Fast reinforcement learning of dialogue policies using stable function approximation

Authors:
Matthias Denecke;Kohji Dohsaka;Mikio Nakano
Affiliations:
Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi Kanagawa;Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi Kanagawa;Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi Kanagawa
Venue:
IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
Year:
2004

Citing 5
Cited 3

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Learning optimal dialogue strategies: a case study of a spoken dialogue agent for email

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Fast reinforcement learning of dialog strategies

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02
Optimizing dialogue management with reinforcement learning: experiments with the NJFun system

Journal of Artificial Intelligence Research
Reinforcement learning: a survey

Journal of Artificial Intelligence Research

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

Computational Linguistics
Evaluation of a hierarchical reinforcement learning spoken dialogue system

Computer Speech and Language
Spatially-aware dialogue control using hierarchical reinforcement learning

ACM Transactions on Speech and Language Processing (TSLP)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a method to speed up reinforcement learning of policies for spoken dialogue systems. This is achieved by combining a coarse grained abstract representation of states and actions with learning only in frequently visited states. The value of unsampled states is approximated by a linear interpolation of known states. Experiments show that the proposed method effectively optimizes dialogue strategies for frequently visited dialogue states.