Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2018)
摘要
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/actions generated by dialogue agents from responses/actions by experts. Then, we incorporate the discriminator as another critic into the advantage actor-critic (A2C) framework, to encourage the dialogue agent to explore state-action within the regions where the agent takes actions similar to those of the experts. Experimental results in a movie-ticket booking domain show that the proposed Adversarial A2C can accelerate policy exploration efficiently.
更多查看译文
关键词
task-completion dialogue,reward function,adversarial learning,policy learning,reinforcement learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络