Skip to main content
Log in

A successive approximation algorithm for an undiscounted Markov decision process

Ein sukzessiver Approximations-Algorithmus zu einem nicht diskontierten Markov-Entscheidungsprozeß

  • Published:
Computing Aims and scope Submit manuscript

Abstract

In this paper we consider a completely ergodic Markov decision process with finite state and decision spaces using the average return per unit time criterion. An algorithm is derived which approximates the optimal solution. It will be shown that this algorithm is finite and supplies upper and lower bounds for the maximal average return and a nearly optimal policy with average return between these bounds.

Zusammenfassung

Diese Arbeit betrachtet den ergodischen Markov-Entscheidungsprozeß mit endlichem Zustandsraum und endlichen Aktionsmengen mit dem Kriterium des Durchschnittsertrags. Ein Algorithmus wird presentiert, der diesen Ertrag approximiert. Es wird bewiesen, daß der Algorithmus konvergiert, und es werden obere und untere Schranken zum optimalen Durchschnittsertrag gegeben. Außerdem wird eine Strategie bestimmt mit zugehörigem Durchschnittsertrag zwischen diesen Schranken.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Howard, R. A.: Dynamic Programming and Markov processes. 5th printing, pp. 32–43. Cambridge: M. I. T. Press 1969.

    Google Scholar 

  2. Odoni, A. R.: On finding the gain for Markov decision processes. O. R.17, 857–860 (1969).

    Google Scholar 

  3. Spremann, K., Gessner, P.: Algorithmus 21. Bewertete Markovprozesse im stationären Zustand —Ein neuer Algorithmus mit Beispiel. Computing13, 173–181 (1974).

    Google Scholar 

  4. Van Nunen, J. A. E. E.: A set of successive approximation methods for discounted Markovian decision problems. (To appear in Z. f. Oper. Res.)

  5. Doob, J. L.: Stochastic Processes, p. 173. New York: J. Wiley 1953.

    Google Scholar 

  6. Van der Wal, J.: The solution of an undiscounted completely ergodic Markov decision process by successive approximation. Memorandum COSOR 74-05. Technological University Eindhoven, March 1974 (Department of Mathematics).

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

van der Wal, J. A successive approximation algorithm for an undiscounted Markov decision process. Computing 17, 157–162 (1976). https://doi.org/10.1007/BF02276760

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02276760

Keywords

Navigation