 |
    |
An Adaptive Dialogue System with Online Dialogue Policy Learning
Alexandros Papangelis1, 2, Nikolaos Kouroupas3, Vangelis Karkaletsis1, and Fillia Makedon2
1National Centre for Scientific Research “Demokritos”, Institute of Informatics and Telecommunications, Greece
[email protected]
[email protected]
2University of Texas at Arlington, Department of Computer Science and Engineering, USA
[email protected]
[email protected]
3University of Piraeus, Department of Informatics, Greece
[email protected]
Abstract. In this work we present an architecture for Adaptive Dialogue Systems and a novel system that serves as a Museum Guide. It employs several online Reinforcement Learning (RL) techniques to achieve adaptation to the environment as well as to different users. Not many systems have been proposed that apply online RL methods and this is one of the first to fully describe an Adaptive Dialogue System with online dialogue policy learning. We evaluate our system through user simulations and compare the several implemented algorithms on a simple scenario.
Keywords: Adaptive Dialogue Systems, Reinforcement Learning
LNAI 7297, p. 323 ff.
[email protected]
© Springer-Verlag Berlin Heidelberg 2012