Constraining the Size Growth of the Task Space with Socially Guided Intrinsic Motivation using Demonstrations. - Archive ouverte HAL Access content directly
Conference Papers Year :

Constraining the Size Growth of the Task Space with Socially Guided Intrinsic Motivation using Demonstrations.

Abstract

This paper presents an algorithm for learning a highly redundant inverse model in continuous and non-preset environments. Our Socially Guided Intrinsic Motivation by Demonstrations (SGIM-D) algorithm combines the advantages of both social learning and intrinsic motivation, to specialise in a wide range of skills, while lessening its dependence on the teacher. SGIM-D is evaluated on a fishing skill learning experiment.
Fichier principal
Vignette du fichier
ijcai11Nguyen.pdf (1.52 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00645995 , version 1 (29-11-2011)

Identifiers

Cite

Sao Mai Nguyen, Adrien Baranes, Pierre-Yves Oudeyer. Constraining the Size Growth of the Task Space with Socially Guided Intrinsic Motivation using Demonstrations.. IJCAI Workshop on Agents Learning Interactively from Human Teachers (ALIHT), 2011, Barcelona, Spain. ⟨hal-00645995⟩
176 View
72 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More