Analyzing parameter sensitivity and classifier representations for real-valued XCS

Authors:
Atsushi Wada;Keiki Takadama;Katsunori Shimohara;Osamu Katai
Affiliations:
ATR Human Information Science Laboratories, Kyoto, Japan and Kyoto University, Graduate School of Informatics, Kyoto, Japan;ATR Human Information Science Laboratories, Kyoto, Japan and Tokyo Institute of Technology, Interdisciplinary Graduate School of Science and Engineering, Yokohama, Kanagawa, Japan;ATR Human Information Science Laboratories, Kyoto, Japan and Kyoto University, Graduate School of Informatics, Kyoto, Japan;Kyoto University, Graduate School of Informatics, Kyoto, Japan
Venue:
IWLCS'03-05 Proceedings of the 2003-2005 international conference on Learning classifier systems
Year:
2007

Citing 3
Cited 1

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
For real! XCS with continuous-valued inputs

Evolutionary Computation
Classifier fitness based on accuracy

Evolutionary Computation

Intrusion detection with evolutionary learning classifier systems

Natural Computing: an international journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

To evaluate a real-valued XCS classifier system, we present a validation of Wilson's XCSR from two points of view. These are: (1) sensitivity of real-valued XCS specific parameters on performance and (2) the design of classifier representation with classifier operators such as mutation and covering. We also propose model with another classifier representation (LU-Model) to compare it with a model with the original XCSR classifier representation (CS-Model.) We did comprehensive experiments by applying a 6-dimensional real-valued multiplexor problem to both models. This revealed the following: (1) there are critical threshold on covering operation parameter (r0), which must be considered in setting parameters to avoid serious decreases in performance; and (2) the LU-Model has an advantage in smaller classifier population size within the same performance level over the CS-Model, which reveals the superiority of alternative classifier representation for real-valued XCS.