Analysis of stagnation behaviour of competitive coevolutionary trained neuro-controllers

Abstract

A new variant of the competitive coevolutionary team-based particle swarm optimiser (CCPSO(t)) algorithm is developed to train multi-agent teams from zero knowledge. Analysis show that the CCPSO algorithm stagnates during the training of simple soccer players. It is hypothesised that the stagnation is caused by saturation of the neural network weights. The… (More)
DOI: 10.1109/SIS.2014.7011795

Topics

8 Figures and Tables

Cite this paper

@article{Scheepers2014AnalysisOS, title={Analysis of stagnation behaviour of competitive coevolutionary trained neuro-controllers}, author={Christiaan Scheepers and Andries Petrus Engelbrecht}, journal={2014 IEEE Symposium on Swarm Intelligence}, year={2014}, pages={1-8} }