Properties for Efficient Demonstrations to a Socially Guided Intrinsically Motivated Learner

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

1 Flowers - Flowing Epigenetic Robots and Systems

The combination of learning by intrinsic moti- vation and social learning has been shown to improve the learner's performance and gain precision over a wider range of motor skills, with for instance the SGIM-D learning algorithm. Nevertheless, this bootstrapping a-priori depends on the demonstrations made by the teacher. We propose in this paper to examine this dependence: to what extend the quality of the demonstrations can influence the learning performance, and which are the characteristics of a good demonstrator. Results on a fishing experiment highlights the importance of the difficulty of the demonstrated tasks, as well as the structure of the actions demonstrated.

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

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

Sao Mai Nguyen, Pierre-Yves Oudeyer. Properties for Efficient Demonstrations to a Socially Guided Intrinsically Motivated Learner. 21st IEEE International Symposium on Robot and Human Interactive Communication, Sep 2012, Paris, France. ⟨hal-00762758⟩