Subgoal Discovery for Hierarchical Dialogue Policy Learning
@article{Tang2018SubgoalDF, title={Subgoal Discovery for Hierarchical Dialogue Policy Learning}, author={D. Tang and Xiujun Li and Jianfeng Gao and C. Wang and L. Li and T. Jebara}, journal={ArXiv}, year={2018}, volume={abs/1804.07855} }
Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning. First, given successful example dialogues, we propose the Subgoal Discovery Network (SDN) to divide a complex goal-oriented task into a set of simpler subgoals in an unsupervised fashion… CONTINUE READING
Supplemental Video
Figures, Tables, and Topics from this paper
Paper Mentions
News Article
32 Citations
A hierarchical approach for efficient multi-intent dialogue policy learning
- Computer Science
- Multimedia Tools and Applications
- 2020
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
- Computer Science
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- 2020
- 1
- PDF
Transfer Learning based Task-oriented Dialogue Policy for Multiple Domains using Hierarchical Reinforcement Learning
- Computer Science
- 2020 International Joint Conference on Neural Networks (IJCNN)
- 2020
- PDF
Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System
- Computer Science
- ArXiv
- 2020
- 3
- PDF
Hierarchical Reinforcement Learning for Open-Domain Dialog
- Computer Science, Mathematics
- AAAI
- 2020
- 11
- PDF
References
SHOWING 1-10 OF 50 REFERENCES
Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
- Computer Science
- EMNLP
- 2017
- 98
- PDF
End-to-End Reinforcement Learning of Dialogue Agents for Information Access
- Computer Science
- ACL
- 2017
- 219
- PDF
Efficient Exploration for Dialogue Policy Learning with BBQ Networks & Replay Buffer Spiking
- 2016
- 49
- PDF
End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
- Computer Science
- ArXiv
- 2017
- 33
- PDF
Distributed dialogue policies for multi-domain statistical dialogue management
- Computer Science
- 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2015
- 37
- PDF
Scaling up deep reinforcement learning for multi-domain dialogue systems
- Computer Science
- 2017 International Joint Conference on Neural Networks (IJCNN)
- 2017
- 40
- PDF
Iterative policy learning in end-to-end trainable task-oriented neural dialog models
- Computer Science
- 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
- 2017
- 54
- PDF
Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density
- Computer Science
- ICML
- 2001
- 434
- PDF