.png){kind=icon}
返回
Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization
.png){kind=icon}
OA
AI
DOI：10.1162/tacl_a_00717.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Training a task-oriented dialogue policy using deep reinforcement learning is promising but requires extensive environment exploration. The amount of wasted invalid exploration makes policy learning inefficient. In this paper, we define and argue that dead-end states are important reasons for invalid exploration. When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn. We propose a Dead-end Detection and Resurrection (DDR) method that detects dead-end states in an efficient manner and provides a rescue action to guide and correct the exploration direction. To prevent dialogue policies from repeating errors, DDR also performs dialogue data augmentation by adding relevant experiences that include dead-end states and penalties into the experience pool. We first validate the dead-end detection reliability and then demonstrate the effectiveness and generality of the method across various domains through experiments on four public dialogue datasets.
期刊
T
IF:
6.9
论文数:
486
被引数:
5.7K
机构
引用论文
Seed Dispersal by Cassowaries (Casuarius casuarius) in North Queensland's Rainforests.png)
Biotropica
BiotropicaIF0
PREAI
分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Correction: Clinical Applicability and Cutoff Values for an Unstructured Neuropsychological Assessment Protocol for Older Adults with Low Formal EducationPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容