@article{deepreinforcementlearningfrompolicy,
  title = {Deep Reinforcement Learning from Policy-Dependent Human Feedback},
  author = {Dilip Arumugam and Jun Ki Lee and Sophie Saskin and Michael L. Littman},
  year = {2019},
  eprint = {1902.04257},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1902.04257v1},
}