This paper presents an algorithm for learning a highly redundant inverse model in continuous and non-preset environments. Our Socially Guided Intrinsic Motivation by Demonstrations (SGIM-D) algorithm combines the advantages of both social learning and intrinsic motivation, to specialise in a wide range of skills, while lessening its dependence on the teacher. SGIM-D is evaluated on a fishing skill learning experiment.
@article{arxiv.1111.6790,
title = {Constraining the Size Growth of the Task Space with Socially Guided Intrinsic Motivation using Demonstrations},
author = {Sao Mai Nguyen and Adrien Baranes and Pierre-Yves Oudeyer},
journal= {arXiv preprint arXiv:1111.6790},
year = {2011}
}
Comments
JCAI Workshop on Agents Learning Interactively from Human Teachers (ALIHT), Barcelona : Spain (2011)