Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning.

Baolin Peng Xiujun Li Jianfeng Gao 0001 Jingjing Liu 0001 Yun-Nung Chen Kam-Fai Wong Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning. 6149-6153 2018 ICASSP https://doi.org/10.1109/ICASSP.2018.8461918 conf/icassp/2018 db/conf/icassp/icassp2018.html#PengLGLCW18