CUED Publications database

Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning

Budzianowski, P and Ultes, S and Su, P-H and Mrkšić, N and Wen, T-H and Casanueva, I and Rojas-Barahona, L and Gašić, M Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning. (Unpublished)

Full text not available from this repository.

Abstract

Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for modelling such dialogues. In this paper, we focus on the under-explored problem of multi-domain dialogue management. First, we propose a new method for hierarchical reinforcement learning using the option framework. Next, we show that the proposed architecture learns faster and arrives at a better policy than the existing flat ones do. Moreover, we show how pretrained policies can be adapted to more complex systems with an additional set of new actions. In doing that, we show that our approach has the potential to facilitate policy optimisation for more sophisticated multi-domain dialogue systems.

Item Type: Article
Uncontrolled Keywords: cs.CL cs.CL cs.AI
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:25
Last Modified: 27 Jul 2017 05:26
DOI: