On Crossover Success Rate in Genetic Programming with Offspring Selection
A lot of progress towards a theoretic description of genetic programming in form of schema theorems has been made, but the internal dynamics and success factors of genetic programming are still not fully understood. In particular, the effects of different crossover operators in combination with offspring selection are still largely unknown. This contribution sheds light on the ability of well-known GP crossover operators to create better offspring (success rate) when applied to benchmark problems. We conclude that standard (sub-tree swapping) crossover is a good default choice in combination with offspring selection, and that GP with offspring selection and random selection of crossover operators does not improve the performance of the algorithm in terms of best solution quality or efficiency.
KeywordsMean Square Error Selection Pressure Genetic Programming Solution Quality Tree Size
Unable to display preview. Download preview PDF.
- 2.Affenzeller, M., Winkler, S.M., Wagner, S.: Effective allele preservation by offspring selection: An empirical study for the TSP. International Journal of Simulation and Process Modelling (2009) (accepted to appear)Google Scholar
- 3.Asuncion, A., Newman, D.J.: UCI machine learning repository (2007)Google Scholar
- 6.Langdon, W.B., Banzhaf, W.: Repeated patterns in genetic programming. Natural Computing (2008) (Published online: May 26, 2007)Google Scholar
- 9.Murphy, G., Ryan, C.: Exploiting the path of least resistance in evolution. In: GECCO 2008: Proceedings of the 10th annual conference on Genetic and evolutionary computation, Atlanta, GA, USA, pp. 1251–1258. ACM, New York (2008)Google Scholar
- 13.Poli, R., Langdon, W.B.: On the search properties of different crossover operators in genetic programming. In: Genetic Programming 1998: Proceedings of the Third Annual Conference, University of Wisconsin, Madison, Wisconsin, USA, pp. 293–301. Morgan Kaufmann, San Francisco (1998)Google Scholar
- 17.Poli, R., Rowe, J.E., Stephens, C.R., Wright, A.H.: Allele diffusion in linear genetic programming and variable-length genetic algorithms with subtree crossover. In: Foster, J.A., Lutton, E., Miller, J., Ryan, C., Tettamanzi, A.G.B. (eds.) EuroGP 2002. LNCS, vol. 2278, pp. 212–227. Springer, Heidelberg (2002)CrossRefGoogle Scholar
- 18.Winkler, S.M., Affenzeller, M., Wagner, S.: Using enhanced genetic programming techniques for evolving classifiers in the context of medical diagnosis. In: Genetic Programming and Evolvable Machines (2009) (Online First)Google Scholar