Robust Intrinsically Motivated Exploration and Active Learning - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Robust Intrinsically Motivated Exploration and Active Learning

Adrien Baranes
  • Fonction : Auteur
  • PersonId : 850157
Pierre-Yves Oudeyer

Résumé

IAC was initially introduced as a developmental mechanism allowing a robot to self-organize developmental trajectories of increasing complexity without pre-programming the particular developmental stages. In this paper, we argue that IAC and other intrinsically motivated learning heuristics could be viewed as active learning algorithms that are particularly suited for learning forward models in unprepared sensorimotor spaces with large unlearnable subspaces. Then, we introduce a novel formulation of IAC, called R-IAC, and show that its performances as an intrinsically motivated active learning algorithm are far superior to IAC in a complex sensorimotor space where only a small subspace is neither unlearnable nor trivial. We also show results in which the learnt forward model is reused in a control scheme.
Fichier non déposé

Dates et versions

inria-00420306 , version 1 (28-09-2009)

Identifiants

  • HAL Id : inria-00420306 , version 1

Citer

Adrien Baranes, Pierre-Yves Oudeyer. Robust Intrinsically Motivated Exploration and Active Learning. IEEE International Conference on Learning and Development, 2009, Shangaï, China. ⟨inria-00420306⟩
55 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More