 |
    |
Classifier Systems for Continuous Payoff Environments
Stewart W. Wilson
Prediction Dynamics, Concord MA 01742 USA, Department of General Engineering, The University of Illinois at Urbana-Champaign IL 61801 USAwilson@prediction-dynamics.com
Abstract. Recognizing that many payoff functions are continuous and depend on the input state x, the classifier system architecture XCS is extended so that a classifier’s prediction is a linear function of x. On a continuous nonlinear problem, the extended system, XCS-LP, exhibits high performance and low error, as well as dramatically smaller evolved populations compared with XCS. Linear predictions are seen as a new direction in the quest for powerful generalization in classifier systems.
LNCS 3103, p. 824 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004