@inproceedings{residuallosspredictionreinforcement,
  title = {Residual Loss Prediction: Reinforcement Learning With No Incremental Feedback},
  author = {Hal Daumé III and John Langford and Amr Sharaf},
  year = {2018},
  booktitle = {ICLR 2018 1},
  url = {https://openreview.net/forum?id=HJNMYceCW},
}