Skip to main content
Top
Published in:
Cover of the book

2021 | OriginalPaper | Chapter

Average Cost Markov Decision Processes with Semi-Uniform Feller Transition Probabilities

Authors : Eugene A. Feinberg, Pavlo O. Kasyanov, Michael Z. Zgurovsky

Published in: Modern Trends in Controlled Stochastic Processes:

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

This paper studies average-cost Markov decision processes with semi-uniform Feller transition probabilities. This class of MDPs was recently introduced by the authors to study MDPs with incomplete information. This paper studies the validity of optimality inequalities, the existence of optimal policies, and the approximations of optimal policies by policies optimizing total discounted costs.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
1.
go back to reference Bäuerle, N., Rieder, U.: Markov Decision Processes with Applications to Finance. Springer, Berlin (2011) CrossRef Bäuerle, N., Rieder, U.: Markov Decision Processes with Applications to Finance. Springer, Berlin (2011) CrossRef
2.
go back to reference Bertsekas, D.P., Shreve, S.E.: Stochastic Optimal Control: The Discrete-Time Case. Academic Press, New York (1978)MATH Bertsekas, D.P., Shreve, S.E.: Stochastic Optimal Control: The Discrete-Time Case. Academic Press, New York (1978)MATH
3.
go back to reference Billingsley, P.: Convergence of Probability Measures. Wiley, New York (1968)MATH Billingsley, P.: Convergence of Probability Measures. Wiley, New York (1968)MATH
5.
go back to reference Dynkin, E.B., Yushkevich, A.A.: Controlled Markov Processes. Springer, New York (1979)CrossRef Dynkin, E.B., Yushkevich, A.A.: Controlled Markov Processes. Springer, New York (1979)CrossRef
7.
go back to reference Feinberg, E.A., Kasyanov, P.O., Liang, Y.: Fatou’s lemma in its classical form and Lebesgue’s convergence theorems for varying measures with applications to Markov decision processes. Theory Probab. Appl. 65(2), 270–291 (2020)MathSciNetCrossRef Feinberg, E.A., Kasyanov, P.O., Liang, Y.: Fatou’s lemma in its classical form and Lebesgue’s convergence theorems for varying measures with applications to Markov decision processes. Theory Probab. Appl. 65(2), 270–291 (2020)MathSciNetCrossRef
8.
go back to reference Feinberg, E.A., Kasyanov, P.O., Zadoianchuk, N.V.: Average-cost Markov decision processes with weakly continuous transition probabilities. Math. Oper. Res. 37(4), 591–607 (2012)MathSciNetCrossRef Feinberg, E.A., Kasyanov, P.O., Zadoianchuk, N.V.: Average-cost Markov decision processes with weakly continuous transition probabilities. Math. Oper. Res. 37(4), 591–607 (2012)MathSciNetCrossRef
9.
go back to reference Feinberg, E.A., Kasyanov, P.O., Zadoianchuk, N.V.: Berge’s theorem for noncompact image sets. J. Math. Anal. Appl. 397(1), 255–259 (2013)MathSciNetCrossRef Feinberg, E.A., Kasyanov, P.O., Zadoianchuk, N.V.: Berge’s theorem for noncompact image sets. J. Math. Anal. Appl. 397(1), 255–259 (2013)MathSciNetCrossRef
10.
go back to reference Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Convergence of probability measures and Markov decision models with incomplete information. Proc. Steklov Inst. Math. 287(1), 96–117 (2014)MathSciNetCrossRef Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Convergence of probability measures and Markov decision models with incomplete information. Proc. Steklov Inst. Math. 287(1), 96–117 (2014)MathSciNetCrossRef
11.
go back to reference Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Partially observable total-cost Markov decision processes with weakly continuous transition probabilities. Math. Oper. Res. 41(2), 656–681 (2016)MathSciNetCrossRef Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Partially observable total-cost Markov decision processes with weakly continuous transition probabilities. Math. Oper. Res. 41(2), 656–681 (2016)MathSciNetCrossRef
12.
go back to reference Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Markov decision processes with incomplete information and semi-uniform Feller transition probabilities. In preparation (2021) Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Markov decision processes with incomplete information and semi-uniform Feller transition probabilities. In preparation (2021)
13.
go back to reference Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Uniform Fatou’s lemma. J. Math. Anal. Appl. 444(1), 550–567 (2016)MathSciNetCrossRef Feinberg, E.A., Kasyanov, P.O., Zgurovsky, M.Z.: Uniform Fatou’s lemma. J. Math. Anal. Appl. 444(1), 550–567 (2016)MathSciNetCrossRef
14.
go back to reference Feinberg, E.A., Kasyanov, P.O., Zadoianchuk, N.V.: Fatou’s lemma for weakly converging probabilities. Theory Probab. Appl. 58(4), 683–689 (2014)MathSciNetCrossRef Feinberg, E.A., Kasyanov, P.O., Zadoianchuk, N.V.: Fatou’s lemma for weakly converging probabilities. Theory Probab. Appl. 58(4), 683–689 (2014)MathSciNetCrossRef
16.
go back to reference Hernández-Lerma, O.: Adaptive Markov Control Processes. Springer, New York (1989)CrossRef Hernández-Lerma, O.: Adaptive Markov Control Processes. Springer, New York (1989)CrossRef
17.
go back to reference Hernández-Lerma, O.: Average optimality in dynamic programming on Borel spaces - Unbounded costs and controls. Syst. Control Lett. 17(3), 237–242 (1991)MathSciNetCrossRef Hernández-Lerma, O.: Average optimality in dynamic programming on Borel spaces - Unbounded costs and controls. Syst. Control Lett. 17(3), 237–242 (1991)MathSciNetCrossRef
18.
go back to reference Hernández-Lerma, O., Lassere, J.B.: Discrete-Time Markov Control Processes: Basic Optimality Criteria. Springer, New York (1996)CrossRef Hernández-Lerma, O., Lassere, J.B.: Discrete-Time Markov Control Processes: Basic Optimality Criteria. Springer, New York (1996)CrossRef
19.
go back to reference Papanicolaou, G.C.: Asymptotic analysis of stochastic equations. In: Rosenblatt, M. (ed.) Studies in Probability Theory, pp. 111–179. Mathematical Association of America, Washington DC (1978) Papanicolaou, G.C.: Asymptotic analysis of stochastic equations. In: Rosenblatt, M. (ed.) Studies in Probability Theory, pp. 111–179. Mathematical Association of America, Washington DC (1978)
20.
go back to reference Parthasarathy, K.R.: Probability Measures on Metric Spaces. Academic Press, New York (1967)CrossRef Parthasarathy, K.R.: Probability Measures on Metric Spaces. Academic Press, New York (1967)CrossRef
21.
go back to reference Schäl, M.: Average optimality in dynamic programming with general state space. Math. Oper. Res. 18(1), 163–172 (1993)MathSciNetCrossRef Schäl, M.: Average optimality in dynamic programming with general state space. Math. Oper. Res. 18(1), 163–172 (1993)MathSciNetCrossRef
Metadata
Title
Average Cost Markov Decision Processes with Semi-Uniform Feller Transition Probabilities
Authors
Eugene A. Feinberg
Pavlo O. Kasyanov
Michael Z. Zgurovsky
Copyright Year
2021
DOI
https://doi.org/10.1007/978-3-030-76928-4_1

Premium Partner