Intrinsically motivated machines - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Book Sections Year : 2008

Intrinsically motivated machines

Frederic Kaplan
Pierre-Yves Oudeyer

Abstract

Children seem intrinsically motivated to manipulate, to ex- plore, to test, to learn and they look for activities and situations that provide such learning opportunities. Inspired by research in developmental psychology and neuroscience, some researchers have started to address the problem of designing intrinsic motivation systems. A robot controlled by such systems is able to autonomously explore its environment not to fulfil predefined tasks but driven by an incentive to search for situations where learning happens efficiently. In this paper, we present the ori- gins of these intrinsically motivated machines, our own research in this novel field and we argue that intrinsic motivation might be a crucial step towards machines capable of life-long learning and open-ended development.
Fichier principal
Vignette du fichier
aiSummit06KaplanOudeyer.pdf (1.68 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00420223 , version 1 (28-09-2009)

Identifiers

  • HAL Id : inria-00420223 , version 1

Cite

Frederic Kaplan, Pierre-Yves Oudeyer. Intrinsically motivated machines. Lungarella, M.; Iida, F.; Bongard, J.; Pfeifer, R. 50 Years of AI, Lungarella, M.; Iida, F.; Bongard, J.; Pfeifer, R., pp.n/a, 2008. ⟨inria-00420223⟩
80 View
236 Download

Share

Gmail Facebook X LinkedIn More