@misc{reinforcementlearningrlhumanpreferences2017,
  title = {{Deep reinforcement learning from human preferences}},
  author = {Paul Christiano and Jan Leike and Tom B. Brown and Miljan Martic and Shane Legg and Dario Amodei},
  year = {2017},
  eprint = {1706.03741},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1706.03741}
}
