3D Function Approximation with rGCS Classifier System
Łukasz Cielecki, Olgierd Unold · 2008
Extended Classifier Systems (XCS) introduced by Wilson became popular instrument used to solve many real-world problems possible to express with ternary representation. Our new model of real-valued LCS – the rGCS – is designed to classify real valued data. rGCS is based on Grammar-based Classifier System (GCS), which was originally used to process context free grammar sentences. To improve 3D function approximation a covering technique was developed. This procedure replenishes the population of system classifiers with new ones created on the fly to satisfy current state of grammar evolution. As a result there is no need to employ a genetic algorithm.