@inproceedings{dorbdynamicallyoptimizingmultiplerewards,
  title = {DORB: Dynamically Optimizing Multiple Rewards with Bandits},
  author = {Ramakanth Pasunuru and Han Guo and Mohit Bansal},
  year = {2020},
  booktitle = {EMNLP 2020 11},
  eprint = {2011.07635},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2011.07635v1},
}