Abstract
In Chapter 7 we showed that Reinforcement Learning (RL) based strategies can significantly outperform supervised strategies, in interaction with a simulated environment. The ultimate test for dialogue strategies, however, is how they perform with real users. For real users it is often difficult to complete even relatively simple tasks using automated dialogue systems.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Rieser, V., Lemon, O. (2011). Comparing Reinforcement and Supervised Learning of Dialogue Policies with Real Users. In: Reinforcement Learning for Adaptive Dialogue Systems. Theory and Applications of Natural Language Processing. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24942-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-24942-6_8
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24941-9
Online ISBN: 978-3-642-24942-6
eBook Packages: Computer ScienceComputer Science (R0)