Kaplan, F. and Oudeyer, P-Y. Maximizing learning progress: an internal reward system for development. In Iida, F. and Pfeifer, R. and Steels, L. and Kuniyoshi, Y., editor, Embodied Artificial Intelligence, LNCS 3139, pages 259-270, Springer-Verlag. London, UK, 2004.

Sony CSL authors: Frédéric Kaplan, Pierre-Yves Oudeyer

Abstract

This chapter presents a generic internal reward system that drives an agent to increase the complexity of its behavior. This reward system does not reinforce a predefined task. Its purpose is to drive the agent to progress in learning given its embodiment and the environment in which it is placed. The dynamics created by such a system are studied first in a simple environment and then in the context of active vision.

Keywords: curiosity, self-developing systems, active learning, active vision

Downloads

[PDF] Adobe Acrobat PDF file

BibTeX entry

@INCOLLECTION { kaplan:04b, ADDRESS="London, UK", AUTHOR="Kaplan, F. and Oudeyer, P-Y.", BOOKTITLE="Embodied Artificial Intelligence", EDITOR="Iida, F. and Pfeifer, R. and Steels, L. and Kuniyoshi, Y.", PAGES="259--270", PUBLISHER="Springer-Verlag", SERIES="LNCS 3139", TITLE="Maximizing learning progress: an internal reward system for development", YEAR="2004", }