Risk-aware decision making and dynamic programming
Boris Defourny, Damien Ernst, Louis A. Wehenkel · ORBi (University of Liège) · 2008
This paper considers sequential decision making problems under uncertainty, the tradeoff between the expected return and the risk of high loss, and methods that use dynamic programming to find optimal policies. It is argued that using Bellman Principle determines how risk considerations on the return can be incorporated. The discussion centers around returns generated by Markov Decision Processes and conclusions concern a large class of methods in Reinforcement Learning. 1