Reward Estimation with Scheduled Knowledge Distillation for Dialogue Policy Learning | |
Qiu JY(邱俊彦)1,2; Haidong Zhang2; Yiping Yang2 | |
刊名 | Connection Science |
2023 | |
卷号 | 35期号:1页码:2174078 |
关键词 | reinforcement learning dialogue policy learning curriculum learning knowledge distillation |
英文摘要 | Formulating dialogue policy as a reinforcement learning (RL) task enables a dialogue system to act optimally by interacting with humans. However, typical RLbased methods normally suffer from challenges such as sparse and delayed reward problems. Besides, with user goal unavailable in real scenarios, the reward estimator is unable to generate reward reflecting action validity and task completion. Those issues may slow down and degrade the policy learning significantly. In this paper, we present a novel scheduled knowledge distillation framework for dialogue policy learning, which trains a compact student reward estimator by distilling the prior knowledge of user goals from a large teacher model. To further improve the stability of dialogue policy learning, we propose to leverage self-paced learning to arrange meaningful training order for the student reward estimator. Comprehensive experiments on Microsoft Dialogue Challenge and MultiWOZ datasets indicate that our approach significantly accelerates the learning speed, and the task-completion success rate can be improved from 0.47%∼9.01% compared with several strong baselines. |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/56657] |
专题 | 综合信息系统研究中心_视知觉融合及其应用 |
通讯作者 | Qiu JY(邱俊彦) |
作者单位 | 1.University of Chinese Academy of Sciences 2.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Qiu JY,Haidong Zhang,Yiping Yang. Reward Estimation with Scheduled Knowledge Distillation for Dialogue Policy Learning[J]. Connection Science,2023,35(1):2174078. |
APA | Qiu JY,Haidong Zhang,&Yiping Yang.(2023).Reward Estimation with Scheduled Knowledge Distillation for Dialogue Policy Learning.Connection Science,35(1),2174078. |
MLA | Qiu JY,et al."Reward Estimation with Scheduled Knowledge Distillation for Dialogue Policy Learning".Connection Science 35.1(2023):2174078. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论