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 stationary policy with highest certain equivalent gain for the infinite duration case. A simple example demonstrates both procedures.

• 저널Management Science · 18(7) · 356–369
• 토픽Simulation Techniques and Applications · Management Science and Operations Research
• DOI10.1287/mnsc.18.7.356
• 저자Ronald A. Howard, James Matheson