arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.06299cs.CLstat.ML
收藏

基于多目标强化学习的统计口语对话系统奖励平衡

Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning

University of Cambridge(剑桥大学)

Stefan Ultes, Paweł Budzianowski, Iñigo Casanueva, Nikola Mrkšić, Lina Rojas-Barahona, Pei-Hao Su, Tsung-Hsien Wen, Milica Gašić, Steve Young

摘要:

强化学习被广泛用于对话策略优化,其中奖励函数通常由多于一个分量组成,例如,对话的成功和对话的长度。在这项工作中,我们提出了一个结构化的方法,通过寻找最佳的奖励组件权重,找到这些组件之间的良好平衡。为了使这种搜索可行,我们使用多目标强化学习来显着减少所需的训练对话的数量。我们应用我们提出的方法来找到六个域的优化组件权重,并将它们与默认基线进行比较。

英文摘要:

Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal reward component weighting. To render this search feasible, we use multi-objective reinforcement learning to significantly reduce the number of training dialogues required. We apply our proposed method to find optimized component weights for six domains and compare them to a default baseline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑