TY - GEN
T1 - Bootstrapping intrinsically motivated learning with human demonstration
AU - Nguyen, Sao Mai
AU - Baranes, Adrien
AU - Oudeyer, Pierre Yves
PY - 2011/11/1
Y1 - 2011/11/1
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/80055011598
U2 - 10.1109/DEVLRN.2011.6037329
DO - 10.1109/DEVLRN.2011.6037329
M3 - Conference contribution
AN - SCOPUS:80055011598
SN - 9781612849904
T3 - 2011 IEEE International Conference on Development and Learning, ICDL 2011
BT - 2011 IEEE International Conference on Development and Learning, ICDL 2011
T2 - 2011 IEEE International Conference on Development and Learning, ICDL 2011
Y2 - 24 August 2011 through 27 August 2011
ER -