@inproceedings{rewardlearningfromhumanpreferencesand,
  title = {Reward learning from human preferences and demonstrations in Atari},
  author = {Borja Ibarz and Jan Leike and Tobias Pohlen and Geoffrey Irving and Shane Legg and Dario Amodei},
  year = {2018},
  booktitle = {NeurIPS 2018 12},
  eprint = {1811.06521},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1811.06521v1},
}