Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning

2016/06/08 by Tiancheng Zhao, Zhao, Tiancheng, Maxine Eskénazi +1 · 11 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multi-Agent Systems and Negotiation #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1606.02560

openalex publication_date 2016/06/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent Q-Networks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state.

Citations

• A Neural Conversational Model
• Long Short-Term Memory
• Prioritized Experience Replay
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Partially observable Markov decision processes for spoken dialog systems
• Language Understanding for Text-based Games Using Deep Reinforcement\n Learning

Cited by

• Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
• Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
• Zero-Shot Dialog Generation with Cross-Domain Latent Actions
• Deep Reinforcement Learning for Multi-Domain Dialogue Systems
• Optimizing Conversational Product Recommendation via Reinforcement Learning
• Learning to Ask Medical Questions using Reinforcement Learning
• Adversarial Learning of Task-Oriented Neural Dialog Models
• The Technological Gap Between Virtual Assistants and Recommendation\n Systems
• Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems
• Variational Reward Estimator Bottleneck: Learning Robust Reward\n Estimator for Multi-Domain Task-Oriented Dialog
• Interactive Teaching for Conversational AI

Related

• Hybrid Supervised Reinforced Model for Dialogue Systems
• Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue
• Deep Reinforcement Learning for On-line Dialogue State Tracking
• End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
• End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning