Advertisement

Learning controllers using neural networks

  • W. T. C. van Luenen
Chapter
Part of the Lecture Notes in Computer Science book series (LNCS, volume 931)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. C.W. Anderson (1987) Strategy learning with multilayer connectionist representations. Proc. 4th Int. Workshop Machine Learning, Univ. California, Irvine, 103–114.Google Scholar
  2. A.W.P. Bakkers and J. van Amerongen (1990) Transputer based control of mechatronic systems. Control, Systems and Computer Engineering Group (BSC), University of Twente, Enschede, Netherlands, Proc. of the 11th World Congress of IFAC in Tallinn, USSR.Google Scholar
  3. A.G. Barto and P. Anandan (1985) Pattern recognizing stochastic learning automata. IEEE Trans. Syst. Man Cybern. 15 (3), 360–375.Google Scholar
  4. A.G. Barto, R.S. Sutton and P.S. Brouwer (1981) Associative search network: a reinforcement associative memory. Biol. Cybern. 40, 201–211.CrossRefGoogle Scholar
  5. A.G. Barto, R.S. Sutton and C.W. Anderson (1983) Neuronlike adaptive elements that can solve learning control problems. IEEE Trans. Systems, Man Cybern. Vol. SMC-13, No. 5, 834–846.Google Scholar
  6. G.F. Franklin and J.D. Powell (1980) Digital control of dynamic systems, Addisson-Wesley Publishing company, Reading, Massachusetts.Google Scholar
  7. A.H. Klopf (1988) A neuronal model of classical conditioning. Psychobiology 16 (2), 85–125.Google Scholar
  8. A.N. Kolmogorov (1957) On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition [in russian]. Dokl. Akad. Nauk USSR 114, 953–956.Google Scholar
  9. W.T.C. van Luenen, P.J. de Jager, J. van Amerongen and H.M. Franken (1993) Limitations of adaptive critic control schemes. Proc. of the Int. Conference on Artificial Neural Networks, Amsterdam, The Netherlands.Google Scholar
  10. W.T.C. van Luenen (1994) Neural networks for control, on knowledge representation and learning. PhD thesis, Control Laboraty, Dept. of Electrical Engineering, University of Twente, The Netherlands.Google Scholar
  11. J.M. Mendel and R.W. McClaren (1970) Reinforcement learning control and pattern recognition systems. In Adaptive learning and pattern recognition systems: theory and applications, Mendel, J.M. and Fu, K.S. (eds.), 287–318, New York, Academic Press.Google Scholar
  12. D. Michie and R.A. Chambers (1968) 'Boxes ‘as a model of pattern-formation. Towards a theoretical Biology, Vol. 1, Prolegomena, C.H. Waddington, Ed., Edinburgh: Edingburgh Univ. Press, 206–215.Google Scholar
  13. K.S. Narendra and M.A.L. Thathachar (1989) Learning Automata, an introduction. Prentice Hall, Englewood Cliffs NJ.Google Scholar
  14. K.S. Narendra and K. Parthasarathy (1990) Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Networks 1 (1).Google Scholar
  15. H. Oosterveen (1990) Design and implementation of a state feedback and a neural controller for inverted pendulum. Master thesis, Control, Systems and Computer Engineering Group (BSC), Reportnr. 89R140, University of Twente, Enschede, The Netherlands.Google Scholar
  16. H.T.A. Potma (1990) Analysis of the adaptive heuristic critic algorithm applied to pole balancing. Master thesis, Control, Systems and Computer Engineering Group (BSC), Reportnr. 90R068, University of Twente, Enschede, The Netherlands.Google Scholar
  17. R.S. Sutton (1988) Learning to predict by the methods of temporal differences. Machine Learning 3, 9–44.Google Scholar
  18. R.S. Sutton and A.G. Barto (1981) Towards a modern theory of adaptive networks: Expectation and prediction. Psychol. Rev. 88, 135–171.CrossRefPubMedGoogle Scholar
  19. B. Widrow and S.D. Stearns (1985) Adaptive signal processing. Prentice Hall, Englewood Cliffs NJ.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • W. T. C. van Luenen
    • 1
  1. 1.Unilever Research LaboratoriumVlaardingen

Personalised recommendations