Abstract
In this paper a combined use of reinforcement learning and simulated annealing is treated. Most of the simulated annealing methods suggest using heuristic temperature bounds as the basis of annealing. Here a theoretically es- tablished approach tailored to reinforcement learning following Softmax action selection policy will be shown. An application example of agent-based routing will also be illustrated.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ahuja, R., Magnanti, T. L., Orlin, J. B.: Network flows, Prentice Hall, ISBN 013617549-X, 1993
Crites, P. H., Barto, A.: Improving elevator performance using reinforcement learning, Advances in Neural Information Processing Systems, Vol. 8, MIT, 1996
Kaelbling L. P., Littman, M., Moore A. J.: Reinforcement learning: a survey, Journal of Artificial Intelligence Research, Vol. 4, 1996, pp. 237–285
Monostori, L., Márkus, A., Van Brussel, H., Westkämper, E.: Machine learning approaches to manufacturing, CIRP Annals, Vol. 45, No. 2, 1996, pp. 675–712.
Monostori, L., Kádár, B.; Viharos, Zs. J., Stefán, P.: AI and machine learning techniques combined with simulation for designing and controlling manufacturing processes and systems, Preprints of the IFAC Symposium on Manufacturing, Modeling, Management and Supervision, MIM 2000, 2000, Patras, Greece, pp. 167–172
Stefán, P., Monostori, L., Pupp, Z.: Reinforcement learning methods in information engineering, MicroCAD’2000 International Computer Science Conference, February 22-24, 2000, University of Miskolc
Sutton, R., Barto, A.: Reinforcement Learning (An Introduction), 1998
Tanenbaum, A.: Computer networks, Panem Press, ISBN 963 545 213 6, 1996
Viharos, Zs. J.: Application capabilities of a general, ANN based cutting model in different phases of manufacturing through automatic determination of its input-output configuration; Journal of Periodica Politechnica-Mechanical Engineering, Vol. 43, No. 2, 1999, pp. 189–196
Numerical recipes in C: The art of scientific computing, Cambridge University Press, ISBN 0-521-43108-5, http://www.nr.com
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
Stefán, P., Monostori, L. (2001). On the Relationship between Learning Capability and the Boltzmann-Formula. In: Monostori, L., Váncza, J., Ali, M. (eds) Engineering of Intelligent Systems. IEA/AIE 2001. Lecture Notes in Computer Science(), vol 2070. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45517-5_26
Download citation
DOI: https://doi.org/10.1007/3-540-45517-5_26
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42219-8
Online ISBN: 978-3-540-45517-2
eBook Packages: Springer Book Archive