Towards increasing learning speed and robustness of XCSF: experimenting with larger offspring set sizes

Authors:
Patrick Stalph;Martin V. Butz
Affiliations:
University of Würzburg, Würzburg, Germany;University of Würzburg, Würzburg, Germany
Venue:
Proceedings of the 10th annual conference companion on Genetic and evolutionary computation
Year:
2008

Citing 11
Cited 0

Classifiers that approximate functions

Natural Computing: an international journal
Properties of the Bucket Brigade

Proceedings of the 1st International Conference on Genetic Algorithms
Analysis and improvement of fitness exploitation in XCS: bounding models, tournament selection, and bilateral accuracy

Evolutionary Computation
Hyper-ellipsoidal conditions in XCS: rotation, linear approximation, and solution structure

Proceedings of the 8th annual conference on Genetic and evolutionary computation
Prediction update algorithms for XCSF: RLS, Kalman filter, and gain adaptation

Proceedings of the 8th annual conference on Genetic and evolutionary computation
Bounding XCS's parameters for unbalanced datasets

Proceedings of the 8th annual conference on Genetic and evolutionary computation
Problem solution sustenance in XCS: Markov chain analysis of niche support distributions and the impact on computational complexity

Genetic Programming and Evolvable Machines
A formal framework and extensions for function approximation in learning classifier systems

Machine Learning
Classifier fitness based on accuracy

Evolutionary Computation
Toward a theory of generalization and learning in XCS

IEEE Transactions on Evolutionary Computation
Function Approximation With XCS: Hyperellipsoidal Conditions, Recursive Least Squares, and Compaction

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The XCS classifier system has been successfully applied to various problem domains including datamining, boolean classifications, and function approximation. In all these applications just two classifiers were reproduced in a match or action set, given a time-recency threshold was met in the set. In this paper, we investigate the effect of selecting more than two classifiers for reproduction in XCSF. We either increase the number of selected classifiers or select a number of classifiers relative to the current match set size. In the functions investigated, both approaches showed a highly significant increase in initial learning speed. Also, in less challenging approximation tasks, the final accuracy reached is not affected by the approach. However, in harder functions, learning may stall due to over-reproductions of inaccurate, ill-estimated classifiers. Thus, we propose an adaptive offspring size rate that may depend on the current reliability of classifier parameter estimates. First results with a fixed offspring set size decrement show promising results. Future work is needed to speed-up XCS's learning progress and adjust its learning speed to the perceived problem difficulty.