@article{whatwouldpidoimitationlearningviaoff,
  title = {What Would pi* Do?: Imitation Learning via Off-Policy Reinforcement Learning},
  author = {Siddharth Reddy and Anca D. Dragan and Sergey Levine},
  year = {2018},
  url = {https://openreview.net/forum?id=B1excoAqKQ},
}