@conference{Guetal17,
  title = {Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning},
  booktitle = {Advances in Neural Information Processing Systems 30 (NIPS 2017)},
  pages = {3849--3858},
  editors = {Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.},
  publisher = {Curran Associates, Inc.},
  month = dec,
  year = {2017},
  author = {Gu, S. and Lillicrap, T. and Turner, R. E. and Ghahramani, Z. and Sch{\"o}lkopf, B. and Levine, S.},
  url = {http://papers.nips.cc/paper/6974-interpolated-policy-gradient-merging-on-policy-and-off-policy-gradient-estimation-for-deep-reinforcement-learning.pdf},
  month_numeric = {12}
}