@inproceedings{learningunknownmarkovdecisionprocessesa,
  title = {Learning Unknown Markov Decision Processes: A Thompson Sampling Approach},
  author = {Yi Ouyang and Mukul Gagrani and Ashutosh Nayyar and Rahul Jain},
  year = {2017},
  booktitle = {NeurIPS 2017 12},
  eprint = {1709.04570},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1709.04570v1},
}