Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework
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
By Sanup S. Araballi, Simon Khan, Chilukuri K. Mohan