Abstract
As reinforcement learning methods increasingly amass accomplishments, the need for comprehending their solutions becomes more crucial. Most explainable reinforcement learning (XRL) methods generate a static explanation depicting their developers' intuition of what should be explained and how. In contrast, literature from the social sciences proposes that meaningful explanations are structured as a dialog between the explainer and the explainee, suggesting a more active role for the user and her communication with the agent. In this paper, we present ASQ-IT -- an interactive tool that presents video clips of the agent acting in its environment based on queries given by the user that describe temporal properties of behaviors of interest. Our approach is based on formal methods: queries in ASQ-IT's user interface map to a fragment of Linear Temporal Logic over finite traces (LTLf), which we developed, and our algorithm for query processing is based on automata theory. User studies show that end-users can understand and formulate queries in ASQ-IT, and that using ASQ-IT assists users in identifying faulty agent behaviors.
Abstract (translated)
随着强化学习方法日益积累成就,理解它们的解决方案变得越来越重要。大部分可解释强化学习(XRL)方法生成静态解释,描述了开发人员对应该解释什么以及如何解释的直觉,而社会科学文献提议有意义的解释应该被组织成解释者与解释ee之间的对话,建议用户及其与Agent的通信应该有更积极的角色。在本文中,我们介绍了ASQ-IT——一个交互工具,基于用户提供的查询,在用户环境中展示Agent的行为视频片段,以描述感兴趣的行为的时间特性。我们的方法基于正式方法:ASQ-IT的用户界面查询映射我们开发的有限状态跟踪(LTLf)片段,我们的查询处理算法基于自动机理论。用户研究结果表明,最终用户能够理解和在ASQ-IT中提出查询,使用ASQ-IT帮助用户识别Agent的不良行为。
URL
https://arxiv.org/abs/2301.09941