Subgoal Discovery For Hierarchical Dialogue Policy Learning | Awesome LLM Papers Add your paper to Awesome LLM Papers

Subgoal Discovery For Hierarchical Dialogue Policy Learning

da Tang, Xiujun Li, Jianfeng Gao, Chong Wang, Lihong Li, Tony Jebara . Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing 2018 – 42 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Agentic Compositional Generalization EMNLP Interdisciplinary Approaches Reinforcement Learning

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. We then use these subgoals to learn a multi-level policy by hierarchical reinforcement learning. We demonstrate our method by building a dialogue agent for the composite task of travel planning. Experiments with simulated and real users show that our approach performs competitively against a state-of-the-art method that requires human-defined subgoals. Moreover, we show that the learned subgoals are often human comprehensible.

Similar Work