1. RISK-SENSITIVE MARKOV DECISION PROCESSES.
- Author
-
Howard, Ronald A. and Matheson, James E.
- Subjects
MARKOV processes ,ITERATIVE methods (Mathematics) ,STOCHASTIC processes ,DECISION making ,PROBABILITY theory ,NUMERICAL analysis ,RISK ,MATHEMATICAL analysis ,MATHEMATICAL optimization ,MATHEMATICAL models - Abstract
This paper considers the maximization of certain equivalent reward generated by a Markov decision process with constant risk sensitivity. First, value iteration is used to optimize possibly time-varying processes of finite duration. Then a policy iteration procedure is developed to find the stationary policy with highest certain equivalent gain for the infinite duration case. A simple example demonstrates both procedures. [ABSTRACT FROM AUTHOR]
- Published
- 1972
- Full Text
- View/download PDF