Abstract
A hybrid method, based on evolutionary computation, Monte Carlo simulation, and neural networks for functional approximation and time series prediction, is proposed to reduce the high computational cost usually required by dynamic programming problems, that appear in complex real applications. As an example of application a scheduling problem related with the control of a water supply network is considered.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bertsekas, D.P.: “Dynamic Programming and Optimal Control”. Athena Scientific, Beltmont, Massachusetts, 1995.
Bellmann, R.; Dreyfus, S.: “Applied Dynamic Programming”. Princeton University Press, Princeton, N.J., 1962.
Bertsekas, D.P.; Tsitsiklis, J.N.: “Neuro-Dynamic Programming”. Athena Scientific, Belmont, Massachusetts, 1996.
Tesauro, G.; Galperin, G.R.: “On-line policy improvement using Monte-Carlo search”. In Advances in Neural Information Processing, 9, pp.1068–1074, MIT Press, 1996.
Watkins, C.J.C.H.: “Learning from Delayed Rewards”. PhD Thesis, Cambridge University, 1989.
Renders, J.M.; Flasse, S.P.: “Hybrid Methods using Genetic Algorithms for Global Optimization”. IEEE Trans. on Systems, Man, and Cybernetics (Part B), Vol.26,No.2, pp.243–258. Abril, 1996.
Moody, J., Darken, C.: “Fast Learning in Networks of Locally-Tuned Processing Units”. Neural Computation 1(2), pp. 281–294, 1989.
Golub, G.H., Van Loan, C.F.: “Matrix Computations”. Johns Hopkins University Press, Baltimore, MD, 1989.
Kanjilal, P.P., Banerjee, D.N..: “On the Application of Orthogonal Transformation for the Design and Analysis of Feedforward Networks”. IEEE Transactions on Neural Networks, 6(5), pp. 1061–1070, 1995.
Salmerón, M.; Ortega, J.; Puntonet, C.G.: “On-line optimization of Radial Basis Function Networks with Orthogonal Techniques”. In Foundations and Tools for Neural Modeling (Mira, J.; Sánchez-Andrés, J.V. Ed.), Lecture Notes in Computer Science, 1606, pp.467–477, Springer-Verlag, Berlin, 1999.
Salmerón, M.; Ortega, J.; Puntonet, C.G.; Prieto, A.: “Improved RAN sequential prediction using orthogonal techniques”. Neurocomputing (in press).
Whitley, D.; Dominic, S.; Das, R.; Anderson, C.: “Genetic Reinforcement Learning for Neurocontrol Problems”. Machine Learning, 13, pp.259–284, 1993.
Tesauro, G.J.; Galperin, G.R.: “On-line policy improvement using Monte-Carlo search”. Advances in Neural Information Processing Systems, 9, MIT Press, pp.1069–1074, 1997.
Tsitsiklis, J.N.; Van Roy, B.: “An analysis of temporal-difference learning with function approximation”. IEEE Trans. on Automatic Control, Vol.42,No.5, pp.674–690. May, 1997.
Crites, R.H.; Barto, A.G.: “Improving elevator performance using reinforcement learning”. Advances in Neural Information Processing, 8, MIT Press, pp.1017–1023,1996.
Zhang, W.; Dietterich, T.G.: “High-performance job-shop scheduling with a time-delay TD(lambda) network”. Advances in Neural Information Processing, 8, MIT Press, pp. 1024–1030, 1996.
Sutton, R.; Barto, A.G.: “Reinforcement Learning: An Introduction”. MIT Press, Cambridge, MA, 1998.
Damas, M.; Salmerón, M; Fernández, J.; Ortega, J.; Olivares, G.: “Parallel Control of Water Supply Networks in Clusters of Computers”. 4th World Multiconference on Systemics, Cybernetics and Informatics (SCI’2000), pp.538–543, ISBN: 980-07-6693-6. Orlando (USA), 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Damas, M., Salmerón, M., Ortega, J., Olivares, G. (2001). Hybrid Framework for Neuro-Dynamic Programming Application to Water Supply Networks. In: Mira, J., Prieto, A. (eds) Bio-Inspired Applications of Connectionism. IWANN 2001. Lecture Notes in Computer Science, vol 2085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45723-2_87
Download citation
DOI: https://doi.org/10.1007/3-540-45723-2_87
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42237-2
Online ISBN: 978-3-540-45723-7
eBook Packages: Springer Book Archive