@article{dqntamerhumanintheloopreinforcement,
  title = {DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback},
  author = {Riku Arakawa and Sosuke Kobayashi and Yuya Unno and Yuta Tsuboi and Shin-ichi Maeda},
  year = {2018},
  eprint = {1810.11748},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1810.11748v1},
}