@article{qxploreqlearningexplorationbymaximizing,
  title = {Reward Prediction Error as an Exploration Objective in Deep RL},
  author = {Riley Simmons-Edler and Ben Eisner and Daniel Yang and Anthony Bisulco and Eric Mitchell and Sebastian Seung and Daniel Lee},
  year = {2019},
  eprint = {1906.08189},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1906.08189v5},
}