Speciation as automatic categorical modularization


Research output: Journal PublicationsJournal Article (refereed)peer-review

76 Citations (Scopus)


Real-world problems are often too difficult to be solved by a single monolithic system. Many natural and artificial systems use a modular approach to reduce the complexity of a set of subtasks while solving the overall problem satisfactorily. There are two distinct ways to do this. In functional modularization, the components perform very different tasks, such as subroutines of a large software project. In categorical modularization, the components perform different versions of basically the same task, such as antibodies in the immune system. This second aspect is the more natural for acquiring strategies in games of conflict. An evolutionary learning system is presented which follows this second approach to automatically create a repertoire of specialist strategies for a game-playing system. This relieves the human effort of deciding how to divide and specialize: species automatically form to deal with different high-quality potential opponents, and a gating algorithm manages the repertoire thus created. The genetic algorithm speciation method used is one based on fitness sharing. The learning task is to play the iterated prisoner's dilemma. The learning system outperforms the Titfor-Tat strategy against unseen test opponents. It learns using a "black box" simulation, with minimal prior knowledge of the learning task. © 1997 IEEE.
Original languageEnglish
Pages (from-to)101-108
Number of pages8
JournalIEEE Transactions on Evolutionary Computation
Issue number2
Publication statusPublished - Jul 1997
Externally publishedYes

Bibliographical note

This work was supported in part by a University College Postgraduate Research Scholarship (for P. J. Darwen) and by an Australian Research Council’s Small Grant. This paper was presented in part at the 1996 IEEE International Conference on Evolutionary Computation (ICEC’96), Nagoya, Japan, May 1996.


  • Categorical modularization
  • Co-evolution
  • Evolutionary learning
  • Implicit fitness sharing
  • Iterated prisoner's dilemma
  • Niching, speciation
  • Tit-for-tat


Dive into the research topics of 'Speciation as automatic categorical modularization'. Together they form a unique fingerprint.

Cite this