Abstract
Both the total reward criterion and the average reward criterion commonly used in Markov decision processes lead to an optimal policy which maximizes the associated expected value. The paper reviews these standard approaches and studies the distribution functions obtained by applying an optimal policy. In particular, an efficient extrapolation method is suggested resulting from the control of Markov decision models with an absorbing set.
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
ALTMAN, E. (2001): Applications of Markov Decision Processes in Communication Networks: a Survey. In E. Feinberg and A. Shwartz (Eds): Markov Decision Processes, Models, Methods, Directions, and Open Problems. Kluwer, Bosten, 488–536.
HINDERER, K. and WALDMANN, K.-H. (2004): Algorithms for countable state Markov decision models with an absorbing set. SIAM J. Control and Optimization, to appear.
NORRIS, J.R. (1997): Markov Chains. Cambridge University Press, Cambridge.
OGIWARA, T. (1995): Nonlinear Perron-Frobenius problem on an ordered Banach space. Japan J. Math., 21, 43–103.
PUTERMAN, M.L. (1994): Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York.
SENNOTT, L.I. (1999): Stochastic Dynamic Programming and the Control of Queueing Systems. Wiley, New York.
WU, C. and LIN, Y. (1999): Minimizing Risk Models in Markov Decision Processes with Policies Depending on Target Values. J. Math. Anal. Appl., 231, 47–60.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin · Heidelberg
About this chapter
Cite this chapter
Waldmann, KH. (2005). On Variability of Optimal Policies in Markov Decision Processes. In: Baier, D., Decker, R., Schmidt-Thieme, L. (eds) Data Analysis and Decision Support. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-28397-8_20
Download citation
DOI: https://doi.org/10.1007/3-540-28397-8_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26007-3
Online ISBN: 978-3-540-28397-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)