@misc{dl2-a09-1,
  title={Off-Policy Deep Reinforcement Learning without Exploration},
  author={Scott Fujimoto, David Meger, Doina Precup},
  year={2019},
  url={https://arxiv.org/abs/1812.02900}
}
@misc{dl2-a09-2,
  title={Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction},
  author={Aviral Kumar, Justin Fu, George Tucker, Sergey Levine},
  year={2019},
  url={https://arxiv.org/abs/1906.00949}
}
@misc{dl2-a09-3,
  title={Conservative Q-Learning for Offline Reinforcement Learning},
  author={Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine},
  year={2020},
  url={https://arxiv.org/abs/2006.04779}
}
@misc{dl2-a09-4,
  title={Offline Reinforcement Learning with Implicit Q-Learning},
  author={Ilya Kostrikov, Ashvin Nair, Sergey Levine},
  year={2021},
  url={https://arxiv.org/abs/2110.06169}
}
@misc{dl2-a09-5,
  title={D4RL: Datasets for Deep Data-Driven Reinforcement Learning},
  author={Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, Sergey Levine},
  year={2021},
  url={https://arxiv.org/abs/2004.07219}
}
@misc{dl2-a09-6,
  title={Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems},
  author={Sergey Levine, Aviral Kumar, George Tucker, Justin Fu},
  year={2020},
  url={https://arxiv.org/abs/2005.01643}
}