@article{learningtogeneralizefromsparseand,
  title = {Learning to Generalize from Sparse and Underspecified Rewards},
  author = {Rishabh Agarwal and Chen Liang and Dale Schuurmans and Mohammad Norouzi},
  year = {2019},
  eprint = {1902.07198},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1902.07198v4},
}