Title :
Properties for efficient demonstrations to a socially guided intrinsically motivated learner
Author :
Nguyen, Sao Mai ; Oudeyer, Pierre-Yves
Author_Institution :
INRIA, ENSTA ParisTech, Paris, France
Abstract :
The combination of learning by intrinsic motivation 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 [1]. 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.
Keywords :
learning by example; learning systems; robots; SGIM-D learning algorithm; bootstrapping a-priori; developmental robotics; fishing experiment; learner performance; learning performance; motor skills; social learning; socially guided intrinsically motivated learner; teacher demonstration; Benchmark testing; Context; Humans; Joints; Optimization; Robots; Space exploration;
Conference_Titel :
RO-MAN, 2012 IEEE
Conference_Location :
Paris
Print_ISBN :
978-1-4673-4604-7
Electronic_ISBN :
1944-9445
DOI :
10.1109/ROMAN.2012.6343819