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

Satinder P. Singh Diane J. Litman Michael J. Kearns Marilyn A. Walker Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System. 105-133 2002 16 J. Artif. Intell. Res. (JAIR) http://www.cs.washington.edu/research/jair/abstracts/singh02a.html db/journals/jair/jair16.html#SinghLKW02