Hybrid Supervised Reinforced Model for Dialogue Systems

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.

11 pages, 9 figures

References in corpus (8)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
• BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
• Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
• RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection