Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

Chang Tian, Wenpeng Yin, Marie-Francine Moens

BibTeX
@inproceedings{tian2022anti,
  author = {Chang Tian and Wenpeng Yin and Marie-Francine Moens},
  title = {{Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System}},
  booktitle = {Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2022},
  doi = {10.18653/v1/2022.findings-naacl.43},
}
Figure