BriefGPT.xyz
Oct, 2022
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
HTML
PDF
Xiaoxiao Wang, Fanyu Meng, Zhaodan Kong, Xin Chen, Xin Liu
TL;DR
本文研究了强化学习中的可解释性问题，提出了一种基于因果关系的解释机制并通过模拟实验验证了其在解释政策方面的优势。
Abstract
explainability
plays an increasingly important role in
machine learning
. Because
reinforcement learning
(RL) involves interactions between
→