Abstract
This paper presents a recurrent hybrid model and training procedure for task-oriented dialogue systems based on Deep Recurrent Q-Networks (DRQN). The model copes with both tasks required for Dialogue Management: State Tracking and Decision Making. It is based on modeling Human-Machine interaction into a latent representation embedding an interaction context to guide the discussion. The model achieves greater performance, learning speed and robustness than a non-recurrent baseline. Moreover, results allow interpreting and validating the policy evolution and the latent representations information-wise.