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}
}
  • D. Tang, Xiujun Li, +3 authors T. Jebara
  • Published 2018
  • Computer Science
  • ArXiv
  • 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
    32 Citations

    Figures, Tables, and Topics from this paper

    Paper Mentions

    News Article
    Meta Dialogue Policy Learning
    • 1
    • PDF
    A hierarchical approach for efficient multi-intent dialogue policy learning
    Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
    • 1
    • PDF
    Transfer Learning based Task-oriented Dialogue Policy for Multiple Domains using Hierarchical Reinforcement Learning
    • PDF
    Structured Hierarchical Dialogue Policy with Graph Neural Networks
    • PDF
    Hierarchical Reinforcement Learning for Open-Domain Dialog
    • 11
    • PDF

    References

    SHOWING 1-10 OF 50 REFERENCES
    Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
    • 98
    • PDF
    Integrating planning for task-completion dialogue policy learning
    • 78
    • PDF
    End-to-End Reinforcement Learning of Dialogue Agents for Information Access
    • 219
    • PDF
    A User Simulator for Task-Completion Dialogues
    • 79
    • PDF
    End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
    • 33
    • PDF
    Distributed dialogue policies for multi-domain statistical dialogue management
    • 37
    • PDF
    Scaling up deep reinforcement learning for multi-domain dialogue systems
    • 40
    • PDF
    Iterative policy learning in end-to-end trainable task-oriented neural dialog models
    • Bing Liu, I. Lane
    • Computer Science
    • 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
    • 2017
    • 54
    • PDF
    Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density
    • 434
    • PDF