Machine Learning

, Volume 9, Issue 1, pp 9–21 | Cite as

Dynamic Parameter Encoding for Genetic Algorithms

  • Nicol N. Schraudolph
  • Richard K. Belew


The common use of static binary place-value codes for real-valued parameters of the phenotype in Holland's genetic algorithm (GA) forces either the sacrifice of representational precision for efficiency of search or vice versa. Dynamic Parameter Encoding (DPE) is a mechanism that avoids this dilemma by using convergence statistics derived from the GA population to adaptively control the mapping from fixed-length binary genes to real values. DPE is shown to be empirically effective and amenable to analysis; we explore the problem of premature convergence in GAs through two convergence models.

Adaptive encoding real-valued parameters ARGOT premature convergence genetic hitchhiking 


  1. Caruana, R.A. & Schaffer, J.D. (1988). Representation and hidden bias: Gray vs. binary coding for geneticalgorithms. In Proceedings of the Fifth International Conference on Machine Learning (pp. 153–161).San Mateo,CA: Morgan Kaufmann.Google Scholar
  2. De Jong, K.A. (1975). An analysis of the behavior of a class of genetic adaptive systems. Ph.D. thesis,Department of Computer and Communication Sciences,University of Michigan, Ann Arbor, MI. University MicrofilmsNo. 76-9381.Google Scholar
  3. Deb, K. (1991). Binary and floating point optimization using messy genetic algorithms (TechnicalReport 91004(dissertation)). Tuscaloosa, AL: University of Alabama, The Clearinghouse for Genetic Algorithms.Google Scholar
  4. Goldberg, D.E. (1989). Genetic algorithms in search, optimization & machine learning. Reading,MA: Addison-Wesley.Google Scholar
  5. Grefenstette, J.J. (1984). A user's guide to GENESIS (Technical Report CS-84-11).Nashville, TN: VanderbiltUniversity.Google Scholar
  6. Hart, W.E. & Belew, R.K. (1991). Optimizing an arbitrary function is hard for the genetic algorithm. In R.K. Belew & L.B. Booker, (eds.) Proceedings of the Fourth International Conference on GeneticAlgorithms (pp.190–195). San Mateo, CA: Morgan Kaufmann.Google Scholar
  7. Holland, J.H. (1975). Adaptation in natural and artificial systems. Ann Arbor, MI: The University ofMichigan Press.Google Scholar
  8. Mandava, V.R., Fitzpatrick, J. M., & Pickens, III, D.R. (1989). Adaptive search space scaling in digitalimageregistration. IEEE Transactions on Medical Imaging, 8, pp. 251–262.Google Scholar
  9. Schaffer, J.D., Caruana, R.A., Eshelman, L. J., & Das, R. (1989). A study of control parameters affectingonlineperformance of genetic algorithms for function optimization. In J.D. Schaffer, (ed.) Proceedings of theThirdInternational Conference on Genetic Algorithms (pp. 51–60). San Mateo, CA: Morgan Kaufmann.Google Scholar
  10. Schwefel, H.P. (1981). Numerical optimization of computer models. Chichester: Wiley.Google Scholar
  11. Shaefer, C.G. (1987). The ARGOT strategy: Adaptive representation genetic optimizer technique. In J.J. Grefenstette,(ed.), Genetic algorithms and their applications: Proceedings of the Second International Conference (pp.50–58).Hillsdale, NJ: Lawrence Erlbaum Associates.Google Scholar
  12. Whitley, D., Mathias, K., & Fitzhorn, P. (1991). Delta coding: An iterative search strategy for geneticalgorithms.In R.K. Belew & L.B. Booker, (eds.) Proceedings of the Fourth International Conference on GeneticAlgorithms(pp. 77–84). San Mateo, CA: Morgan Kaufmann.Google Scholar

Copyright information

© Kluwer Academic Publishers 1992

Authors and Affiliations

  • Nicol N. Schraudolph
    • 1
  • Richard K. Belew
    • 1
  1. 1.Computer Science & Engineering DepartmentUniversity of CaliforniaSan Diego, La Jolla

Personalised recommendations