@inproceedings{onlearningintrinsicrewardsforpolicy,
  title = {On Learning Intrinsic Rewards for Policy Gradient Methods},
  author = {Zeyu Zheng and Junhyuk Oh and Satinder Singh},
  year = {2018},
  booktitle = {NeurIPS 2018 12},
  eprint = {1804.06459},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1804.06459v2},
}