Ir al contenido

Documat


Studying How Innate Motivations Can Drive Skill Acquisition in Cognitive Robots

    1. [1] Universidade da Coruña

      Universidade da Coruña

      A Coruña, España

  • Localización: XoveTIC 2019: The 2nd XoveTIC Conference (XoveTIC 2019), A Coruña, Spain, 5–6 September / Alberto Alvarellos González (ed. lit.), Joaquim de Moura (ed. lit.), Beatriz Botana Barreiro (ed. lit.), Javier Pereira-Loureiro (ed. lit.) Árbol académico, Manuel Francisco González Penedo (ed. lit.) Árbol académico, 2019, ISBN 978-3-03921-444-0
  • Idioma: inglés
  • Enlaces
  • Resumen
    • In this paper, we address the problem of how to bootstrap a cognitive architecture to opportunistically start learning skills in domains where multiple skills can be learned at the same time. To this end, taking inspiration from a series of computational models of the use of motivations in infants, we propose an approach that leverages two types of cognitive motivations: exploratory and proficiency based, the latter modulated by the concept of interestingness as an implementation of attentional mechanisms. This approach is tested in an illustrative experiment with a real robot.


Fundación Dialnet

Mi Documat

Opciones de artículo

Opciones de compartir

Opciones de entorno