Interactive Robot Education - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Interactive Robot Education

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.
Fichier principal
Vignette du fichier
PBRL_01-Akrour.pdf (289.6 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00931347 , version 1 (15-01-2014)

Identifiers

  • HAL Id : hal-00931347 , version 1

Cite

Riad Akrour, Marc Schoenauer, Michèle Sebag. Interactive Robot Education. ECML/PKDD Workshop on Reinforcement Learning with Generalized Feedback: Beyond Numeric Rewards, Sep 2013, Berlin, Germany. ⟨hal-00931347⟩
456 View
298 Download

Share

Gmail Mastodon Facebook X LinkedIn More