3 years ago

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning.

Jianfeng Gao, Kam-Fai Wong, Shang-Yu Su, Baolin Peng, Xiujun Li, Jingjing Liu

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the world model, to mimic real user response and generate simulated experience. During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience. The effectiveness of our approach is demonstrated on a movie-ticket booking task in both simulated and human-in-the-loop settings.

Publisher URL: http://arxiv.org/abs/1801.06176

DOI: arXiv:1801.06176v3

You might also like
Never Miss Important Research

Researcher is an app designed by academics, for academics. Create a personalised feed in two minutes.
Choose from over 15,000 academics journals covering ten research areas then let Researcher deliver you papers tailored to your interests each day.

  • Download from Google Play
  • Download from App Store
  • Download from AppInChina

Researcher displays publicly available abstracts and doesn’t host any full article content. If the content is open access, we will direct clicks from the abstracts to the publisher website and display the PDF copy on our platform. Clicks to view the full text will be directed to the publisher website, where only users with subscriptions or access through their institution are able to view the full article.