Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems

Pei-Hao Su, David Vandyke, Milica Gašić, Nikola Mrkšić, Tsung-Hsien Wen, Steve Young


Anthology ID:
W15-4655
Volume:
Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2015
Address:
Prague, Czech Republic
Editors:
Alexander Koller, Gabriel Skantze, Filip Jurcicek, Masahiro Araki, Carolyn Penstein Rose
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
417–421
Language:
URL:
https://aclanthology.org/W15-4655
DOI:
10.18653/v1/W15-4655
Bibkey:
Cite (ACL):
Pei-Hao Su, David Vandyke, Milica Gašić, Nikola Mrkšić, Tsung-Hsien Wen, and Steve Young. 2015. Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems. In Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 417–421, Prague, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems (Su et al., SIGDIAL 2015)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-dup-bibkey/W15-4655.pdf