mlsanityData to 14 Oct 2026

Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework

arXiv 2603.13257 ↗First posted 24 Feb 2026cs.AIcited by 0

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

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 textitLunar 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 < 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 45 references that are in the map. First posted on arXiv 24 Feb 2026.

Builds on

14 of 45 references.

References · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2016OpenAI Gymcited by 1,736
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  6. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  7. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  8. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  9. 2017Visualizing and Understanding Atari Agentscited by 141
  10. 2020Explainable Reinforcement Learning: A Surveycited by 141
  11. 2017Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigationcited by 77
  12. 2016Graying the black box: Understanding DQNscited by 68
2 more
  1. 2018Toward Interpretable Deep Reinforcement Learning with Linear Model U-Treescited by 65
  2. 2018Establishing Appropriate Trust via Critical Statescited by 48

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Explainable Deep Reinforcement Learning
  2. 2026Explainable Reinforcement Learning via Physics-Aware Policy Distillation
  3. 2026ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
  4. 2026Explaining Reinforcement Learning Agents via Inductive Logic Programming
  5. 2023Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery
  6. 2025BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies
  7. 2016Particle Swarm Optimization for Generating Interpretable Fuzzy Reinforcement Learning Policies
  8. 2025From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation