Abstract
This article investigates the of applicability of adding evolvability promoting mechanisms to a genetic algorithm to enhance its ability to handle perpetually novel dynamic environments, especially one that has stationary periods allowing the Genetic Algorithm (GA) to converge on a temporary global optimum. We utilize both biological and evolutionary computation (EC) definitions of evolvability to create two measures: one based on the improvements in fitness; the other based on the amount of genotypic change. These two evolvability measures are used alongside fitness to modify how selection proceeds in the GA. We call this modified GA the Estimation of Evolvability Genetic Algorithm (EEGA). When tested against a regular GA (with random immigrants), the EEGA is able to track the global optimum more closely than the GA during the dynamic period. Unlike most GA extensions, the EEGA works effectively at a lower level of diversity than does the GA, showing that it is the quality of the diverse members in the population and not just the quantity that helps the GA evolve.
Similar content being viewed by others
Notes
The emphasis on diversity alone, while common, is not universal. Moving beyond the GA world, the idea of targeting diversity and evolving step-sizes is common in Evolutionary Strategies [8].
Premature convergence is said to occur when a population becomes dominated by individuals with relatively poor fitness, but where the population shows no sign of moving to a more highly fit area of the search space.
Based on the dynamic performance of the GA, the relationship between selection effect and innovation effect is not always positive in an evolutionary process, however, the optimal relationship should be positive, which implies good fitness and a healthy gene pool.
Of course Price's equation has been used for other purposes in EC, for example see [4].
Non-parametric statistics were used, e.g. percentiles instead of averages and standard deviations, as the results were not normally distributed.
References
L. Altenberg, “The evolution of evolvability in genetic programming,” in Advances in Genetic Programming, K. Kinnear (ed.), MIT Press: Cambridge, 1994, pp. 47–74.
E. S. Andersen, “Population thinking, Price's equation and the analysis of economic evolution,” Evolutionary and Institutional Economics Review, in press.
T. Bäck, “Optimal mutation rates in genetic search,” in Proceedings of the Fifth International Conference on Genetic Algorithms, S. Forrest (ed.), Morgan Kaufmann: San Mateo, 1993, pp. 2–8.
J. K. Bassett, M. A. Potter, and K. A. De Jong, “Looking under the EA Hood with Price's equation,” in Proceeding of the Genetic and Evolutionary Computation Conference (GECCO 2004), Springer: Berlin, 2004, vol. 1, pp. 914–922.
M. A. Bedau and N. H. Packard, “Measurement of evolutionary activity, teleology, and life,” in Artificial Life II, C. G. Langton, C. Taylor, J. D. Farmer, and S. Rasmussen (eds.), Addison-Wesley: Reading, MA, 1992, pp. 431–461.
M. A. Bedau, “Quantifying the extent and intensity of adaptive evolution,” in Proceedings of 1999 Genetic and Evolutionary Computation Conference Workshop Program, A. Wu (ed.), Morgan Kaufmann: San Fransisco, 1999, pp. 34–37.
H.-G. Beyer, “How GAs do NOT work—Understanding GAs without schemata and building blocks,” Technical Report of the Systems Analysis Research Group SYS-2/95, University of Dortmund, Department of Computer Science, April 1995.
H.-G. Beyer, in The Theory of Evolution Strategies, Springer: Berlin, 2001.
J. Branke, Evolutionary Optimization in Dynamic Environments, Kluwer Academic Publishers: Boston, 2001.
L. Cavalli-Sforza and M. Feldman, “Evolution of continuous variation: Direct approach through joint distribution of genotypes and phenotypes,” in Proc. Natl. Acad. Sci. USA, vol. 73, pp. 1689–1692, 1976.
J. Chen and M. Wineberg, “Enhancement of the shifting balance genetic algorithm for highly multimodal problems,” in Proceedings of the Congress on Evolutionary Computation 2004 (CEC 2004), G. W. Greenwood et al. (eds.), IEEE Press: NJ, 2004, pp. 744–751.
N. L. Chrystopher, “Measuring evolvability as the rate of complexity increase,” in Artificial Life VII Workshop Proceedings, C. C. Maley and E. Boudreau (eds.), 2000, pp. 55–57.
H. G. Cobb and J. J. Grefenstette, “Genetic algorithms for tracking changing environments,” in Proceeding of the Fifth International Conference on Genetic Algorithms, S. Forrest (ed.), Morgan Kaufmann: San Mateo, CA, 1993, pp. 523–530.
C. A. Coello Coello, “An updated survey of evolutionary multiobjective optimization techniques: State of the art and future trends,” in Proceedings of the Congress on Evolutionary Computation (CEC 99), P. J. Angeline (ed.), IEEE Press: Piscataway, NJ, 1999, vol. 1, pp. 3–9.
C. A. Coello Coello, “A comprehensive survey of evolutionary-based multiobjective optimization techniques,” Knowledge and Information Systems, vol. 1, pp. 269–308, 1999.
R. Dawkins, in The Blind Watchmaker: Why the Evidence of Evolution Reveals a Universe Without Design, W.W. Norton and Co: New York, 1986.
R. Dawkins, Climbing Mount Improbable, W.W. Norton and Co: New York, 1996.
K. A. De Jong, “An analysis of the behavior of a class of genetic adaptive systems,” Doctoral dissertation, University of Michigan, Dissertation Abstracts International, vol. 36, 5140B. (University Microfilms No. 76-9381), 1975.
D. J. Earl and M. W. Deem, “Evolvability is a selectable trait,” in Proceedings of the National Academy of Sciences USA, vol. 101, pp. 11531–11536, 2004.
S. Frank, “George Price's contributions to evolutionary genetics,” Journal of Theoretical Biology, vol. 175, pp. 373–388, 1995.
T. Fogarty, “Varying the probability of mutation in the genetic algorithm,” in P roceedings of the Third International Conference on Genetic Algorithms, J. Schaffer (ed.), Morgan Kaufmann Publishers: San Mateo, 1989, pp. 104–109.
S. Forrest and M. Mitchell, “Relative building-block fitness and the building block hypothesis,” in Foundations of Genetic Algorithms 2, Morgan Kaufmann: San Mateo, CA, 1993.
A. Fukunaga, “Restart scheduling for genetic algorithms,” in Proceedings of 5th International Conference on Parallel Problem Solving from Nature (PPSN-V), Springer: Berlin, 1998, pp. 357–366.
F. Ghannadian, C. Alford, and R. Schonkwiler, “Application of random restart to genetic algorithms,” Information Sciences, vol. 95, pp. 81–102, 1996.
M. Glickman and K. Sycara, “Evolvability and static vs. dynamic fitness,” in Workshop Proceedings of Artificial Life VII, C. C. Maley (ed.), 2000.
J. J. Grefenstette, “Evolvability in dynamic fitness landscapes: A genetic algorithm approach,” in Proceeding of the Congress on Evolutionary Computation (CEC 1999), P. J. Angeline (ed.), IEEE: Piscataway, NJ, 1999.
D. E. Goldberg and J. Richardson, “Genetic algorithms with sharing for multimodal function optimization,” in Proceedings of the Second International Conference on Genetic Algorithms, J. J. Grefenstette (ed.), Lawrence Erlbaum Associates: Hillsdale, NJ, 1987, pp. 41–49.
D. E. Goldberg, in The Design of Innovation: Lessons from and for Competent Genetic Algorithms, Kluwer Academic: Boston, MA, 2002.
W. D. Hamilton, in Narrow Roads of Gene Land, The Collected Papers of W.D. Hamilton, W. H. Freeman: Oxford, 1998, vol. 1, p. 263.
G. R. Harik and D. E. Goldberg, “Learning linkage,” in Foundations of Genetic Algorithms 4, Morgan Kaufmann: San Francisco, CA, 1996, pp. 247–262.
J. H. Holland, in Adaptation in Natural and Artificial Systems, University of Michigan Press, Ann Arbor, MI, 1975.
J. H. Holland, “Building blocks, cohort genetic algorithms, and hyperplane-defined functions,” Evolutionary Computation, vol. 8, pp. 373–391, 2000.
M. Hollander and D. A. Wolfe, in Nonparametric Statistical Methods, John Wiley & Sons, New York, 1973.
T. Jones and S. Forrest, “Fitness distance correlation as a measure of problem difficulty for genetic algorithms,” in Proceedings of the Sixth International Conference on Genetic Algorithms, L. Eshelmann (ed.), Morgan Kaufmann: San Mateo, CA, 1995, pp. 184–192.
M. Kirschner and J. Gerhart, “Evolvability,” in Proceedings of the National Academy of Sciences of the USA, vol. 95, pp. 8420–8427, 1998.
T. Knudsen, “General selection theory and economic evolution: The Price equation and the replicator/interactor distinction,” Journal of Economic Methodology, vol. 11, pp. 147–173, 2004.
S. J. Louis and G. J. E. Rawlins, “Syntactic analysis of convergence in genetic algorithms,” in Foundations of Genetic Algorithm 2, L. D. Whitley (ed.), Morgan Kaufmann: San Mateo, CA, 1993, pp. 141–151.
S. W. Mahfoud, “Crowding and preselection revisited,” in Proc Parallel Problem Solving from Nature (PPSN 2), 1992, pp. 27–36.
O. J. Mengshoel and D. E. Goldberg, “Probabilistic crowding: Deterministic crowding with probabilistic replacement,” in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-99), W. Banzhaf et al. (eds.), Morgan Kaufmann: San Francisco, 1999, pp. 409–416.
R. W. Morrison and K. A. De Jong, “Measurement of population diversity,” in Artificial Evolution, P. Collet, C. Fonlupt, J-K Hao, E. Lutton, and M. Schoenauer (eds.), pp. 31–41, 2002.
B. Naudts and L. Kallel, “A comparison of predictive measures of problem difficulty in evolutionary algorithms,” IEEE Transactions on Evolutionary Computation, vol. 4, pp. 1–15, 2000.
M. Pagel (ed.), in Encyclopedia of Evolution, Oxford University Press: Oxford, 2002.
M. A. Potter, J. K. Bassett, and K. A. De Jong, “Visualizing evolvability with Price's equation,” in Proceedings of the 2003 Congress on Evolutionary Computation (CEC 2003), IEEE Press: NJ, 2003, pp. 2785–2790.
G. R. Price, “Selection and covariance,” Nature, vol. 227, pp. 520–521, 1970.
G. R. Price, “Extension of covariance selection mathematics,” Annals of Human Genetics, vol. 35, pp. 485–490, 1972.
G. R. Price, “Fisher's fundamental theorem made clear,” Annals of Human Genetics, vol. 36, pp. 129–140, 1972.
A. Robertson, “The spectrum of genetic variation,” in Population Biology and Evolution, R. C. Lewontin (ed.), Syracuse University Press: New York, 1968, pp. 5–16.
J. D. Schaffer, “Multiple objective optimization with vector evaluated genetic algorithms,” in Proceedings of the First international Conference on Genetic Algorithms, J. J. Grefenstette (ed.), Lawrence Erlbaum Associates: Hillsdale, NJ, 1985, pp. 93–100.
J. D. Schaffer, R. Caruana, L. J. Eshelman, and R. Das, “A study of control parameters affecting online performance of genetic algorithms for function optimization,” in The Third International Conference on Genetic Algorithms, J. D. Schaffer (ed.), Morgan Kaufmann: San Mateo, CA, 1989, pp. 51–60.
T. Smith, P. Husbands, P. Layzell, and M. O’Shea, “Fitness landscapes and evolvability,” Evolutionary Computation, vol. 10, pp. 1–34, 2002.
W. M. Spears, “Simple subpopulation schemes”, in Proceedings of the Third Annual Evolutionary Programming Conference, A. V. Sebald and L. J. Fogel (eds.), World Scientific: River Edge, NJ, 1994, pp. 296–307.
H. Suzuki, “An example of design optimization for high evolvability: string-rewriting grammar,” BioSystems, vol. 69, pp. 211–222, 2003.
D. Thierens, “Scalability problems of simple genetic algorithms,” Evolutionary Computation, vol. 7, pp. 331–352, 1999.
S. Tsutsui and Y. Fujimoto, “Forking genetic algorithm with blocking and shrinking modes,” in Proceedings of the Fifth International Conference on Genetic Algorithms, S. Forrest (ed.), Morgan Kaufmann: San Mateo, CA, 1993, pp. 206–213.
P. D. Turney, “Increasing evolvability considered as a large-scale trend in evolution,” GECCO-99 Workshop on Evolvability, pp. 43–46, 1999.
R. K. Ursem, “Diversity-guided evolutionary algorithms,” in Proceedings of Parallel Problem Solving from Nature VII (PPSN 7), 2002, pp. 462–471.
G. P. Wagner and L. Altenberg, “Complex adaptations and the evolution of evolvability,” Evolution, vol. 50, pp. 967–976, 2002.
L. D. Whitley, S. B. Rana, J. Dzubera, and K. E. Mathias, “Evaluating evolutionary algorithms,” Artificial Intelligence, vol. 85, pp. 245–276, 1996.
M. Wineberg and F. Oppacher, “Enhancing the GA's ability to cope with dynamic environments,” in Proceedings of the Second Genetic and Evolutionary Computation Conference (GECCO-2000), D. Whitley (ed.), Morgan Kaufmann: San Francisco, 2000, pp. 3–10.
M. Wineberg, Improving the behavior of the genetic algorithm in a dynamic environment, PHD thesis, Carleton University, Ottawa, Ontario, Canada, 2000.
M. Wineberg and J. Chen, “The shifting balance genetic algorithm as more than just another island model GA,” in Genetic and Evolutionary Computation (GECCO 2004), K. Deb et al. (eds.), Springer: Berlin, 2004, pp. 318–329.
K. Q. Zhu and Z. Liu, “Population diversity in permutation-based genetic algorithm,” in Conference on Cybernetics and Intelligent Systems, Springer, 2004.
Acknowledgments
This research was supported by the Natural Sciences and Engineering Research Council of Canada (NSERC).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, Y., Wineberg, M. Estimation of evolvability genetic algorithm and dynamic environments. Genet Program Evolvable Mach 7, 355–382 (2006). https://doi.org/10.1007/s10710-006-9015-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10710-006-9015-5