Strength or Accuracy? Fitness Calculation in Learning Classifier Systems

Tim Kovacs, Lanzi P. L., Stolzmann W., Wilson S. W.

Research output: Chapter in Book/Report/Conference proceedingChapter in a book

Abstract

Wilson's XCS is a clear departure from earlier classifier systems in terms of the way it calculates the fitness of classifiers for use in the genetic algorithm. Despite the growing body of work on XCS and the advantages claimed for it there has been no detailed comparison of XCS and traditional strength-based systems. This work takes a step towards rectifying this situation by surveying a number of issues related to the change in fitness. I distinguish different definitions of overgenerality for strength and accuracy-based fitness and analyse some implications of the use of accuracy, including an apparent advantage in addressing the explore/exploit problem. I analyse the formation of strong overgenerals, a major problem for strength-based systems, and illustrate their dependence on biased reward functions. I consider motivations for biasing reward functions in single step environments, and show that non-trivial multi step environments have biased Q-functions. I conclude that XCS's accuracy-based fitness appears to have a number of significant advantages over traditional strength-based fitness. [For a revised version please see the chapter in "Strength or Accuracy: Credit Assignment in Learning Classifier Systems" PhD Thesis, 2002. School of Computer Science. University of Birmingham. Birmingham, U.K. http://www.cs.bris.ac.uk/~kovacs/author.directory/thesis/thesis.html]
Translated title of the contributionStrength or Accuracy? Fitness Calculation in Learning Classifier Systems
Original languageEnglish
Title of host publicationLearning Classifier Systems. From Foundations to Applications
PublisherSpringer
Volume1813
Publication statusPublished - 2000

Bibliographical note

Other page information: 143-160
Other identifier: 1000541

Fingerprint Dive into the research topics of 'Strength or Accuracy? Fitness Calculation in Learning Classifier Systems'. Together they form a unique fingerprint.

Cite this