@article{anonparametricoffpolicypolicygradient,
  title = {A Nonparametric Off-Policy Policy Gradient},
  author = {Samuele Tosatto and Joao Carvalho and Hany Abdulsamad and Jan Peters},
  year = {2020},
  eprint = {2001.02435},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2001.02435v3},
}