Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning

Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning Lu Chen author Xiang Zhou author Cheng Chang author Runzhe Yang author Kai Yu author 2017-09 text Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing Martha Palmer editor Rebecca Hwa editor Sebastian Riedel editor Association for Computational Linguistics Copenhagen, Denmark conference publication chen-etal-2017-agent 10.18653/v1/D17-1260 https://aclanthology.org/D17-1260/ 2017-09 2454 2464