Hierarchical reinforcement learning for composite-task dialogues

As in many complex text-based scenarios, a conversation can often be decomposed into multiple parts, each taking care of a subtopic or subtask that contributes to the success of the whole dialogue. An example is a travel assistant, which can converse with a user to deal with subtasks like hotel reservation, air ticket purchase, etc. In this talk, we will show how hierarchical deep reinforcement learning can be a useful framework for managing such "composite-task dialogues": (1) more efficient policy optimization with given subtasks; and (2) discovery of dialogue subtasks from corpus in an unsupervised way.