Supporting multiple user types with a multimodal dialog agent

Michael Groble*, Will Thompson

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent research has addressed the problem of formulating a dialog agent as a partially observable Markov decision process (POMDP), and learning a dialog policy that is optimal given the particular characteristics of the transition, observation and reward functions of the POMDP. This paper addresses the problem of trying to learn a small set of dialog agent policies that provide near-optimal behavior over a wide range of variations in POMDPs, reflecting different user preferences and environment characteristics. We show for a very simple dialog, we can cover a large number of simulated users to within 10% of their optimal return using fewer than 5% of the individual optimal policies.

Original languageEnglish (US)
Title of host publicationProceedings - 2007 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2007
Pages329-332
Number of pages4
DOIs
StatePublished - Dec 1 2007
Event2007 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2007 - Silicon Valley, CA, United States
Duration: Nov 2 2007Nov 5 2007

Other

Other2007 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Workshops, WI-IAT Workshops 2007
CountryUnited States
CitySilicon Valley, CA
Period11/2/0711/5/07

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications

Cite this