An Evolutionary Function Approximation Approach to Compute Prediction in XCSF

@inproceedings{Hamzeh2005AnEF,
  title={An Evolutionary Function Approximation Approach to Compute Prediction in XCSF},
  author={A. Hamzeh and A. Rahmani},
  booktitle={ECML},
  year={2005}
}
XCSF is a new extension to XCS that is developed to extend XCS's reward calculation capability via computing. This new feature is called computable prediction. The first version of XCSF tries to find the most appropriate equation to compute each classifier's reward using a weight update mechanism. In this paper, we try to propose a new evolutionary mechanism to compute these equations using genetic algorithms. 
9 Citations
Extending XCSFG beyond Linear Approximation
  • A. Hamzeh, A. Rahmani
  • Mathematics, Computer Science
  • 2006 IEEE International Conference on Evolutionary Computation
  • 2006
  • 4
A New Architecture of XCS to Approximate Real-Valued Functions Based on High Order Polynomials Using Variable-Length GA
  • A. Hamzeh, A. Rahmani
  • Mathematics, Computer Science
  • Third International Conference on Natural Computation (ICNC 2007)
  • 2007
  • 6
Learning classifier systems: a complete introduction, review, and roadmap
  • 223
  • PDF
2 Frog and Fly : A 1-D Continuous-action Problem
  • PDF
Three Architectures for Continuous Action
  • S. Wilson
  • Computer Science, Mathematics
  • IWLCS
  • 2005
  • 34
  • PDF

References

SHOWING 1-10 OF 13 REFERENCES
XCS with computed prediction in multistep environments
  • 26
  • PDF
Extending XCSF beyond linear approximation
  • 51
  • PDF
Tournament Selection: Stable Fitness Pressure in XCS
  • 53
  • PDF
Classifier Fitness Based on Accuracy
  • S. Wilson
  • Mathematics, Computer Science
  • Evolutionary Computation
  • 1995
  • 1,436
  • PDF
Classifiers that approximate functions
  • S. Wilson
  • Computer Science, Mathematics
  • Natural Computing
  • 2004
  • 180
  • Highly Influential
Function approximation with a classifier system
  • 105
  • Highly Influential
Classifier Systems for Continuous Payoff Environments
  • S. Wilson
  • Mathematics, Computer Science
  • GECCO
  • 2004
  • 34
Genetic and Evolutionary Computation — GECCO 2003
  • 890
Genetic and Evolutionary Computation – GECCO 2004
  • 378
An algorithmic description of XCS
  • 537
...
1
2
...