Skip to main content
Top

2014 | OriginalPaper | Chapter

18. Optimality Conditions for Partially Observable Markov Decision Processes

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

Published in: Continuous and Distributed Systems

Publisher: Springer International Publishing

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

search-config
loading …

Abstract

This note describes sufficient conditions for the existence of optimal policies for Partially Observable Markov Decision Processes (POMDPs). The objective criterion is either minimization of total discounted costs or minimization of total nonnegative costs. It is well-known that a POMDP can be reduced to a Completely Observable Markov Decision Process (COMDP) with the state space being the sets of believe probabilities for the POMDP. Thus, a policy is optimal in POMDP if and only if it corresponds to an optimal policy in the COMDP. Here we provide sufficient conditions for the existence of optimal policies for COMDP and therefore for POMDP.

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!

Literature
1.
go back to reference Bertsekas, D.P., Shreve, S.E.: Stochastic Optimal Control: The Discrete-Time Case. Academic Press, New York (1978) (reprinted by Athena Scientific, Belmont, 1996) Bertsekas, D.P., Shreve, S.E.: Stochastic Optimal Control: The Discrete-Time Case. Academic Press, New York (1978) (reprinted by Athena Scientific, Belmont, 1996)
2.
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
3.
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)MathSciNetCrossRefMATH 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)MathSciNetCrossRefMATH
4.
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
5.
go back to reference Feinberg, E.A., Lewis, M.E.: Optimality inequalities for average cost Markov decision processes and the stochastic cash balance problem. Math. Oper. Res. 32(4), 769–783 (2007) Feinberg, E.A., Lewis, M.E.: Optimality inequalities for average cost Markov decision processes and the stochastic cash balance problem. Math. Oper. Res. 32(4), 769–783 (2007)
6.
7.
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
8.
go back to reference Parthasarathy, K.R.: Probability Measures on Metric Spaces. Academic Press, New York (1967)MATH Parthasarathy, K.R.: Probability Measures on Metric Spaces. Academic Press, New York (1967)MATH
10.
go back to reference Sawaragi, Y., Yoshikawa, T.: Descrete-time markovian decision processes with incomplete state observations. Ann. Math. Statist. 41, 78–86 (1970)MathSciNetCrossRefMATH Sawaragi, Y., Yoshikawa, T.: Descrete-time markovian decision processes with incomplete state observations. Ann. Math. Statist. 41, 78–86 (1970)MathSciNetCrossRefMATH
11.
go back to reference Yushkevich, A.A.: Reduction of a controlled Markov model with incomplete data to a problem with complete information in the case of Borel state and control spaces. Theor. Probab. Appl. 21, 153–158 (1976)CrossRefMATH Yushkevich, A.A.: Reduction of a controlled Markov model with incomplete data to a problem with complete information in the case of Borel state and control spaces. Theor. Probab. Appl. 21, 153–158 (1976)CrossRefMATH
Metadata
Title
Optimality Conditions for Partially Observable Markov Decision Processes
Authors
Eugene A. Feinberg
Pavlo O. Kasyanov
Mikhail Z. Zgurovsky
Copyright Year
2014
DOI
https://doi.org/10.1007/978-3-319-03146-0_18