An I-POMDP Based Multi-Agent Architecture for Dialogue Tutoring

DOI

10.2991/icaicte.2013.96How to use a DOI?

Keywords

Computer based education, dialogue system, interactive partially observable Markov decision process.

Abstract

Dialogue systems have been widely con-sidered as useful tools for education. The challenging tasks in developing a dia-logue tutoring system include correctly interpreting student input and choosing appropriate responses. In this paper, we present a two-agent architecture for ad-dressing the challenges. The two agents are learner agents in a reinforcement learning algorithm, which is based on the interactive partially observable Markov decision process (I-POMDP). One agent learns user behavior for disambiguating student input, and the other learns the optimal teaching strategies.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fangju Wang
PY  - 2013/08
DA  - 2013/08
TI  - An I-POMDP Based Multi-Agent Architecture for Dialogue Tutoring
BT  - Proceedings of the 2013 International Conference on Advanced ICT and Education
PB  - Atlantis Press
SP  - 469
EP  - 472
SN  - 1951-6851
UR  - https://doi.org/10.2991/icaicte.2013.96
DO  - 10.2991/icaicte.2013.96
ID  - Wang2013/08
ER  -