Abstract
In this paper optimal control of risk-sensitive Markov decision processes with countable states is studied. The state space is not assumed to be communicating. The focus is on dependence of the optimal values on the transition characteristics-communication, transience or absorption. A vanishing discount approach is used to introduce a partition of the state space, and certain transformation of the optimal values under discount is shown to convergence to the optimal values under risk sensitivity, as the discount factor tends to vanish. The partition of the state space turns out to be closely related to the characteristics of state communication, but weights more on the values under discount.
Similar content being viewed by others
Data Availability
Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.
References
Alanis-Duran A, Cavazos-Cadena R. An optimality system for finite average Markov decision chains under risk-aversion. Kybernetika(Prague). 2012;48(1):83–104.
Arapostathis A, Borkar VS, Fernandez-Gaucherand E, Ghosh MK, Marcus SI. Discrete-time controlled Markov processes with average cost criterion: a survey. SIAM J Control Optim. 1993;31(2):282–344.
Bäuerle N, Rieder U. More risk-sensitive Markov decision processes. Math Oper Res. 2014;39(1):105–20.
Blancas-Rivera R, Cavazos-Cadena R, Cruz-Suarez H. Discounted approximations in risk-sensitive average Markov cost chains with finite state space. Math Methods Oper Res. 2020;91(2):241–68.
Borkar VS, Meyn SP. Risk-sensitive optimal control for Markov decision processes with monotone cost. Math Oper Res. 2002;27(1):192–209.
Cavazos-Cadena R, Cruz-Suarez D. Discounted approximations to the risk-sensitive average cost in finite Markov chains. J Math Anal Appl. 2017;450(2):1345–62.
Cavazos-Cadena R, Fernandez-Gaucherand E. The vanishing discount approach in Markov chains with risk-sensitive criteria. IEEE Trans Automat Control. 2000;45(10):1800–16.
Cavazos-Cadena R. Characterization of the optimal risk-sensitive average cost in denumerable Markov decision chains. Math Oper Res. 2018;43(3):1025–50.
Cavazos-Cadena R, Hernandez-Hernandez D. Contractive approximations for the Varadhan’s function on a finite Markov chain. Theory Probab Appl. 2008;52(2):315–23.
Cavazos-Cadena R, Hernandez-Hernandez D. Discounted approximations for risk-sensitive average criteria in Markov decision chains with finite state space. Math Oper Res. 2011;36(1):133–46.
Cavazos-Cadena R, Hernandez-Hernandez D. Vanishing discount approximations in controlled Markov chains with risk-sensitive average criterion. Adv Appl Probab. 2018;50(1):204–30.
Cavazos-Cadena R. Solution to the risk-sensitive average cost optimality equation in a class of Markov decision processes with finite state space. Math Methods Oper Res. 2003;57(2):263–85.
Cavazos-Cadena R. Solutions of the average cost optimality equation for finite Markov decision chains: risk-sensitive and risk-neutral criteria. Math Methods Oper Res. 2009;70(3):541–66.
Cavazos-Cadena R, Hernandez-Hernandez D. A system of Poisson equations for a nonconstant Varadhan functional on a finite state space. Appl Math Optim. 2006;53(1):101–19.
Cavazos-Cadena R, Salem-Silva F. The discounted method and equivalence of average criteria for risk-sensitive Markov decision processes on Borel spaces. Appl Math Optim. 2010;61(2):167–90.
Di Masi GB, Stettner L. Infinite horizon risk sensitive control of discrete time Markov processes with small risk. Systems Control Lett. 2000;40(1):15–20.
Howard RA, Matheson JE. Risk-sensitive Markov decision processes. Manag Sci. 1972;18:356–69.
Jaśkiewicz A. Average optimality for risk-sensitive control with general state space. Ann Appl Probab. 2007;17(2):654–75.
Di Masi GB, Stettner L. Risk-sensitive control of discrete-time Markov processes with infinite horizon. SIAM J Control Optim. 1999;38(1):61–78.
Puterman ML. Markov decision processes. Handbooks Oper Res Manag Sci. 1990;2:331–434.
Acknowledgements
The authors are grateful to the referee for valuable comments and suggestions for improvement.
Funding
This work is supported by the NSFC 11671226.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Huang, T., Lu, X. & Chen, J. A Discount Vanishing Approximation for Markov Decision Processes with Risk Sensitivity. J Dyn Control Syst (2024). https://doi.org/10.1007/s10883-024-09691-3
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10883-024-09691-3