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

• Published in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6149 - 6153
• Main Authors: Peng, Baolin, Li, Xiujun, Gao, Jianfeng, Liu, Jingjing, Chen, Yun-Nung, Wong, Kam-Fai
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2018
• Subjects: adversarial learning; Gallium nitride; Learning (artificial intelligence); Motion pictures; Natural languages; policy learning; reinforcement learning; reward function; Task analysis; task-completion dialogue; Training; Trajectory

This paper presents a new method - adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems. Inspired by generative adversarial networks (GAN), we train a discriminator to differentiate responses...