@inproceedings{taskcompletiondialoguepolicylearningvia,
  title = {Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network},
  author = {Sihan Wang and Kaijie Zhou and Kunfeng Lai and Jianping Shen},
  year = {2020},
  booktitle = {EMNLP 2020 11},
  url = {https://aclanthology.org/2020.emnlp-main.278},
}