Passer à la navigation principale Passer à la recherche Passer au contenu principal

An iterative algorithm for forward-parameterized skill discovery

  • ENSTA ParisTech
  • Univ. Bordeaux

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

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.

langue originaleAnglais
titre2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016
EditeurInstitute of Electrical and Electronics Engineers Inc.
Pages186-192
Nombre de pages7
ISBN (Electronique)9781509050697
Les DOIs
étatPublié - 7 févr. 2017
Evénement2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016 - Cergy-Pontoise, France
Durée: 19 sept. 201622 sept. 2016

Série de publications

Nom2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016

Une conférence

Une conférence2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016
Pays/TerritoireFrance
La villeCergy-Pontoise
période19/09/1622/09/16

Empreinte digitale

Examiner les sujets de recherche de « An iterative algorithm for forward-parameterized skill discovery ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation