@article{pitfallsoflearningarewardfunctiononline,
  title = {Pitfalls of learning a reward function online},
  author = {Stuart Armstrong and Jan Leike and Laurent Orseau and Shane Legg},
  year = {2020},
  eprint = {2004.13654},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2004.13654v1},
}