Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu, Yun-Nung Chen


Abstract
This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning. To obviate DDQ’s high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data. Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning. The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent’s capability of adapting to a changing environment is tested.
Anthology ID:
D18-1416
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3813–3823
Language:
URL:
https://aclanthology.org/D18-1416
DOI:
10.18653/v1/D18-1416
Bibkey:
Cite (ACL):
Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu, and Yun-Nung Chen. 2018. Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3813–3823, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning (Su et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1416.pdf
Code
 MiuLab/D3Q +  additional community code