@article{offpolicydeepreinforcementlearning,
  title = {Off-Policy Deep Reinforcement Learning without Exploration},
  author = {Scott Fujimoto and David Meger and Doina Precup},
  year = {2018},
  eprint = {1812.02900},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1812.02900v3},
}