JavaXCSF: the XCSF learning classifier system in Java

@article{Stalph2010JavaXCSFTX,
  title={JavaXCSF: the XCSF learning classifier system in Java},
  author={Patrick O. Stalph and Martin Volker Butz},
  journal={ACM Sigevolution},
  year={2010},
  volume={4},
  pages={16-19}
}
Learning Classifier Systems were introduced by John H. Holland and constituted one of the first genetics-based machine learning techniques. The most prominent Learning Classifier System is XCS [3]. XCS can also be used for function approximation, then called XCSF [4]. JavaXCSF is an implementation of the XCSF Learning Classifier System. It is freely available from www.coboslab.psychologie.uni-wuerzburg.de/code/ Based on previous implementations, the code was extended and heavily restructured… 

Figures from this paper

References

SHOWING 1-5 OF 5 REFERENCES
Classifier Fitness Based on Accuracy
TLDR
A classifier system, XCS, is investigated, in which each classifier maintains a prediction of expected payoff, but the classifier's fitness is given by a measure of the prediction's accuracy, making it suitable for a wide range of reinforcement learning situations where generalization over states is desirable.
Classifiers that approximate functions
A classifier system, XCSF, is introduced in which the predictionestimation mechanism is used to learn approximations to functions.The addition of weight vectors to the classifiers
Function Approximation With XCS: Hyperellipsoidal Conditions, Recursive Least Squares, and Compaction
TLDR
Performance comparisons with other, heuristic function approximation techniques show that XCSF yields competitive or even superior noise-robust performance, and a novel closest classifier matching mechanism for the efficient compaction of XCS's final problem solution.
Documentation of JavaXCSF
  • Documentation of JavaXCSF
  • 2009
Documentation of JavaXCSF. Technical Report Y2009N001, COBOSLAB, Department of Psychology III, University of Würzburg, Röntgenring
  • 2009