Coevolutionary Dynamics of a Multi-Population Genetic Programming System (1999) [2 citations — 1 self]
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
author = {Josh C. Bongard},
title = {Coevolutionary Dynamics of a Multi-Population Genetic Programming System},
booktitle = {Proceedings of the 5th European Conference on Advances in Artificial Life, volume 1674 of LNAI},
year = {1999},
pages = {154--158},
publisher = {Springer}
}
Bookmarks
OpenURL
Abstract:
. This report presents an asynchronous, distributed genetic programming (GP) system using a master/slave architecture. Using symbolic regression for fourier functions as the problem domain, the system was found to demonstrate cooperative coevolutionary dynamics when multiple client populations evolve solutions to similar, but different problems: specifically, closely coupled populations were found to promote continuous search, which in some cases leads to the discovery of better solutions. 1 Introduction The abilities of various evolutionary algorithms to traverse large search spaces have been well documented[5][7], as well as their amenability to parallel implementation [3]. Much work has investigated various parallel architectures that partition, or otherwise reorganize a single problem[4][8][11]: focus is placed on the dispersion and synthesis of partial solutions, often referred to as building blocks or schemas. However, there is little investigation of parallel algorithm...
