@article{gapincreasingpolicyevaluationfor,
  title = {Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning},
  author = {Tadashi Kozuno and Dongqi Han and Kenji Doya},
  year = {2019},
  eprint = {1906.07586},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1906.07586v1},
}