We introduce a data-driven, model-agnostic technique for generating a
human-interpretable summary of the salient points of contrast within an
evolving dynamical system, such as the learning process of a control agent. It
involves the aggregation of transition data along both spatial and temporal
dimensions according to an information-theoretic divergence measure. A
practical algorithm is outlined for continuous state spaces, and deployed to
summarise the learning histories of deep reinforcement learning agents with the
aid of graphical and textual communication methods. We expect our method to be
complementary to existing techniques in the realm of agent interpretability.

本文提出了一种数据驱动、模型无关的技术，用于生成一个易于人理解的摘要，概括一个演变动力系统（如控制代理的学习过程）中的显著对比要点。该技术根据信息论差异度沿时间和空间维度对转换数据进行聚合，并以图形和文本通信方法为辅助，对连续状态空间下的深度强化学习代理的学习历史进行摘要。我们期望我们的方法能够补充现有的代理可解释性技术。