@conference{GuLilGhaTurLev17,
  title = {Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic},
  booktitle = {Proceedings International Conference on Learning Representations (ICLR)},
  month = apr,
  year = {2017},
  author = {Gu, Shixiang and Lillicrap, Timothy and Ghahramani, Zoubin and Turner, Richard E. and Levine, Sergey},
  url = {https://openreview.net/pdf?id=rkE3y85ee},
  month_numeric = {4}
}