Hybrid Reinforcement/Supervised Learning for Dialogue Policies from COMMUNICATOR Data

Hybrid Reinforcement/Supervised Learning for Dialogue Policies from COMMUNICATOR Data (2005)

Cached

Download Links

by James Henderson , Oliver Lemon , Kallirroi Georgila

Venue:	In IJCAI workshop on Knowledge and Reasoning in Practical Dialogue Systems
Citations:	50 - 18 self

Versions

Version History

Metadata Version 2

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Hybrid Reinforcement/Supervised Learning for Dialogue Policies from COMMUNICATOR Data	user correction - Legacy Corrections
AUTHOR NAME	James Henderson	user correction - Legacy Corrections
AUTHOR AFFIL	School of Informatics; University of Edinburgh	user correction - Legacy Corrections
AUTHOR ADDR	2 Buccleuch Place, Edinburgh EH8 9LW, United Kingdom	user correction - Legacy Corrections
AUTHOR NAME	Oliver Lemon	user correction - Legacy Corrections
AUTHOR AFFIL	School of Informatics; University of Edinburgh	user correction - Legacy Corrections
AUTHOR ADDR	2 Buccleuch Place, Edinburgh EH8 9LW, United Kingdom	user correction - Legacy Corrections
AUTHOR NAME	Kallirroi Georgila	user correction - Legacy Corrections
AUTHOR AFFIL	School of Informatics; University of Edinburgh	user correction - Legacy Corrections
AUTHOR ADDR	2 Buccleuch Place, Edinburgh EH8 9LW, United Kingdom	user correction - Legacy Corrections
ABSTRACT	We propose a method for learning dialogue management policies from a fixed dataset. The method is designed for use with "Information State Update " (ISU)-based dialogue systems, which represent the state of a dialogue as a large set of features, resulting in a very large state space and a very large policy space. To address the problem that any fixed dataset will only provide information about small portions of these state and policy spaces, we propose a hybrid model which combines reinforcement learning (RL) with supervised learning.	user correction - Legacy Corrections
YEAR	2005	INFERENCE
VENUE	In IJCAI workshop on Knowledge and Reasoning in Practical Dialogue Systems	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	14 found	ParsCit 1.0