Is a self-adaptive Pareto approach beneficial for controlling embodied virtual robots?

Authors:
Jason Teo;Hussein A. Abbass
Affiliations:
Artificial Life and Adaptive Robotics Lab, School of Computer Science, University of New South Wales, Canberra, Australia;Artificial Life and Adaptive Robotics Lab, School of Computer Science, University of New South Wales, Canberra, Australia
Venue:
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII
Year:
2003

Citing 1
Cited 0

Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600)

CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02

Quantified Score

Hi-index	0.00

Visualization

Abstract

A self-adaptive Pareto Evolutionary Multi-objective Optimization (EMO) algorithm is proposed for evolving controllers for a virtually embodied robot. The main contribution of the self-adaptive Pareto approach is its ability to produce controllers with different locomotion capabilities in a single run, therefore reducing the evolutionary computational cost significantly. The aim of this paper is to verify this hypothesis.