Evolved neurocontrollers for pole-balancing

  • Frank Pasemann
  • Ulf Dieckmann
Neural Networks for Communications, Control and Robotics
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1240)


An evolutionary algorithm for the development of neural networks with arbitrary connectivity is presented. The algorithm is not based on genetic algorithms, but is inspired by a biological theory of coevolving species. It sets no constraints on the number of neurons and the architecture of a network, and develops network topology and parameters like weights and bias terms simultaneously. Designed for generating neuromodules acting in embedded systems like autonomous agents, it can be used also for the evolution of neural networks solving nonlinear control problems. Here we report on a first test, where the algorithm is applied to a standard control problem: the balancing of an inverted pendulum.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Albrecht, R. F., Reeves, C. R., and Steele, N. C. (eds.), Artificial Neural Nets and Genetic Algorithms, Proceedings of the International Conference in Innsbruck, Austria, 1993, Springer, Wien 1993.Google Scholar
  2. [2]
    Anderson, C. W. (1989). Learning to control an inverted pendulum using neural networks. IEEE Control Systems Magazine, 9, 31–37.Google Scholar
  3. [3]
    Anderson, C. W. and Miller W. T. (1990). Challinging Control Problems. In W. T. Miller, R. S. Sutton, and P. J. Werbos, Neural Networks for Control, MIT Press.Google Scholar
  4. [4]
    Barto, A. G., Sutton, R. S., and Anderson, C. W. (1983). Neuronlike adaptive elements that solve difficult learning control problems. IEEE Transactions on Systems, Man, Cybernetics, 13, 834–846.Google Scholar
  5. [5]
    Branke, J. (1995). Evolutionary algorithms for neural network design and training. In Proceedings 1st Nordic Workshop on Genetic Algorithms and its Applications, Vaasa, Finland.Google Scholar
  6. [6]
    Bapi, R. S., D'Cruz, B., and Bugmann, G. (1996) Neuro-resistive grid approach to trainable controllers: A pole balancing example, submitted to Neural Computing and Applications.Google Scholar
  7. [7]
    Dasgupta, D., and McGregor, D. R. (1993). Evolving neurocontrollers for pole balancing. In S. Gielen and B. Kappen (eds.), ICANN'93 Proceedings of the International Conference on Artificial Neural Networks, Amsterdam 13.–16. Sept. 1993. Berlin: Springer-Verlag, 1993, pp. 834–837.Google Scholar
  8. [8]
    Dieckmann, U. (1995), Coevolution as an autonomous learning strategy for neuromodules, in: Herrmann, H., Pöppel, E., and Wolf, D. (eds.), Supcrcomputing in Brain Research — From Tomography to Neural Networks, Singapore: World Scientific, (pp.331–347).Google Scholar
  9. [9]
    Geva, S., and Sitte, J. (1993), A cartpole experiment benchmark for trainable controllers, IEEE Control Systems Magazin, 13, 40–51.Google Scholar
  10. [10]
    Schaffer, J. D., Whitley, D., and Eshelman, L. J. (1992). Combination of genetic algorithms and neural networks: A survey of the state of the art. In: Proccedings International Workshop on combinations of genetic algorithms and neural networks (COGANN-92), Los Alamitos, CA, IEEE Computer Society Press.Google Scholar
  11. [11]
    Selfridge, O. G., Sutton, R. S., and Barto, A. G. (1985). Training and tracking in robotics. In Proccedings International Joint Conference on Artificial Intelligence (IJCAI-85), Los Angeles, CA, pp: 670–672.Google Scholar
  12. [12]
    Widrow, B. (1987), The original adaptive neural net broom-balancer. Proc. IEEE Intern. Symp. Circuits and Systems, 351–357.Google Scholar
  13. [13]
    Wieland, A. P. (1991). Evolving neural network controllers for unstable systems. In: International Joint Conference on Neural Networks, Seattle, USA, Julyl991. Proccedings Vol.2. Seattle: IEEE Service Center, 1991.Google Scholar
  14. [14]
    Yao, X. (1993). A review of evolutionary artificial neural networks. International Journal of Intelligent Systems, 8, 539–567.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Frank Pasemann
    • 1
  • Ulf Dieckmann
    • 2
  1. 1.Research Center Jülich, IBI 1JülichGermany
  2. 2.International Institute for Applied Systems Analysis, ADNLaxenburgAustria

Personalised recommendations