Risk-Sensitive Markov Decision Processes

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 stationa...

Full description

Saved in:
Bibliographic Details
Published in:Management science 1972-03, Vol.18 (7), p.356-369
Main Authors: Howard, Ronald A, Matheson, James E
Format: Article
Language:English
Subjects:
Coefficients
Eigenvalues
Eigenvectors
Expected values
Lotteries
Markov analysis
Markov processes
Mathematical constants
Matrices
Probability
Risk aversion
Taxicabs
Transition probabilities
Utility functions
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0025-1909
1526-5501
DOI:10.1287/mnsc.18.7.356