Evolving Genes to Balance a Pole

  • Miguel Nicolau
  • Marc Schoenauer
  • Wolfgang Banzhaf
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6021)


We discuss how to use a Genetic Regulatory Network as an evolutionary representation to solve a typical GP reinforcement problem, the pole balancing. The network is a modified version of an Artificial Regulatory Network proposed a few years ago, and the task could be solved only by finding a proper way of connecting inputs and outputs to the network. We show that the representation is able to generalize well over the problem domain, and discuss the performance of different models of this kind.


Generalisation Test Promoter Site Genetic Regulatory Network Cart Model Extra Protein 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Banzhaf, W., Beslon, G., Christensen, S., Foster, J.A., Képès, F., Lefort, V., Miller, J.F., Radman, M., Ramsden, J.J.: From artificial evolution to computational evolution: a research agenda. Nature Reviews Genetics 7, 729–735 (2006)CrossRefGoogle Scholar
  2. 2.
    Kirschner, M., Gerhart, J.: The plausibility of life: Resolving Darwin’s dilemma. Yale University Press, New Haven (2005)Google Scholar
  3. 3.
    Hasty, J., McMillan, D., Isaacs, F., Collins, J.J.: Computational studies of gene regulatory networks: In numero molecular biology. Nature Reviews Genetics 2, 268–279 (2001)CrossRefGoogle Scholar
  4. 4.
    Lones, M.A., Tyrrell, A.M.: Modelling biological evolvability: Implicit context and variation filtering in enzyme genetic programming. BioSystems 76(1-3), 229–238 (2004)CrossRefGoogle Scholar
  5. 5.
    Zhan, S., Miller, J.F., Tyrrell, A.M.: An evolutionary system using development and artificial genetic regulatory networks. In: Proc. IEEE CEC 2008. IEEE Press, Los Alamitos (2008)Google Scholar
  6. 6.
    Banzhaf, W.: Artificial regulatory networks and genetic programming. In: Riolo, R., Worzel, B. (eds.) Genetic Programming Theory and Practice, ch. 4, pp. 43–62. Kluwer Publishers, Dordrecht (2003)Google Scholar
  7. 7.
    Wolfe, K., Shields, D.: Molecular evidence for an ancient duplication of the entire yeast genome. Nature 387, 708–713 (1997)CrossRefGoogle Scholar
  8. 8.
    Kellis, M., Birren, B.W., Lander, E.S.: Proof and evolutionary analysis of ancient genome duplication in the yeast saccharomyces cerevisiae. Nature 428, 617–624 (2004)CrossRefGoogle Scholar
  9. 9.
    Kuo, P.D., Banzhaf, W.: Small world and scale-free network topologies in an artificial regulatory network model. In: Pollack, J., et al. (eds.) Artificial Life IX, pp. 404–409. Bradford Books (2004)Google Scholar
  10. 10.
    Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man and Cybernetics 13, 834–846 (1983)Google Scholar
  11. 11.
    Whitley, D., Dominic, S., Das, R., Anderson, C.W.: Genetic reinforcement learning for neurocontrol problems. Machine Learning 13(2-3), 259–284 (1993)CrossRefGoogle Scholar
  12. 12.
    Rechenberg, I.: Evolutionsstrategie 1994. Frommann-Holzboog, Stuttgart (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Miguel Nicolau
    • 1
  • Marc Schoenauer
    • 1
  • Wolfgang Banzhaf
    • 2
  1. 1.INRIA Saclay - Île-de-FranceLRI- Université Paris-SudParisFrance
  2. 2.Memorial UniversityNewfoundlandCanada

Personalised recommendations