Whom Will an Intrinsically Motivated Robot Learner Choose to Imitate from?

Sao Mai Nguyen (1) , Pierre-Yves Oudeyer (1)

1 Flowers - Flowing Epigenetic Robots and Systems

This paper studies an interactive learning system that couples internally guided learning and social interaction in the case it can interact with several teachers. Socially Guided Intrinsic Motivation with Interactive learning at the Meta level (SGIM- IM) is an algorithm for robot learning of motor skills in high- dimensional, continuous and non-preset environments, with two levels of active learning: SGIM-IM actively decides at a meta- level when and to whom to ask for help; and an active choice of goals in autonomous exploration. We illustrate through an air hockey game that SGIM-IM efficiently chooses the best strategy.

Mots clés: Active Learning; Intrinsic Motivation; Social Learning; Programming by Demonstration; Imitation

Domaines: Intelligence artificielle [cs.AI]; Informatique; Apprentissage [cs.LG]; Robotique [cs.RO]

Sao Mai Nguyen, Pierre-Yves Oudeyer. Whom Will an Intrinsically Motivated Robot Learner Choose to Imitate from?. Post-Graduate Conference on Robotics and Development of Cognition: RobotDoC-PhD 2012, Sep 2012, Lausanne, Switzerland. ⟨hal-00762762⟩