Towards a Theory of Strong Overgeneral Classifiers

Tim Kovacs, Martin Worthy, Spears William

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


We analyse the concept of strong overgeneral rules, the Achilles' heel of traditional Michigan-style learning classifier systems, using both the traditional strength-based and newer accuracy-based approaches to rule fitness. We argue that different definitions of overgenerality are needed to match the goals of the two approaches, present minimal conditions and environments which will support strong overgeneral rules, demonstrate their dependence on the reward function, and give some indication of what kind of reward functions will avoid them. Finally, we distinguish fit overgeneral rules, show how strength and accuracy-based fitness differ in their response to fit overgenerals and conclude by considering possible extensions to this work. [This work has been subsumed by "Strength or Accuracy: Credit Assignment in Learning Classifier Systems" PhD Thesis, 2002. School of Computer Science. University of Birmingham. Birmingham, U.K.]
Translated title of the contributionTowards a Theory of Strong Overgeneral Classifiers
Original languageEnglish
Title of host publicationFoundations of Genetic Algorithms 6
PublisherMorgan Kaufmann
Publication statusPublished - 2001

Bibliographical note

Other page information: 165-184
Other identifier: 1000608


Dive into the research topics of 'Towards a Theory of Strong Overgeneral Classifiers'. Together they form a unique fingerprint.

Cite this