Classifier Conditions Using Gene Expression Programming

  • Authors:
  • Stewart W. Wilson

  • Affiliations:
  • Prediction Dynamics, Concord, USA 01742 and Department of Industrial and Enterprise Systems Engineering, The University of Illinois at Urbana-Champaign, USA IL 61801

  • Venue:
  • Learning Classifier Systems
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The classifier system XCSF was modified to use gene expression programming for the evolution and functioning of the classifier conditions. The aim was to fit environmental regularities better than is typically possible with conventional rectilinear conditions. An initial experiment approximating a nonlinear oblique environment showed excellent fit to the regularities.