Fast reinforcement learning of dialog strategies

Authors:
D. Goddeau;J. Pineau
Affiliations:
Cambridge Res. Lab., Compaq Comput. Corp., MA, USA;-
Venue:
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02
Year:
2000

Citing 0
Cited 7

A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies

The Knowledge Engineering Review
Partially observable Markov decision processes for spoken dialog systems

Computer Speech and Language
Automatic learning of dialogue strategy using dialogue simulation and reinforcement learning

HLT '02 Proceedings of the second international conference on Human Language Technology Research
Evaluating user simulations with the Cramér-von Mises divergence

Speech Communication
Hybrid reinforcement/supervised learning of dialogue policies from fixed data sets

Computational Linguistics
Using knowledge of misunderstandings to increase the robustness of spoken dialogue systems

Knowledge-Based Systems
Fast reinforcement learning of dialogue policies using stable function approximation

IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 (MDPs) to the problem of learning the dialog strategies. It extends work done at AT&T 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.