@inproceedings{learninggaussianpoliciesfromsmoothed,
  title = {Learning Gaussian Policies from Smoothed Action Value Functions},
  author = {Ofir Nachum and Mohammad Norouzi and George Tucker and Dale Schuurmans},
  year = {2018},
  booktitle = {ICLR 2018 1},
  url = {https://openreview.net/forum?id=B1nLkl-0Z},
}