arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.06338cs.AI
收藏

为AI计划员决策提供解释

Towards Providing Explanations for AI Planner Decisions

King’s College London(伦敦国王学院)

Rita Borgo, Michael Cashmore, Daniele Magazzeni

摘要:

为了让人们对人工智能产生信任,人类必须了解人工智能系统试图实现什么,以及为什么。为了克服这个问题,底层的人工智能过程必须产生对用户透明和可理解的理由和解释。AI规划能够很好地应对这一挑战。在本文中,我们提出了一种方法来提供初步的解释,由规划师的决定。通过允许用户在计划中建议替代行动,然后将产生的计划与计划者找到的计划进行比较,来创建解释。该方法在新的XAI计划框架中实施。

英文摘要:

In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why. To overcome this problem, the underlying AI process must produce justifications and explanations that are both transparent and comprehensible to the user. AI Planning is well placed to be able to address this challenge. In this paper we present a methodology to provide initial explanations for the decisions made by the planner. Explanations are created by allowing the user to suggest alternative actions in plans and then compare the resulting plans with the one found by the planner. The methodology is implemented in the new XAI-Plan framework.

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。

↑