@article{optionganlearningjointrewardpolicy,
  title = {OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning},
  author = {Peter Henderson and Wei-Di Chang and Pierre-Luc Bacon and David Meger and Joelle Pineau and Doina Precup},
  year = {2017},
  eprint = {1709.06683},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1709.06683v2},
}