Universität Bielefeld Electronic Collections animiertes Foto Universität Bielefeld

Access to the Document



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

Nguyen, Sao Mai ; Oudeyer, Pierre-Yves



Download file

Abstract:
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 (SGIMIM) is an algorithm for robot learning of motor skills in highdimensional, continuous and non-preset environments, with two levels of active learning: SGIM-IM actively decides at a metalevel 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.


Keywords: Active Learning , Intrinsic Motivation , Social Learning , Programming by Demonstration , Imitation
Institution: Research Institute for Cognition and Robotics (CoR-Lab)
DDC classification: Data processing, computer science, computer systems

Suggested Citation:
Sao Mai Nguyen, Pierre-Yves Oudeyer, Whom Will an Intrinsically Motivated Robot Learner Choose to Imitate from?. Proceedings of the Post-Graduate Conference on Robotics and Development of Cognition, J. Szufnarowska, Ed., September 2012


URL: http://biecoll.ub.uni-bielefeld.de/volltexte/2012/5238



 Questions or comments: publikationsdienste.ub@uni-bielefeld.de
 Latest update: 15 Feb 2011
 Legal Notice
OPUS-Logo     OAI compliant      BU Logo
OAI-Logo