Exploring Sensitization in the Context of Extending the Behavior of an Artificial Agent

Tristan Gillard (1) , Jérémy Fix (1, 2) , Alain Dutech (3)

1 BISCUIT - Bio-Inspired, Situated and Cellular Unconventional Information Technologies
2 CentraleSupélec [campus de Metz]
3 Inria - Institut National de Recherche en Informatique et en Automatique

Sensitization, a non-associative learning widely observed across phylogeny, is fundamental for adaptation and, thus, survival of living organisms. This paper investigates one form of sensitization, namely pseudo-conditioning, in order to present a new computational model inspired by its characteristics. We develop this model as part of the Iterant Deformable Sensorimotor Medium (IDSM), a recently developed abstract model of sensorimotor behavior formation. The characteristics of the presented model are studied and analyzed in the light of our long term objective of investigating new unsupervised learning mechanisms for artificial autonomous agents.

Mots clés: Non-associative Learning; Sensitization; Pseudo-conditioning; Artificial Agent; Adaptive Behavior Acquisition; Embodiement; Non-associative learning sensitization pseudo-conditioning artificial agent adaptive behavior acquisition embodiment; Non-associative learning; sensitization; pseudo-conditioning; artificial agent; adaptive behavior acquisition; embodiment

Domaines: Intelligence artificielle [cs.AI]

Tristan Gillard, Jérémy Fix, Alain Dutech. Exploring Sensitization in the Context of Extending the Behavior of an Artificial Agent. International Conference on Simulation of Adaptive Behavior (SAB22), Sep 2022, Cergy-Pontoise, France. pp.15-27, ⟨10.1007/978-3-031-16770-6_2⟩. ⟨hal-04031636⟩