@article{o2tdnearoptimaloffpolicytdlearning,
  title = {O$^2$TD: (Near)-Optimal Off-Policy TD Learning},
  author = {Bo Liu and Daoming Lyu and Wen Dong and Saad Biaz},
  year = {2017},
  eprint = {1704.05147},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1704.05147v2},
}