Intrinsically motivated exploration as efficient active learning in unknown and unprepared spaces

Pierre-Yves Oudeyer 1 Adrien Baranes 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : Intrinsic motivations are mechanisms that guide curiosity-driven exploration (Berlyne, 1965). They have been proposed to be crucial for self-organizing developmental trajectories (Oudeyer et al. , 2007) as well as for guiding the learning of general and reusable skills (Barto et al., 2005). Here, we argue that they can be considered as “active learning” algorithms, and show that some of them also allow for very efficient learning in unprepared sensorimotor spaces, outperforming existing active learning algorithms.
Type de document :
Communication dans un congrès
the 8th International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, 2008, Brighton, United Kingdom. Lund University Cognitive Studies, Lund:LUCS, Brighton., 2p., 2008
Liste complète des métadonnées

Littérature citée [4 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/inria-00420125
Contributeur : Jérôme Béchu <>
Soumis le : lundi 28 septembre 2009 - 11:38:50
Dernière modification le : jeudi 16 novembre 2017 - 17:12:01
Document(s) archivé(s) le : mardi 15 juin 2010 - 22:17:54

Fichier

OudeyerBaranesEpirob08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00420125, version 1

Collections

INRIA | ENSTA | PARISTECH | ENSTA_U2IS

Citation

Pierre-Yves Oudeyer, Adrien Baranes. Intrinsically motivated exploration as efficient active learning in unknown and unprepared spaces. the 8th International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, 2008, Brighton, United Kingdom. Lund University Cognitive Studies, Lund:LUCS, Brighton., 2p., 2008. 〈inria-00420125〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

331

Téléchargements de fichiers

220

Contact


archive-ouverte@inria.fr