@inproceedings{adaptivedialogpolicylearningwith,
  title = {Adaptive Dialog Policy Learning with Hindsight and User Modeling},
  author = {Yan Cao and Keting Lu and Xiaoping Chen and Shiqi Zhang},
  year = {2020},
  booktitle = {SIGDIAL (ACL) 2020 7},
  eprint = {2005.03299},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2005.03299v1},
}