Hybrid Reinforcement/Supervised Learning for Dialogue Policies from COMMUNICATOR Data (2005)
| Venue: | In IJCAI workshop on Knowledge and Reasoning in Practical Dialogue Systems |
| Citations: | 50 - 18 self |
BibTeX
@INPROCEEDINGS{Henderson05hybridreinforcement/supervised,
author = {James Henderson and Oliver Lemon and Kallirroi Georgila},
title = {Hybrid Reinforcement/Supervised Learning for Dialogue Policies from COMMUNICATOR Data},
booktitle = {In IJCAI workshop on Knowledge and Reasoning in Practical Dialogue Systems},
year = {2005}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
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.
