TL;DR本篇论文介绍了一种基于 agent assessment module 的 AI 系统执行高级指令序列并回答用户问题的方法，通过不同类别的查询来比较这种方法的计算要求和正确模型的学习所需的努力，并介绍了动态因果决策网络来捕捉 STRIPS-like 领域的因果结构。
Abstract
One of the several obstacles in the widespread use of ai systems is the lack of requirements of interpretability that can enable a layperson to ensure the safe and reliable behavior of such systems. We extend the