Interactive Robot Education

Riad Akrour 1, 2 Marc Schoenauer 1, 2 Michèle Sebag 1, 2
2 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : Aimed at on-board robot training, an approach hybridizing active preference learning and reinforcement learning is presented: Interactive Bayesian Policy Search (IBPS) builds a robotic controller through direct and frugal interaction with the human expert, iteratively emitting preferences among a few behaviors demonstrated by the robot. These preferences allow the robot to gradually refine its policy utility estimate, and select a new policy to be demonstrated, after an Expected Utility of Selection criterion. The paper contribution is on handling the preference noise, due to expert's mistakes or disinterest when demonstrated behaviors are equally unsatisfactory. A noise model is proposed, enabling a resource-limited robot to soundly estimate the preference noise and maintain a robust interaction with the expert, thus enforcing a low sample complexity. A proof of principle of the IBPS approach, in simulation and on-board, is presented.
Type de document :
Communication dans un congrès
Johannes Fuernkranz and Eyke Hüllermeier. ECML/PKDD Workshop on Reinforcement Learning with Generalized Feedback: Beyond Numeric Rewards, Sep 2013, Berlin, Germany. 2013
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00931347
Contributeur : Marc Schoenauer <>
Soumis le : mercredi 15 janvier 2014 - 11:34:08
Dernière modification le : jeudi 11 janvier 2018 - 06:22:14
Document(s) archivé(s) le : mardi 15 avril 2014 - 22:16:48

Fichier

PBRL_01-Akrour.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00931347, version 1

Collections

Citation

Riad Akrour, Marc Schoenauer, Michèle Sebag. Interactive Robot Education. Johannes Fuernkranz and Eyke Hüllermeier. ECML/PKDD Workshop on Reinforcement Learning with Generalized Feedback: Beyond Numeric Rewards, Sep 2013, Berlin, Germany. 2013. 〈hal-00931347〉

Partager

Métriques

Consultations de la notice

433

Téléchargements de fichiers

233