Avoiding the pitfalls of noisy fitness functions with genetic algorithms

Fiacc Larkin, Conor Ryan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We have examined the application of genetic Algorithms to noisy fitness functions and consider the accepted wisdom of sampling, or multiple evaluations of individuals, as a mechanism for identifying true performance. Given a large (> 10%) amount of noise, a standard GA of surprisingly modest population size outperforms a GA using sampling, when compared on fitness versus evaluations. We also document a detrimental phenomenon we term the Glass Ceiling, which is when individuals of high fitness become confused with individuals of perfect fitness by the GA. We pinpoint the precise conditions that create this effect.

Original languageEnglish
Title of host publicationProceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Pages1861-1862
Number of pages2
DOIs
Publication statusPublished - 2009
Event11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009 - Montreal, QC, Canada
Duration: 8 Jul 200912 Jul 2009

Publication series

NameProceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009

Conference

Conference11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Country/TerritoryCanada
CityMontreal, QC
Period8/07/0912/07/09

Keywords

  • Clones
  • Genetic algorithms
  • Noisy fitness functions
  • Performance
  • The glass ceiling

Fingerprint

Dive into the research topics of 'Avoiding the pitfalls of noisy fitness functions with genetic algorithms'. Together they form a unique fingerprint.

Cite this