Jianfeng Gao, Kam-Fai Wong, Baolin Peng, Jingjing Liu, Xiujun Li. Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning. In Iryna Gurevych, Yusuke Miyao, editors, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers. pages 2182-2192, Association for Computational Linguistics, 2018. [doi]
@inproceedings{GaoWPLL18,
title = {Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning},
author = {Jianfeng Gao and Kam-Fai Wong and Baolin Peng and Jingjing Liu and Xiujun Li},
year = {2018},
url = {https://aclanthology.info/papers/P18-1203/p18-1203},
researchr = {https://researchr.org/publication/GaoWPLL18},
cites = {0},
citedby = {0},
pages = {2182-2192},
booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers},
editor = {Iryna Gurevych and Yusuke Miyao},
publisher = {Association for Computational Linguistics},
isbn = {978-1-948087-32-2},
}