Sciweavers

Share
JAIR
2002

Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System

11 years 5 months ago
Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a dialogue policy, which addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We report on the design, construction and empirical evaluation of NJFun, an experimental spoken dialogue system that provides users with access to information about fun things to do in New Jersey. Our results show that by optimizing its performance via reinforcement learning, NJFun measurably improves system performance.
Satinder P. Singh, Diane J. Litman, Michael J. Kea
Added 22 Dec 2010
Updated 22 Dec 2010
Type Journal
Year 2002
Where JAIR
Authors Satinder P. Singh, Diane J. Litman, Michael J. Kearns, Marilyn A. Walker
Comments (0)
books