The Royal Road functions: description, intent and experimentation

  • R. J. Quick
  • V. J. Rayward-Smith
  • G. D. Smith
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1143)

Abstract

This paper describes an analysis of a set of experiments on the Royal Road functions, aimed at developing a GA that was robust for a set of such functions. The Royal Road functions were designed to be easy for Genetic Algorithms to solve and it was expected that other techniques would have difficulty in finding good solutions. However, it is discovered that a simple thresholding algorithm was able to produce comparable results on the basic Royal Road function and remained robust when applied to variations of the function. The GA required modification to compete on some variations and suffered severe performance deterioration on others.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dan Adler. Genetic algorithms and simulated annealing: A marriage proposal. In IEEL International conference on neural networks, 1993.Google Scholar
  2. 2.
    J.F Dockx, K. Lutsko. Survival of the fittest in Alaska. In The Fourth International Workshop Artificial Intelligence and Statistics. Fort Lauderdale, 1993.Google Scholar
  3. 3.
    Kathryn A. Dowsland. Simulated annealing. In Modern Heuristic Techniques for Combinatorial Problems. Blackwell Scientific Publications, 1993.Google Scholar
  4. 4.
    Gunter Dueck and Tobias Scheuer. Threshold accepting: A general purpose optimization algorithm appearing superior to simulated annealing. In Journal of Computational Physics, 1989.Google Scholar
  5. 5.
    Stephanie Forrest and Melanie Mitchell. Relative building-block fitness and the building-block hypothesis. In Foundations of Genetic Algorithms-2. Fort Lauderdale, 1993.Google Scholar
  6. 6.
    David E. Goldburg. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Publishing Company, Inc., 1989.Google Scholar
  7. 7.
    David E. Goldburg. A note on boltzmann tournament selection for genetic algorithms and population-oriented simulated annealing. In Complex Systems, 1990.Google Scholar
  8. 8.
    John J. Grefenstette. Deception considered harmful. In Foundations of Genetic Algorithms-2. Morgan Kaufmann, 1993.Google Scholar
  9. 9.
    John H. Holland. Royal road functions. In Internet Genetic Algorithms Digest, 7∶22. Massachusetts Insitue of Technology, 1993.Google Scholar
  10. 10.
    Melanie Mitchell John H. Holland and Stephanie Forrest. The royal road for genetic algorithms: Fitness landscapes and G.A. performance. In Proceedings of the First European Conference on Artificial Life. Massachusetts Insitue of Technology, 1992.Google Scholar
  11. 11.
    Terry Jones. A description of Hollands's Royal Road function. Massachusetts Institute of Technology, 1995.Google Scholar
  12. 12.
    John H. Holland Melanie Mitchell and Stephanie Forrest. When will a genetic algorithm outperform hill climbing ? In Advances in Neural Information Processing Systems 6. Morgan Kaufmann, 1993.Google Scholar
  13. 13.
    George D. Smith. Economic applications of genetic algorithms. In Applications of Modern Heuristic Methods, edited V.J. Rayward-Smith, Alfred Waller, 1995.Google Scholar

Copyright information

© Springer-Verlag 1996

Authors and Affiliations

  • R. J. Quick
    • 1
  • V. J. Rayward-Smith
    • 1
  • G. D. Smith
    • 1
  1. 1.University of East AngliaNorwichUK

Personalised recommendations