将深度强化学习转化为可读的模糊规则，让智能体决策过程透明可验。
Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework
- 用聚类分状态、回归定动作，把神经网络策略转成人类能读懂的条件句。
- 在月球着陆器任务中，解释精度达81.48%，比决策树高21个百分点。
- 规则如“左漂高处则右修正上推”，适合安全关键场景的人工审核。
深度强化学习在连续控制任务中表现卓越，但其决策过程不透明，难以应用于安全敏感领域。现有可解释性方法或仅提供局部解释（如SHAP、LIME），或使用过于简化的代理模型无法捕捉连续动态（如决策树）。本文提出一种分层Takagi-Sugeno-Kang模糊分类系统（FCS），通过K均值聚类进行状态划分，结合岭回归实现局部动作推理，将神经策略蒸馏为可读的IF-THEN规则。引入三项量化指标：模糊规则激活密度（FRAD）衡量解释聚焦程度，模糊集覆盖度（FSC）验证词汇完整性，动作空间粒度（ASG）评估控制模式多样性。采用动态时间规整（DTW）验证行为时序一致性。在《Lunar Lander(Continuous)》任务上的实证表明，三角形隶属函数变体达到81.48% ± 0.43%的行为保真度，优于决策树21个百分点。该框架在可解释性上显著优于高斯型（FRAD=0.814 vs. 0.723，p<0.001），且均方误差低至0.0053，DTW距离为1.05。提取出的规则如“若着陆器高空左漂，则施加向上推力并向右修正”支持人工验证，为可信自主系统提供可行路径。
原文摘要 · Abstract (English)
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 \textit{Lunar Lander(Continuous)} shows the Triangular membership function variant achieves 81.48\% $\pm$ 0.43\% fidelity, outperforming Decision Trees by 21 percentage points. The framework exhibits statistically superior interpretability (FRAD = 0.814 vs. 0.723 for Gaussian, $p < 0.001$) with low MSE (0.0053) and DTW distance (1.05). Extracted rules such as ``IF lander drifting left at high altitude THEN apply upward thrust with rightward correction'' enable human verification, establishing a pathway toward trustworthy autonomous systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。