Interpretability in RL

RL: Reinforcement Learning

Overview

Interpretability in reinforcement learning studies how to understand what an agent has learned, why it takes particular actions, and whether its behavior is safe and reliable. Some methods build readable policies directly, using decision trees, symbolic rules, programs, or concept-based representations; others distill neural policies into simpler models. Post-hoc approaches use feature attribution, attention analysis, probing, and causal interventions, while formal verification checks properties such as safety and failure probabilities. Work spans settings from Atari and continuous control to healthcare and robotics, but a central challenge is balancing explanation simplicity and faithfulness with policy performance, and establishing whether explanations help people detect or fix real failures.

Latest papers

CardsList

81 papers9 papers in the last four weeks, down 18% on the four weeks before. 0.1% of all new papers.

  1. D'BEAST: Logged Bad Experiences as Explanation for Autonomous Driving Agents

    Nov 15, 2026Ahmad Alfan Alfian Irfan, Nur Ahmad Khatim, Mansur AriefInterpretability in RLRL for Autonomous Driving

  2. ReShap: Interpretable Reinforcement Learning for High-Dimensional Multi-Action Settings

    Nov 11, 2026Yiyu Qian, Pengfei Guo, Liyuan ZhaoInterpretability in RLReinforcement Learning

  3. Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics

    Nov 10, 2026Vladimir Krsmanovic, Bernd FinkbeinerReinforcement LearningFormal Methods for RL

  4. Value-oriented policy distillation for interpretable wind farm power control

    Nov 5, 2026Max Bruninx, Timothy Verstraeten, Jan Decuyper +2Power SystemsPolicy Distillation

  5. Reconstructing Fraudulent Strategies in Online Payments via Interpretable Inverse Reinforcement Learning

    Nov 3, 2026Huilin He, Weiyu Han, Linbo Shao +4Synthetic Data AugmentationFinancial Fraud Detection

  6. Hyperbolic Inverse Reinforcement Learning

    Oct 30, 2026Iulia Rusu, Anoop Praturu, Sergei Gepshtein +1Reinforcement LearningInterpretability in RL

  7. CausalXRL: Explainable Reinforcement Learning through Causal Graph Reasoning

    Oct 30, 2026Yanming Zhang, Eric Papenhausen, Klaus MuellerInterpretability in RLCausal Interpretability

  8. Interpretable Meta-Policies for Neural Decision Making

    Oct 27, 2026Raban Emunds, Jannis Blüml, Quentin Delfosse +1Interpretability in RLNeuro-Symbolic RL

  9. Reason-guided Human Reward Modeling for Preference-based Reinforcement Learning

    Oct 16, 2026Anshul Nayak, Shahil Shaik, Jonathan Smereka +1Preference-Based RLReward Modeling

  10. The Thinking Leakage in Reinforcement Learning for LLMs

    Oct 9, 2026Wenxuan Zhu, Shuming Liu, Bang An +4RL for Language Model ReasoningRL Post-Training

  11. Visualizing the World Model in an Agent's Value Function

    Oct 9, 2026Shawheen Naderi, Fatemeh Akherati, Yubei ChenWorld ModelsInterpretability in RL

  12. Temporally Interpretable Differentiable Decision Trees

    Oct 7, 2026Eisuke Hirota, Aarav Sane, Rohan PalejaInterpretable MLInterpretability in RL

  13. Towards the Automatic Synthesis of Interpretable Chess Tactics

    Oct 6, 2026Abhijeet Krishnan, Chris MartensGame-Playing AgentsChess

  14. Learning Explainable Representations of Complex Game-playing Strategies

    Oct 6, 2026Abhijeet Krishnan, Colin M. Potts, Arnav Jhala +3Game-Playing AgentsProgram Synthesis

  15. Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football

    Oct 5, 2026Kenjiro Ide, Taiga Someya, Kohei Kawaguchi +1Sequential Decision MakingInterpretability in RL

  16. Escaping Local Views: Discovering Latent Concepts for Interpretable Multi-Agent Reinforcement Learning

    Sep 28, 2026Yijie Sun, Sanquan Sun, Yanda Zhu +3Reinforcement LearningPartially Observable RL

  17. Learning and interpreting policies for simultaneous entanglement requests in quantum networks

    Sep 24, 2026Leon Rode, Sumeet Khatri, Supartha PodderInterpretability in RL

  18. Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System

    Sep 2, 2026Bente Hinkenhuis, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor AlsahagAlgorithmic FairnessDebiased ML

  19. ShuttleArena: Interpretable Self-Play in Physics-Based Badminton

    Aug 26, 2026Peize DingGame-Playing AgentsSelf-Play RL

  20. Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents

    Aug 18, 2026Ram Rachum, Yotam Amitai, Bálint Gyevnár +2Explainability EvaluationInterpretability in RL

  21. Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning

    Aug 15, 2026Joanikij Chulev, Hendrik BaierInterpretability in RLCounterfactual Learning

  22. XAI-Guided Conservative Decentralized Execution for Offline Multi-Agent Network Slicing

    Aug 14, 2026Eslam Eldeeb, Hatim Chergui, Merouane DebbahNetwork SlicingWireless Resource Allocation

  23. Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training

    Aug 8, 2026Binwen Tan, Jingchao Wang, Dengzhe Hou +6RL for Language Model ReasoningMulti-Task RL

  24. Interpretable reinforcement learning with decision-tree pruning

    Aug 7, 2026Mark Leon Ringer, Michel TokicInterpretability in RL

  25. Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Arctic Shipping

    Aug 6, 2026Vaishnav Vaidheeswaran, Dilith Jayakody, Biruk Ambaw +3Reinforcement LearningMeta-Reinforcement Learning

  26. dtControl2+ε\varepsilon: Trading Optimality for Explainability in MDPs via Decision Trees

    Jul 28, 2026Tereza Kinská, Jan Křetínský, Tobias Meggendorfer +2Markov Decision ProcessesMarkov Models