Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework
Proceedings of the AAAI Symposium Series · 18.05.2026 · 8 (1) · 11-20
DOI: 10.1609/aaaiss.v8i1.42511 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 18.05.2026. Verfasst von Sanup S. Araballi und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains. Existing explainability methods either provide only local insights (SHAP, LIME) or employ over-simplified surrogates failing to capture continuous dynamics (decision trees). This work proposes a Hierarchical Takagi-Sugeno-Kang (TSK) Fuzzy Classifier System (FCS) distilling neural policies into human-readable IF-THEN rules through K-Means clustering for state partitioning and Ridge Regression for local action inference. Three quantifiable metrics are introduced: Fuzzy Rule Activation Density (FRAD) measuring explanation focus, Fuzzy Set Coverage (FSC) validating vocabulary completeness, and Action Space Granularity (ASG) assessing control mode diversity. Dynamic Time Warping (DTW) validates temporal behavioral fidelity. Empirical evaluation on Lunar Lander Continuous shows the Triangular membership function variant achieves 81.48% ± 0.43% fidelity, outperforming Decision Trees by 21 percentage points. The framework exhibits statistically superior interpretability (FRAD = 0.814 vs. 0.723 for Gaussian, p
Zitieren
APA
Araballi, S. S., Khan, S., & Mohan, C. K. (2026). Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework. Proceedings of the AAAI Symposium Series, 8(1), 11-20. https://doi.org/10.1609/aaaiss.v8i1.42511
Vancouver
Araballi SS, Khan S, Mohan CK. Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework. Proceedings of the AAAI Symposium Series. 2026;8(1):11-20. doi:10.1609/aaaiss.v8i1.42511
BibTeX
@article{Araballi2026,
author = {Araballi, Sanup S. and Khan, Simon and Mohan, Chilikuri K.},
title = {Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {8},
number = {1},
pages = {11--20},
doi = {10.1609/aaaiss.v8i1.42511}
}
EUVIMED