论文标题
弥合差距：提供临时符号解释，以解决依次的决策问题，并具有难以理解的表示
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations
论文作者
论文摘要
随着越来越复杂的AI系统被引入我们的日常生活中，因此对于这样的系统来说，能够解释其决策的理由并允许用户对这些决定进行质疑变得重要。允许进行这种解释性对话的重大障碍可能是用户与AI系统之间的词汇不匹配。本文介绍了根据用户指定的概念提供对比解释的方法，用于顺序决策设置，其中系统的模型可以最好地表示为难以理解的模型。我们通过构建可以利用该任务的局部近似值的部分符号模型来做到这一点，以回答用户查询。我们在流行的Atari游戏（蒙特祖玛的复仇）和Sokoban（著名的计划基准）上测试了这些方法，并报告了用户研究的结果，以评估人们是否发现以这种形式产生的解释有用。
As increasingly complex AI systems are introduced into our daily lives, it becomes important for such systems to be capable of explaining the rationale for their decisions and allowing users to contest these decisions. A significant hurdle to allowing for such explanatory dialogue could be the vocabulary mismatch between the user and the AI system. This paper introduces methods for providing contrastive explanations in terms of user-specified concepts for sequential decision-making settings where the system's model of the task may be best represented as an inscrutable model. We do this by building partial symbolic models of a local approximation of the task that can be leveraged to answer the user queries. We test these methods on a popular Atari game (Montezuma's Revenge) and variants of Sokoban (a well-known planning benchmark) and report the results of user studies to evaluate whether people find explanations generated in this form useful.
