Intrinsically motivated exploration as efficient active learning in unknown and unprepared spaces - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Intrinsically motivated exploration as efficient active learning in unknown and unprepared spaces

Pierre-Yves Oudeyer
Adrien Baranes
  • Function : Author
  • PersonId : 850157

Abstract

Intrinsic motivations are mechanisms that guide curiosity-driven exploration (Berlyne, 1965). They have been proposed to be crucial for self-organizing developmental trajectories (Oudeyer et al. , 2007) as well as for guiding the learning of general and reusable skills (Barto et al., 2005). Here, we argue that they can be considered as “active learning” algorithms, and show that some of them also allow for very efficient learning in unprepared sensorimotor spaces, outperforming existing active learning algorithms.
Fichier principal
Vignette du fichier
OudeyerBaranesEpirob08.pdf (440.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00420125 , version 1 (28-09-2009)

Identifiers

  • HAL Id : inria-00420125 , version 1

Cite

Pierre-Yves Oudeyer, Adrien Baranes. Intrinsically motivated exploration as efficient active learning in unknown and unprepared spaces. the 8th International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, 2008, Brighton, United Kingdom. 2p. ⟨inria-00420125⟩
136 View
96 Download

Share

Gmail Facebook X LinkedIn More