Memory-Enhanced Evolutionary Robotics: The Echo State Network Approach

Cédric Hartland 1 Nicolas Bredeche 1, 2, 3 Michèle Sebag 3
2 TANC - Algorithmic number theory for cryptology
LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau], Inria Saclay - Ile de France, X - École polytechnique, CNRS - Centre National de la Recherche Scientifique : UMR7161
3 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : Interested in Evolutionary Robotics, this paper focuses on the acquisition and exploitation of memory skills. The targeted task is a well-studied benchmark problem, the Tolman maze, requiring in principle the robotic controller to feature some (limited) counting abilities. An elaborate experimental setting is used to enforce the controller generality and prevent opportunistic evolution from mimicking deliberative skills through smart reactive heuristics. The paper compares the prominent NEAT approach, achieving the non-parametric optimization of Neural Nets, with the evolutionary optimization of Echo State Networks, pertaining to the recent field of Reservoir Computing. While both search spaces offer a sufficient expressivity and enable the modelling of complex dynamic systems, the latter one is amenable to robust parametric, linear optimization with Covariance Matrix Adaptation-Evolution Strategies.
Type de document :
Communication dans un congrès
Congress on Evolutionary Computation (CEC 2009), 2009, Trondheim, Norway. 2009
Liste complète des métadonnées

https://hal.inria.fr/inria-00413238
Contributeur : Nicolas Bredeche <>
Soumis le : mardi 3 novembre 2009 - 12:01:36
Dernière modification le : jeudi 10 mai 2018 - 02:06:29
Document(s) archivé(s) le : jeudi 30 juin 2011 - 11:47:37

Fichier

cec2009tolman.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00413238, version 1

Collections

Citation

Cédric Hartland, Nicolas Bredeche, Michèle Sebag. Memory-Enhanced Evolutionary Robotics: The Echo State Network Approach. Congress on Evolutionary Computation (CEC 2009), 2009, Trondheim, Norway. 2009. 〈inria-00413238〉

Partager

Métriques

Consultations de la notice

256

Téléchargements de fichiers

192