Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning Shang-Yu Su author Xiujun Li author Jianfeng Gao author Jingjing Liu author Yun-Nung Chen author 2018-oct-nov text Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Ellen Riloff editor David Chiang editor Julia Hockenmaier editor Jun’ichi Tsujii editor Association for Computational Linguistics Brussels, Belgium conference publication su-etal-2018-discriminative 10.18653/v1/D18-1416 https://aclanthology.org/D18-1416/ 2018-oct-nov 3813 3823