Exploring the Reliability of SHAP Values in Reinforcement Learning

Raphael C. Engelhardt, Moritz Lange, Laurenz Wiskott, Wolfgang Konen. Exploring the Reliability of SHAP Values in Reinforcement Learning. In Luca Longo, Sebastian Lapuschkin, Christin Seifert, editors, Explainable Artificial Intelligence - Second World Conference, xAI 2024, Valletta, Malta, July 17-19, 2024, Proceedings, Part III. Volume 2155 of Communications in Computer and Information Science, pages 165-184, Springer, 2024. [doi]

Abstract

Abstract is missing.