Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning
Journal
IEEE International Conference on Acoustics, Speech and Signal Processing
Journal Volume
2018-April
Pages
6149-6153
Date Issued
2018
Author(s)
Abstract
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.
SDGs
Type
conference paper