Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance

Wang, Xiaoxiao, Meng, Fanyu, Liu, Xin, Kong, Zhaodan, Chen, Xin

arXiv.org Artificial Intelligence 

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.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found