Reinforcement Learning for Spoken Dialogue Systems
Satinder Pal Singh, Michael J. Kearns, Diane J. Litman, Marilyn A. Walker · 1999
Recently, a number of authors have proposed treating dialogue systems as Markov decision processes (MDPs). However, the practical application of MDP algorithms to dialogue systems faces a number of severe technical challenges. We have built a general software tool (RLDS, for Reinforcement Learning for Dialogue Systems) based on the MDP framework, and have applied it to dialogue corpora gathered from two dialogue systems built at AT&T Labs. Our experiments demonstrate that RLDS holds promise as a tool for "browsing" and understanding correlations in complex, temporally dependent dialogue corpora. 1 Introduction Systems in which human users speak to a computer in order to achieve a goal are called spoken dialogue systems. Such systems are some of the few realized examples of openended, real-time, goal-oriented interaction between humans and computers, and are therefore an important and exciting testbed for AI and machine learning research. Spoken dialogue systems typically integrate ma...