A Short Note on Combining Multiple Policies in Risk-Sensitive Exponential Average Reward Markov Decision Processes

Chang, Hyeong SooThis work was done while he was a visiting associate professor at ISR, University of Maryland, College Park.This short note presents a method of combining multiple policies in a given policy set such that the resulting policy improves all policies in the set for risk-sensitive exponential average reward Markov decision processes (MDPs), extending the work of Howard and Matheson for the singleton policy set case. Some applications of the method in solving risk-sensitive MDPs are also discussed.enRisk-sensitive Markov decision processpolicy improvementA Short Note on Combining Multiple Policies in Risk-Sensitive Exponential Average Reward Markov Decision ProcessesTechnical Report