Autonomous Robots

, Volume 36, Issue 3, pp 273–294

Socially guided intrinsic motivation for robot learning of motor skills

Authors

    • Flowers TeamINRIA and ENSTA ParisTech
  • Pierre-Yves Oudeyer
    • Flowers TeamINRIA and ENSTA ParisTech
Article

DOI: 10.1007/s10514-013-9339-y

Cite this article as:
Nguyen, S.M. & Oudeyer, P. Auton Robot (2014) 36: 273. doi:10.1007/s10514-013-9339-y

Abstract

This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our algorithmic architecture, called SGIM-D, allows efficient learning of high-dimensional continuous sensorimotor inverse models in robots, and in particular learns distributions of parameterised motor policies that solve a corresponding distribution of parameterised goals/tasks. This is made possible by the technical integration of imitation learning techniques within an algorithm for learning inverse models that relies on active goal babbling. After reviewing social learning and intrinsic motivation approaches to action learning, we describe the general framework of our algorithm, before detailing its architecture. In an experiment where a robot arm has to learn to use a flexible fishing line, we illustrate that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation and benefits from human demonstration properties to learn how to produce varied outcomes in the environment, while developing more precise control policies in large spaces.

Keywords

Active learningIntrinsic motivationExploration Motor skill learningInverse model Programming by demonstrationLearning from demonstrationImitation

Copyright information

© Springer Science+Business Media New York 2013