paper-with-me

홈 › Papers

Dynamic Dialogue Policy for Continual Reinforcement Learning

2022-04-12 · COLING 2022 10 · Christian Geishauser, Carel van Niekerk, Nurul Lubis, Michael Heck, Hsien-Chin Lin, Shutong Feng, Milica Gašić

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.

📄 PDF Abstract BibTeX arXiv:2204.05928

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems

2026-04-07 · Hui Wang, Fafa Zhang, Meng Liu, Xiangyu Chen 외 arxiv

To address the challenge that current dialogue policy planning methods struggle to dynamically adapt to diverse user characteristics, this paper proposes a User Portrait based Nested Rollout Policy Adaptation (UP-NRPA) o…

Reinforcement Learning

Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

2022-07-24 · Findings (NAACL) 2022 7 · Chang Tian, Wenpeng Yin, Marie-Francine Moens

A dialogue policy module is an essential part of task-completion dialogue systems. Recently, increasing interest has focused on reinforcement learning (RL)-based dialogue policy. Its favorable performance and wise action…

Reinforcement Learning (RL)

Guided Dialogue Policy Learning without Adversarial Learning in the Loop

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Ziming Li, Sungjin Lee, Baolin Peng, Jinchao Li 외

Reinforcement learning methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning

2022-02-28 · Wai-Chung Kwan, Hongru Wang, Huimin Wang, Kam-Fai Wong

Dialogue Policy Learning is a key component in a task-oriented dialogue system (TDS) that decides the next action of the system given the dialogue state at each turn. Reinforcement Learning (RL) is commonly chosen to lea…

Dialogue ManagementManagementReinforcement Learning (RL)Survey

Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training

2026-08-04 · Yibei Liu, Jiajun Chen, Qianle Zhang, Tangyue Jin 외 arxiv

Reinforcement fine-tuning (RFT) is widely believed to inherently resist catastrophic forgetting in continual post-training of multimodal large language models. Under pronounced task distributional shifts, however, forget…