arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.03809cs.CLcs.LG
收藏

面向任务的多Agent对话策略学习及角色感知的奖励分解

Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition

DCST, Tsinghua University(清华大学计算机科学与技术系);Tsinghua University(清华大学)

Ryuichi Takanobu, Runze Liang, Minlie Huang

摘要:

近年来,许多研究已经将强化学习应用于训练对话策略,并显示出很大的前景。一种常见的方法是采用用户模拟器来获得用于强化学习算法的大量模拟用户体验。然而,模拟真实的用户模拟器是具有挑战性的。基于规则的模拟器需要大量的领域专业知识来完成复杂的任务,而数据驱动的模拟器需要大量的数据,甚至不清楚如何评估模拟器。为了避免事先建立一个明确的用户模拟器,我们提出了多Agent对话策略学习,它把系统和用户作为对话代理。两个智能体相互作用,同时共同学习。该方法使用演员-评论家框架,以促进预训练和提高可扩展性。我们还提出了混合价值网络的角色感知的奖励分解,以整合面向任务的对话中的每个代理的角色特定的领域知识。实验结果表明,该方法可以成功地建立一个系统的政策和用户的政策,并通过会话交互的两个代理可以实现高的任务成功率。

英文摘要:

Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement learning algorithms. However, modeling a realistic user simulator is challenging. A rule-based simulator requires heavy domain expertise for complex tasks, and a data-driven simulator requires considerable data and it is even unclear how to evaluate a simulator. To avoid explicitly building a user simulator beforehand, we propose Multi-Agent Dialog Policy Learning, which regards both the system and the user as the dialog agents. Two agents interact with each other and are jointly learned simultaneously. The method uses the actor-critic framework to facilitate pretraining and improve scalability. We also propose Hybrid Value Network for the role-aware reward decomposition to integrate role-specific domain knowledge of each agent in the task-oriented dialog. Results show that our method can successfully build a system policy and a user policy simultaneously, and two agents can achieve a high task success rate through conversational interaction.

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。

↑