Applying XCSR to Design-Oriented Environments
David F. Wyatt, Larry Bull, Ian C. Parmee · UWE Research Repository (UWE Bristol) · 2004
Learning classifier systems have previously been shown to have some application in single-step tasks with the generic features typically found in problems addressed by an Interactive Evolutionary Design process. This paper extends work in the area by applying the classifier system to progressively more complex multi-modal test environments. Analysis of the XCSR classifier system is made with respect to feature sampling, parameter sensitivity, training set size and rule subsumption. Results show that XCSR is able to deduce the characteristics of such problem spaces to a suitable level of accuracy.