@article{learningfromextremebanditfeedback,
  title = {Learning from eXtreme Bandit Feedback},
  author = {Romain Lopez and Inderjit S. Dhillon and Michael. I. Jordan},
  year = {2020},
  eprint = {2009.12947},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2009.12947v2},
}