Evolvability of Neuromodulated Learning for Robots

Neuromodulation is thought to be one of the underlying principles of learning and memory in biological neural networks. Recent experiments have shown that neuroevolutionary methods benefit from neuromodulation in simple grid-world problems. In this paper we investigate the performance of a neuroevolutionary method applied to a more realistic robotic task. While confirming the favorable effect of neuromodulatory structures, our results indicate that the evolution of such architectures requires a mechanism which allows for selective modular targetting of the neuromodulatory connections.


Editeur(s):
El-Rayis, Ahmed O.
Stoica, Adrian
Tunstel, Eddie
Huntsberger, Terry
Arslan, Tughrul
Vijayakumar, Sethu
Publié dans:
Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, 41-46
Présenté à:
The 2008 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, Edinburgh, Scotland, August 6-8, 2008
Année
2008
Publisher:
Los Alamitos, CA, IEEE Computer Society
Mots-clefs:
Autres identifiants:
Laboratoires:




 Notice créée le 2008-06-18, modifiée le 2019-03-16

n/a:
Télécharger le documentPDF
Lien externe:
Télécharger le documentURL
Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)