Genetic lander: An experiment in accurate neuro-genetic control

Abstract : The control problem of soft-landing a toy lunar module sim-ulation is investigated in the context of neural nets. While traditional supervised back-propagation training is inappropriate for lack of train-ing exemplars, genetic algorithms allow a controller to be evolved with-out diiculty: Evolution is a form of unsupervised learning. A novelty introduced in this paper is the presentation of additional renormalized inputs to the net; experiments indicate that the presence of such inputs allows precision of control to be attained faster, when learning time is measured by the number of generations for which the GA must run to attain a certain mean performance.
Type de document :
Communication dans un congrès
Davidor, Yuval and Schwefel, Hans-Paul and Männer, Reinhard. Proc. PPSN III, Oct 1994, Jérusalem, France. LNCS, Springer Verlag, 866, pp.452 - 461, 1994, Parallel Problem Solving from Nature — PPSN III. 〈10.1007/3-540-58484-6_288〉
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01079614
Contributeur : Marc Schoenauer <>
Soumis le : lundi 3 novembre 2014 - 12:15:52
Dernière modification le : jeudi 12 avril 2018 - 01:49:25
Document(s) archivé(s) le : mercredi 4 février 2015 - 10:31:21

Fichier

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

Identifiants

Collections

Citation

Edmund Ronald, Marc Schoenauer. Genetic lander: An experiment in accurate neuro-genetic control. Davidor, Yuval and Schwefel, Hans-Paul and Männer, Reinhard. Proc. PPSN III, Oct 1994, Jérusalem, France. LNCS, Springer Verlag, 866, pp.452 - 461, 1994, Parallel Problem Solving from Nature — PPSN III. 〈10.1007/3-540-58484-6_288〉. 〈hal-01079614〉

Partager

Métriques

Consultations de la notice

137

Téléchargements de fichiers

104