Abstract
Consider a controlled Markov chain whose transition probabilities are parameterized by α known to be in a finite set A. To each α is associated a prespecified control law φ(α). The adaptive controller selects at each time t the control action indicated by φ(αt), where αt is the maximum likelihood estimate of α. The asymptotic behavior of αt is studied.
References
M.H. Degroot, Optimal Statistical Decisions, McGraw-Hill, New York, 1970.
Y. Bar-Shalom and E. Tse, Dual effect, certainty equivalence, and separation in stochastic control, IEEE Trans. Aut. Cont. AC-19(5), 494–500, 1974.
P. Mandl, Estimation and control in Markov chains, Adv. Appl. Prob. 6, 40–60, 1974.
K.J. Astrom and B. Wittenmark, On self-tuning regulators, Automatica 9, 185–199, 1973.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1979 Springer-Verlag
About this paper
Cite this paper
Borkar, V., Varaiya, P. (1979). Adaptive control of Markov chains. In: Kohlmann, M., Vogel, W. (eds) Stochastic Control Theory and Stochastic Differential Systems. Lecture Notes in Control and Information Sciences, vol 16. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0009389
Download citation
DOI: https://doi.org/10.1007/BFb0009389
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-09480-7
Online ISBN: 978-3-540-35211-2
eBook Packages: Springer Book Archive