Neural network design for J function approximation in dynamic programming

  title={Neural network design for J function approximation in dynamic programming},
  author={Xiaolin Pang and P. Werbos},
This paper will show that a new neural network design can solve an example of difficult function approximation problems which are crucial to the field of approximate dynamic programming(ADP). Although conventional neural networks have been proven to approximate smooth functions very well, the use of ADP for problems of intelligent control or planning requires the approximation of functions which are not so smooth. As an example, this paper studies the problem of approximating the J function of… CONTINUE READING
Highly Cited
This paper has 117 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 37 extracted citations

118 Citations

Citations per Year
Semantic Scholar estimates that this publication has 118 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 26 references

Learning in the brain: engineering interpretation

  • P. Werbos
  • K. Pribram, (eds.), Learning as Self-organization…
  • 1996
1 Excerpt

Optimization methods for brain-like intelligent control

  • P. Werbos
  • IEEE Conference on Decision and Control
  • 1995
2 Excerpts


  • D. Prokhorov
  • Santiago & D. Wunsch, “Adaptive critic designs: a…
  • 1995

Asymptotically optimal functional estimation by minimum complexity criteria

  • A. Barron
  • Proceedings of 1994 IEEE International Symposium…
  • 1994
1 Excerpt

Fundamentals of Neural Networks: architectures

  • L. Fausett
  • algorithms and applications, Prentice Hall
  • 1994
1 Excerpt

Supervised learning: can it escape its local minimum

  • P. Werbos
  • WCNN93 Proceedings, Erlbaum, 1993. Reprinted in V…
  • 1994
1 Excerpt

The brain as a neurocontroller: New hypotheses and new experimental possibilities

  • P. Werbos
  • K.Pribram (eds.), Origins: Brain and Self…
  • 1994
1 Excerpt

Similar Papers

Loading similar papers…