@article{TosCarPet21,
  title = {Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)},
  volume = {44},
  number = {10},
  pages = {5996--6010},
  month = oct,
  year = {2021},
  note = {*early access},
  author = {Tosatto, S. and Carvalho, J. and Peters, J.},
  doi = {10.1109/TPAMI.2021.3088063},
  month_numeric = {10}
}