R-IAC : Robust Intrinsically Motivated Active Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

R-IAC : Robust Intrinsically Motivated Active Learning

Abstract

IAC was initially introduced as a developmental mechanisms allowing a robot to self-organize developmental trajectories of increasing complexity without pre-programming the particular developmental stages. In this paper, we argue that IAC and other intrinsically motivated learning heuristics could be viewed as active learning algorithms that are particularly suited for learning forward models in unprepared sensorimotor spaces with large unlearnable subspaces. Then, we introduce a novel formulation of IAC, called R-IAC, and show that its performances as an intrinsically motivated active learning algorithm are far superior to IAC in a complex sensorimotor space where only a small subspace is neither unlearnable nor trivial. We also show results in which the learnt forward model is reused in a control scheme.
Fichier principal
Vignette du fichier
BaranesOudeyerICDL09.pdf (896.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00438595 , version 1 (04-12-2009)

Identifiers

  • HAL Id : inria-00438595 , version 1

Cite

Adrien Baranes, Pierre-Yves Oudeyer. R-IAC : Robust Intrinsically Motivated Active Learning. International Conference on Development and Learning 2009, Jun 2009, Shanghai, China. ⟨inria-00438595⟩
59 View
157 Download

Share

Gmail Facebook X LinkedIn More