Bootstrapping Intrinsically Motivated Learning with Human Demonstrations

Details Bootstrapping Intrinsically Motivated Learning with Human Demonstrations Bootstrapping Intrinsically Motivated Learning with Human Demonstrations

2011-12-08

arxiv.org/abs/1112.1937v1

Computer Science

Learning

IEEE International Conference on Development and Learning, Frankfurt : Germany (2011)

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Bootstrapping Intrinsically Motivated Learning with Human Demonstrations does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Bootstrapping Intrinsically Motivated Learning with Human Demonstrations, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bootstrapping Intrinsically Motivated Learning with Human Demonstrations will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-42836