An Iterative Algorithm for Forward-Parameterized Skill Discovery - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

An Iterative Algorithm for Forward-Parameterized Skill Discovery

Abstract

We introduce COCOTTE (COnstrained Complexity Optimization Through iTerative merging of Experts), an iterative algorithm for discovering discrete, meaningful parameterized skills and learning explicit models of them from a set of behaviour examples. We show that forward-parameterized skills can be seen as smooth components of a locally smooth function and, framing the problem as the constrained minimization of a complexity measure, we propose an iterative algorithm to discover them. This algorithm fits well in the developmental robotics framework, as it does not require any external definition of a parameterized task, but discovers skills parameterized by the action from data. An application of our method to a simulated setup featuring a robotic arm interacting with an object is shown.
Fichier principal
Vignette du fichier
Matricon_ICDL16_final.pdf (615.07 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01370820 , version 1 (23-09-2016)

Identifiers

  • HAL Id : hal-01370820 , version 1

Cite

Adrien Matricon, David Filliat, Pierre-Yves Oudeyer. An Iterative Algorithm for Forward-Parameterized Skill Discovery. Sixth Joint IEEE International Conference Developmental Learning and Epigenetic Robotics (ICDL-EPIROB), Sep 2016, Cergy-Pontoise, France. ⟨hal-01370820⟩
166 View
273 Download

Share

Gmail Mastodon Facebook X LinkedIn More