@article{learningpoliciesformarkovdecision, title = {Learning Policies for Markov Decision Processes from Data}, author = {Manjesh K. Hanawal and Hao liu and Henghui Zhu and Ioannis Ch. Paschalidis}, year = {2017}, eprint = {1701.05954}, archivePrefix = {arXiv}, url = {http://arxiv.org/abs/1701.05954v1}, }