.png){kind=icon}
返回
Reward estimation for dialogue policy optimisation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csl.2018.02.003.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Viewing dialogue management as a reinforcement learning task enables a system to learn to act optimally by maximising a reward function. This reward function is designed to induce the system behaviour required for the target application and for goal oriented applications, this usually means fulfilling the user's goal as efficiently as possible. However, in real-world spoken dialogue system applications, the reward is hard to measure because the user's goal is frequently known only to the user. Of course, the system can ask the user if the goal has been satisfied but this can be intrusive. Furthermore, in practice, the accuracy of the user's response has been found to be highly variable. This paper presents two approaches to tackling this problem. Firstly, a recurrent neural network is utilised as a task success predictor which is pre-trained from off-line data to estimate task success during subsequent on-line dialogue policy learning. Secondly, an on-line learning framework is described whereby a dialogue policy is jointly trained alongside a reward function modelled as a Gaussian process with active learning. This Gaussian process operates on a fixed dimension embedding which encodes each varying length dialogue. This dialogue embedding is generated in both a supervised and unsupervised fashion using different variants of a recurrent neural network. The experimental results demonstrate the effectiveness of both off-line and on-line methods. These methods enable practical on-line training of dialogue policies in real-world applications. (C) 2018 Published by Elsevier Ltd.
Keyword:
Dialogue systems
Reinforcement learning
Deep learning
Reward estimation
Gaussian process
Active learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
C
IF:
3.4
论文数:
1.5K
被引数:
2.6K
机构
引用论文
Short-term response to iron resupply in an iron-limited open ocean diatom reveals rapid decay of iron-responsive transcripts.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏
分享收藏
查看更多内容