 2010, Krakow, Poland. pp.290-299, 2010. 〈inria-00506771〉

Partager

Métriques

Consultations de la notice

257

Téléchargements de fichiers

224