Back to Search Start Over

Evolution of Neural Controllers with Adaptive Synapses and Compact Genetic Encoding

Authors :
Dario Floreano
J. Urzelai
Source :
Advances in Artificial Life ISBN: 9783540664529, ECAL
Publication Year :
1999
Publisher :
Springer Berlin Heidelberg, 1999.

Abstract

This paper is concerned with artificial evolution of neurocontrollers with adaptive synapses for autonomous mobile robots. The method consists of encoding on the genotype a set of local modification rules that synapses obey while the robot freely moves in the environment [2]. The synaptic weights are not encoded on the genotype. In the experiments presented here, a "behavior-based fitness" function gives reproductive advantage to robots that can solve a sequential task. The results show that evolutionary adaptive controllers solve the task much faster and better than evolutionary standard (non-adaptive) controllers, that the method scales up well to large architectures whereas standard controllers do not, and that evolved adaptive controllers are not trivial and cannot be reduced to a fixed-weight network.

Details

ISBN :
978-3-540-66452-9
ISBNs :
9783540664529
Database :
OpenAIRE
Journal :
Advances in Artificial Life ISBN: 9783540664529, ECAL
Accession number :
edsair.doi...........d9c9259a3023052a4a9238c87f783c8a
Full Text :
https://doi.org/10.1007/3-540-48304-7_25