• DOI:10.18653/v1/D18-1253
Corpus ID: 5041395

Subgoal Discovery for Hierarchical Dialogue Policy Learning

@article{Tang2018SubgoalDF,
  title={Subgoal Discovery for Hierarchical Dialogue Policy Learning},
  author={Da Tang and Xiujun Li and Jianfeng Gao and C. Wang and L. Li and T. Jebara},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.07855}
}

• Da 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… Expand

View on ACL

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed