%0 Journal Article
%T Central-limit approach to risk-aware Markov decision processes
%A Pengqian Yu
%A Jia Yuan Yu
%A Huan Xu
%J Mathematics
%D 2015
%I arXiv
%X 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.
%U http://arxiv.org/abs/1512.00583v1