@article{offpolicyreinforcementlearningwith2,
  title = {Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction},
  author = {Jiachen Li and Shuo Cheng and Zhenyu Liao and Huayan Wang and William Yang Wang and Qinxun Bai},
  year = {2021},
  eprint = {2110.12081},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.12081v3},
}