Ryuichi Takanobu, Runze Liang, Minlie Huang. Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition. In Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel R. Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020. pages 625-638, Association for Computational Linguistics, 2020. [doi]
@inproceedings{TakanobuLH20,
title = {Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition},
author = {Ryuichi Takanobu and Runze Liang and Minlie Huang},
year = {2020},
url = {https://www.aclweb.org/anthology/2020.acl-main.59/},
researchr = {https://researchr.org/publication/TakanobuLH20},
cites = {0},
citedby = {0},
pages = {625-638},
booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020},
editor = {Dan Jurafsky and Joyce Chai and Natalie Schluter and Joel R. Tetreault},
publisher = {Association for Computational Linguistics},
isbn = {978-1-952148-25-5},
}