Google Research

Interactive reinforcement learning for task-oriented dialogue management

  • Pararth Shah
  • Dilek Hakkani-Tur
  • Larry Heck
Workshop on Deep Learning for Action and Interaction, NIPS 2016 (2016)

Abstract

Dialogue management is the component of a dialogue system that determines the optimal action for the system to take at each turn. An important consideration for dialogue managers is the ability to adapt to new user behaviors unseen during training. In this paper, we investigate policy gradient based methods for interactive reinforcement learning where the agent receives action-specific feedback from the user and incorporates this feedback into its policy. We show that using the feedback to directly shape the policy enables a dialogue manager to learn new interactions faster compared to interpreting the feedback as a reward value.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work