Dynamic Dialogue Policy for Continual Reinforcement Learning

Christian Geishauser, Carel van Niekerk, Hsien-chin Lin, Nurul Lubis, Michael Heck, Shutong Feng, Milica Gašić


Abstract
Continual learning is one of the key components of human learning and a necessary requirement of artificial intelligence. As dialogue can potentially span infinitely many topics and tasks, a task-oriented dialogue system must have the capability to continually learn, dynamically adapting to new challenges while preserving the knowledge it already acquired. Despite the importance, continual reinforcement learning of the dialogue policy has remained largely unaddressed. The lack of a framework with training protocols, baseline models and suitable metrics, has so far hindered research in this direction. In this work we fill precisely this gap, enabling research in dialogue policy optimisation to go from static to dynamic learning. We provide a continual learning algorithm, baseline architectures and metrics for assessing continual learning models. Moreover, we propose the dynamic dialogue policy transformer (DDPT), a novel dynamic architecture that can integrate new knowledge seamlessly, is capable of handling large state spaces and obtains significant zero-shot performance when being exposed to unseen domains, without any growth in network parameter size. We validate the strengths of DDPT in simulation with two user simulators as well as with humans.
Anthology ID:
2022.coling-1.21
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
266–284
Language:
URL:
https://aclanthology.org/2022.coling-1.21
DOI:
Bibkey:
Cite (ACL):
Christian Geishauser, Carel van Niekerk, Hsien-chin Lin, Nurul Lubis, Michael Heck, Shutong Feng, and Milica Gašić. 2022. Dynamic Dialogue Policy for Continual Reinforcement Learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 266–284, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Dynamic Dialogue Policy for Continual Reinforcement Learning (Geishauser et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.21.pdf