Bootstrapping Intrinsically Motivated Learning with Human Demonstrations

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

1 Flowers - Flowing Epigenetic Robots and Systems

This paper studies the coupling of internally guided learning and social interaction, and more specifically the improvement owing to demonstrations of the learning by intrinsic motivation. We present Socially Guided Intrinsic Motivation by Demonstration (SGIM-D), an algorithm for learning in continuous, unbounded and non-preset environments. After introducing social learning and intrinsic motivation, we describe the design of our algorithm, before showing through a fishing experiment that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation to gain a wide repertoire while being specialised in specific subspaces.

Mots clés: Intrinsic Motivation; Social Learning; Learning by Demonstration; Imitation Learning; Human Teacher

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

Sao Mai Nguyen, Adrien Baranes, Pierre-Yves Oudeyer. Bootstrapping Intrinsically Motivated Learning with Human Demonstrations. IEEE International Conference on Development and Learning, 2011, Frankfurt, Germany. pp.Nguyen. ⟨hal-00645986⟩