14/09/2016 – Talk by prof. Jia Yuan Yu (Concordia Institute of Information System Engineering)

Title: Central-Limit Approach to Risk-aware Markov Decision Processes
Time: 14:00
Location: Meeting room
Type: Research Result
Speaker: Jia Yuan Yu
Abstract: Whereas classical Markov decision processes maximize the expected reward, we consider minimizing the risk. We propose to evaluate the risk associated to a given policy over a long-enough time horizon with the help of a central limit theorem. The proposed approach works whether the transition probabilities are known or not. We also provide a gradient-based policy improvement algorithm that converges to a local optimum of the risk objective.