Robustness in the long run: Auto-teaching vs Anticipation in Evolutionary Robotics

Nicolas Godzik 1 Marc Schoenauer 1 Michèle Sebag 1
1 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
Abstract : In Evolutionary Robotics, auto-teaching networks, neural networks that modify their own weights during the life-time of the robot, have been shown to be powerful architectures to develop adaptive controllers. Unfortunately, when run for a longer period of time than that used during evolution, the long-term behavior of such networks can become unpredictable. This paper gives an example of such dangerous behavior, and proposes an alternative solution based on anticipation: as in auto-teaching networks, a secondary network is evolved, but its outputs try to predict the next state of the robot sensors. The weights of the action network are adjusted using some back-propagation procedure based on the errors made by the anticipatory network. First results -- in simulated environments -- show a tremendous increase in robustness of the long-term behavior of the controller.
Type de document :
Communication dans un congrès
Xin Yao et al. Parallel Problem Solving from Nature, Sep 2004, Birmingham, Springer Verlag, 3242 (3242), pp.932-941, 2004, LNCS
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00145172
Contributeur : Marc Schoenauer <>
Soumis le : mercredi 9 mai 2007 - 06:41:01
Dernière modification le : jeudi 10 mai 2018 - 02:06:57
Document(s) archivé(s) le : mercredi 7 avril 2010 - 03:33:14

Fichier

ppsn2004.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00145172, version 1

Collections

Citation

Nicolas Godzik, Marc Schoenauer, Michèle Sebag. Robustness in the long run: Auto-teaching vs Anticipation in Evolutionary Robotics. Xin Yao et al. Parallel Problem Solving from Nature, Sep 2004, Birmingham, Springer Verlag, 3242 (3242), pp.932-941, 2004, LNCS. 〈inria-00145172〉

Partager

Métriques

Consultations de la notice

306

Téléchargements de fichiers

723