Using habituation as a simple and fundamental learning mechanism in an embodied artificial agent - Department of Complex Systems, Artificial Intelligence  & Robotics Accéder directement au contenu
Article Dans Une Revue Adaptive Behavior Année : 2023

Using habituation as a simple and fundamental learning mechanism in an embodied artificial agent

Résumé

Habituation, a non-associative learning widely observed across phylogeny, is fundamental for adaptation and, thus, survival of living organisms. This paper investigates the main characteristics of habituation in order to present three new computational models inspired by habituation. We develop these models as part of the Iterant Deformable Sensorimotor Medium (IDSM), a recently developed abstract model of behavior formation. The characteristics of these models are studied and analyzed. Our long-term objective is to research new unsupervised learning mechanisms for artificial learning agents.
Fichier principal
Vignette du fichier
IDSM_with_habituation_AB22.pdf (10.94 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04031614 , version 1 (16-03-2023)

Identifiants

Citer

Tristan Gillard, Jérémy Fix, Alain Dutech. Using habituation as a simple and fundamental learning mechanism in an embodied artificial agent. Adaptive Behavior, In press, 31 (4), pp.299-321. ⟨10.1177/10597123221116183⟩. ⟨hal-04031614⟩
25 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More