Adaptation of Length in a Nonstationary Environment

Han Yu¹, Annie S. Wu¹, Kuo-Chi Lin², and Guy Schiavone²

¹School of EECS
University of Central Florida
P.O. Box 162362
Orlando, FL 32816-2362
{hyu,aswu}@cs.ucf.edu

²Institute for Simulation and Training
University of Central Florida
Orlando, FL 32826-0544
{klin,guy}@pegasus.cc.ucf.edu

Abstract. In this paper, we examine the behavior of a variable length GA in a nonstationary problem environment. Results indicate that a variable length GA is better able to adapt to changes than a fixed length GA. Closer examination of the evolutionary dynamics reveals that a variable length GA can in fact take advantage of its variable length representation to exploit good quality building blocks after a change in the problem environment.

LNCS 2724, p. 1541 ff.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003