Fast Reinforcement Learning of Dialog Strategies

David Goddeau and Joelle Pineau
IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP2000), June, 2000.

  • Adobe portable document format (pdf) (107KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Dialog management is a critical component of an effective spoken language application. It is also one of the most difficult and time consuming to engineer. This paper examines the application of reinforcement learning and Markov Decision Processes (MDP's) to the problem of learning the dialog strategies. It extends work done at AT&T [1] [2] in two directions. First it examines the ability of RL to learn optimal strategies in the presence of speech recognition errors. Second, it describes a technique for reducing the amount of data required to train these models. This is significant as the difficulty of training MDP-based dialog managers is a serious roadblock to deploying them in realistic applications.

reinforcement learning, dialog models, dialogue

Sponsor: Compaq Computers Corp., Cambridge Research Lab

Text Reference
David Goddeau and Joelle Pineau, "Fast Reinforcement Learning of Dialog Strategies," IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP2000), June, 2000.

BibTeX Reference
   author = "David Goddeau and Joelle Pineau",
   title = "Fast Reinforcement Learning of Dialog Strategies",
   booktitle = "IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP2000)",
   month = "June",
   year = "2000",