Abstract
For a discrete Markovian Decision Process with finite state space an error bound is given for an arbitrary approximate solutionv′ of the Value Determination Equation.
Similar content being viewed by others
References
Howard, R.A.: Dynamic Programming and Markov Processes. New York-London 1960.
Odoni, A.R.: On finding the maximal gain for Markov Decision Processes. Opns. Res.17, 1969, 857–860.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Steinbuβ, W. An error bound concerning Howard's Value Determination Equation. Zeitschrift für Operations Research 26, 185–188 (1982). https://doi.org/10.1007/BF01917110
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01917110