@article{learningpoliciesfromselfplaywithpolicy,
  title = {Learning Policies from Self-Play with Policy Gradients and MCTS Value Estimates},
  author = {Dennis J. N. J. Soemers and Éric Piette and Matthew Stephenson and Cameron Browne},
  year = {2019},
  eprint = {1905.05809},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1905.05809v1},
}