Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning

@inproceedings{Peng2017CompositeTD,
  title={Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning},
  author={Baolin Peng and Xiujun Li and L. Li and Jianfeng Gao and A. Çelikyilmaz and Sungjin Lee and K. Wong},
  booktitle={EMNLP},
  year={2017}
}
  • Baolin Peng, Xiujun Li, +4 authors K. Wong
  • Published in EMNLP 2017
  • Computer Science
    • Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks. For example, the agent needs to reserve a hotel and book a flight so that there leaves enough time for commute between arrival and hotel check-in. This paper addresses this challenge by formulating the task in the mathematical framework of options over Markov Decision Processes (MDPs), and proposing a hierarchical deep… CONTINUE READING
    View on ACL
    arxiv.org
    98 Citations
    Highly Influential Citations
    6
    Background Citations
    49
    Methods Citations
    26
    Results Citations
    1

    Figures, Tables, and Topics from this paper

    Figures and Tables

    Explore Further: Topics Discussed in This Paper

    98 Citations
    Citation Type

    Citation Type

    AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning
    • 5
    AgentGraph: Toward Universal Dialogue Management With Structured Deep Reinforcement Learning
    • 9
    • PDF
    Subgoal Discovery for Hierarchical Dialogue Policy Learning
    • 32
    • PDF
    Integrating planning for task-completion dialogue policy learning
    • 78
    • PDF
    Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition
    • 4
    • PDF
    A hierarchical approach for efficient multi-intent dialogue policy learning
    Meta Dialogue Policy Learning
    • 1
    • PDF
    Building Advanced Dialogue Managers for Goal-Oriented Dialogue Systems
    • 2
    • PDF
    Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
    • 1
    • PDF
    Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog
    • 22
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 69 REFERENCES
    Scaling up deep reinforcement learning for multi-domain dialogue systems
    • 40
    • PDF
    End-to-End Reinforcement Learning of Dialogue Agents for Information Access
    • 219
    • PDF
    Deep Reinforcement Learning for Dialogue Generation
    • 796
    • PDF
    Distributed dialogue policies for multi-domain statistical dialogue management
    • 37
    • PDF
    A User Simulator for Task-Completion Dialogues
    • 79
    • PDF
    End-to-end optimization of goal-driven and visually grounded dialogue systems
    • 98
    • PDF
    Hierarchical Reinforcement Learning for Spoken Dialogue Systems
    • 45
    • PDF
    Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning
    • 2,364
    • Highly Influential
    • PDF
    Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
    • 287
    • PDF
    End-to-End Task-Completion Neural Dialogue Systems
    • 229
    • PDF