Pole-balancing with different evolved neurocontrollers
The paper presents various evolved neurocontrollers for the pole-balancing problem with good benchmark performance. They are small neural networks with recurrent connectivity. The applied evolutionary algorithm, which is not based on genetic algorithms, was designed to evolve neural networks with arbitrary connectivity. It uses no quantization of inputs, outputs or internal parameters, and sets no constraints on the number of neurons. Network topology and parameters like weights and bias terms are developed simultaneously.
Unable to display preview. Download preview PDF.
- 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.Anderson, C. W. (1989). Learning to control an inverted pendulum using neural networks. IEEE Control Systems Magazine, 9, 31–37.Google Scholar
- 3.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
- 4.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
- 5.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, Berlin: Springer-Verlag, 1993, pp. 834–837.Google Scholar
- 6.Dieckmann, U. (1995), Coevolution as an autonomous learning strategy for neuromodules, in: Herrmann, H., Pöppel, E., and Wolf, D. (eds.), Supercomputing in Brain Research-From Tomography to Neural Networks, Singapore: World Scientific, (pp. 331–347).Google Scholar
- 7.Pasemann, F., Dieckmann, U. (1997). Evolved Neurocontrollers for pole-balancing. In: Proceedings IWANN'97, Lanzarote, Spain, June 4–6, 1997, Lecture Notes in Computer Science. Berlin: Springer-Verlag.Google Scholar
- 8.Pasemann, F., Nelle, E. (1993). Elements of non-convergent neurodynamics, in: Andersson, S. L, Andersson, A.E., Ottoson, U.: Dynamical Systems-Theory and Applications. Singapore: World Scientific.Google Scholar
- 9.Geva, S., and Sitte, J. (1993). A cartpole experiment benchmark for trainable controllers, IEEE Control Systems Magazin, 13, 40–51.Google Scholar
- 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: Proceedings International Workshop on combinations of genetic algorithms and neural networks (COGANN-92), Los Alamitos, CA, IEEE Computer Society Press.Google Scholar
- 11.Yao, X. (1993). A review of evolutionary artificial neural networks. International Journal of Intelligent Systems, 8, 539–567.Google Scholar