Exploration strategies in developmental robotics: a unified probabilistic framework - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2013

Exploration strategies in developmental robotics: a unified probabilistic framework

Abstract

We present a probabilistic framework unifying two important families of exploration mechanisms recently shown to be efficient to learn complex non-linear redundant sensorimotor mappings. These two explorations mechanisms are: 1) goal babbling, 2) active learning driven by the maximization of empirically measured learning progress. We show how this generic framework allows to model several recent algorithmic architectures for exploration. Then, we propose a particular implementation using Gaussian Mixture Models, which at the same time provides an original empirical measure of the competence progress. Finally, we perform computer simulations on two simulated setups: the control of the end effector of a 7-DoF arm and the control of the formants produced by an articulatory synthesizer.
Fichier principal
Vignette du fichier
CMF_PYO_ICDL2013.pdf (372.01 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00860641 , version 1 (11-09-2013)

Identifiers

  • HAL Id : hal-00860641 , version 1

Cite

Clément Moulin-Frier, Pierre-Yves Oudeyer. Exploration strategies in developmental robotics: a unified probabilistic framework. ICDL-Epirob - International Conference on Development and Learning, Epirob, Aug 2013, Osaka, Japan. ⟨hal-00860641⟩
512 View
654 Download

Share

More