https://scholars.lib.ntu.edu.tw/handle/123456789/559426
Title: | Discriminative deep Dyna-Q: Robust planning for dialogue policy learning | Authors: | Su, S.-Y. Li, X. Gao, J. Liu, J. YUN-NUNG CHEN |
Issue Date: | 2020 | Start page/Pages: | 3813-3823 | Source: | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 | 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.1 © 2018 Association for Computational Linguistics |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85062083317&partnerID=40&md5=f4397ee8a77a664510b0b84cbf926754 https://scholars.lib.ntu.edu.tw/handle/123456789/559426 |
SDG/Keyword: | Deep learning; Natural language processing systems; User experience; Changing environment; Domain extensions; Policy learning; Q algorithms; Robust planning; Training data; Quality control |
Appears in Collections: | 資訊工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.