Exploration strategies in developmental robotics: a unified probabilistic framework

Clément Moulin-Frier 1, * Pierre-Yves Oudeyer 1
* Corresponding author
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
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.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-00860641
Contributor : Clément Moulin-Frier <>
Submitted on : Wednesday, September 11, 2013 - 11:24:22 AM
Last modification on : Wednesday, July 3, 2019 - 10:48:04 AM
Long-term archiving on : Thursday, April 6, 2017 - 5:20:59 PM

File

CMF_PYO_ICDL2013.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00860641, version 1

Citation

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⟩

Share

Metrics

Record views

869

Files downloads

592