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.


Editor(s):
El-Rayis, Ahmed O.
Stoica, Adrian
Tunstel, Eddie
Huntsberger, Terry
Arslan, Tughrul
Vijayakumar, Sethu
Published in:
Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, 41-46
Presented at:
The 2008 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, Edinburgh, Scotland, August 6-8, 2008
Year:
2008
Publisher:
Los Alamitos, CA, IEEE Computer Society
Keywords:
Other identifiers:
Laboratories:




 Record created 2008-06-18, last modified 2018-03-17

n/a:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)