论文标题
增强学习的因果解释：量化状态和时间重要性
Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance
论文作者
论文摘要
解释性在机器学习中起着越来越重要的作用。此外，人类通过因果关系观看世界，因此更喜欢因果解释而不是关联的解释。因此，在本文中，我们开发了一种因果解释机制，该机制量化了国家对行动和随着时间的重要性的因果重要性。我们还通过一系列模拟研究（包括作物灌溉，二十一点，避免碰撞和月球兰德勒）来证明我们机制比最先进的关联方法的优势。
Explainability plays an increasingly important role in machine learning. Furthermore, humans view the world through a causal lens and thus prefer causal explanations over associational ones. Therefore, in this paper, we develop a causal explanation mechanism that quantifies the causal importance of states on actions and such importance over time. We also demonstrate the advantages of our mechanism over state-of-the-art associational methods in terms of RL policy explanation through a series of simulation studies, including crop irrigation, Blackjack, collision avoidance, and lunar lander.
