{"total":65,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31,"area":null},{"id":"2302.12232","title":"Concept Learning for Interpretable Multi-Agent Reinforcement Learning","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2112.08907","title":"Inherently Explainable Reinforcement Learning in Natural Language","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2304.08349","title":"Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach","created":"2023-04-17","cited_by_count":15,"area":null},{"id":"2205.10032","title":"Survey on Fair Reinforcement Learning: Theory and Practice","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2312.11118","title":"Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes","created":"2023-12-18","cited_by_count":14,"area":null},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2107.13668","title":"Discovering User-Interpretable Capabilities of Black-Box Planning Agents","created":"2021-07-28","cited_by_count":10,"area":null},{"id":"2210.11825","title":"Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agents","created":"2022-10-21","cited_by_count":10,"area":null},{"id":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9,"area":"offlinerl"},{"id":"2205.07394","title":"Sibyl: Adaptive and Extensible Data Placement in Hybrid Storage Systems Using Online Reinforcement Learning","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2105.07099","title":"Feature-Based Interpretable Reinforcement Learning based on State-Transition Models","created":"2021-05-14","cited_by_count":6,"area":null},{"id":"2207.01911","title":"Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications","created":"2022-07-05","cited_by_count":6,"area":null},{"id":"2207.10163","title":"Constrained Prescriptive Trees via Column Generation","created":"2022-07-20","cited_by_count":6,"area":null},{"id":"2408.09135","title":"Vanilla Gradient Descent for Oblique Decision Trees","created":"2024-08-17","cited_by_count":6,"area":null},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2108.06898","title":"Neural-to-Tree Policy Distillation with Policy Improvement Criterion","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2211.05551","title":"Causal Counterfactuals for Improving the Robustness of Reinforcement Learning","created":"2022-11-02","cited_by_count":5,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2206.04266","title":"There is no Accuracy-Interpretability Tradeoff in Reinforcement Learning for Mazes","created":"2022-06-09","cited_by_count":4,"area":null},{"id":"2211.03162","title":"ProtoX: Explaining a Reinforcement Learning Agent via Prototyping","created":"2022-11-06","cited_by_count":4,"area":null},{"id":"2504.05625","title":"Model-Agnostic Policy Explanations with Large Language Models","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2203.04303","title":"Policy Regularization for Legible Behavior","created":"2022-03-08","cited_by_count":3,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2309.10346","title":"Explaining Agent Behavior with Large Language Models","created":"2023-09-19","cited_by_count":3,"area":"agents"},{"id":"2311.18062","title":"Understanding Your Agent: Leveraging Large Language Models for Behavior Explanation","created":"2023-11-29","cited_by_count":3,"area":"agents"},{"id":"2411.12173","title":"SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks","created":"2024-11-19","cited_by_count":3,"area":"deeprl"},{"id":"2509.04809","title":"TalkToAgent: A Human-centric Explanation of Reinforcement Learning Agents with Large Language Models","created":"2025-09-05","cited_by_count":3,"area":"agents"},{"id":"2510.21809","title":"Embodied Navigation with Auxiliary Task of Action Description Prediction","created":"2025-10-21","cited_by_count":3,"area":"deeprl"},{"id":"2112.07620","title":"Tree-based Focused Web Crawling with Reinforcement Learning","created":"2021-12-12","cited_by_count":2,"area":null},{"id":"2207.06269","title":"Policy Optimization with Sparse Global Contrastive Explanations","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2210.01007","title":"Reward Learning with Trees: Methods and Evaluation","created":"2022-10-03","cited_by_count":2,"area":"alignment"},{"id":"2410.16517","title":"RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space","created":"2024-10-21","cited_by_count":2,"area":"deeprl"},{"id":"2504.05393","title":"Interactive Explanations for Reinforcement-Learning Agents","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2109.14493","title":"Automatic Discovery and Description of Human Planning Strategies","created":"2021-09-29","cited_by_count":1,"area":null},{"id":"2201.08520","title":"Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2301.03043","title":"XDQN: Inherently Interpretable DQN through Mimicking","created":"2023-01-08","cited_by_count":1,"area":null},{"id":"2405.14629","title":"Which Experiences Are Influential for RL Agents? Efficiently Estimating The Influence of Experiences","created":"2024-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2506.14246","title":"Mxplainer: Explain and Learn Insights by Imitating Mahjong Agents","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2507.07848","title":"\"So, Tell Me About Your Policy...\": Distillation of interpretable policies from Deep Reinforcement Learning agents","created":"2025-07-10","cited_by_count":1,"area":"deeprl"},{"id":"2109.08180","title":"Interpretable Local Tree Surrogate Policies","created":"2021-09-16","cited_by_count":0,"area":null},{"id":"2203.00822","title":"Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation","created":"2022-03-02","cited_by_count":0,"area":null},{"id":"2211.04987","title":"Interpretable Deep Reinforcement Learning for Green Security Games with Real-Time Information","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2301.09941","title":"ASQ-IT: Interactive Explanations for Reinforcement-Learning Agents","created":"2023-01-24","cited_by_count":0,"area":null},{"id":"2301.11168","title":"Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2304.09769","title":"End-to-End Policy Gradient Method for POMDPs and Explainable Agents","created":"2023-04-19","cited_by_count":0,"area":null},{"id":"2305.16924","title":"Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback","created":"2023-05-26","cited_by_count":0,"area":"alignment"},{"id":"2307.15456","title":"Worrisome Properties of Neural Network Controllers and Their Symbolic Representations","created":"2023-07-28","cited_by_count":0,"area":null},{"id":"2309.06097","title":"Fidelity-Induced Interpretable Policy Extraction for Reinforcement Learning","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2406.14324","title":"Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2502.00684","title":"Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning","created":"2025-02-02","cited_by_count":0,"area":"deeprl"},{"id":"2505.16833","title":"Strategically Linked Decisions in Long-Term Planning and Reinforcement Learning","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2509.14925","title":"Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation","created":"2025-09-18","cited_by_count":0,"area":"deeprl"},{"id":"2603.13257","title":"Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework","created":"2026-02-24","cited_by_count":0,"area":"deeprl"},{"id":"2603.27971","title":"Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning","created":"2026-03-30","cited_by_count":0,"area":"alignment"},{"id":"2605.07837","title":"Approximation-Free Differentiable Oblique Decision Trees","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14897","title":"Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models","created":"2026-05-14","cited_by_count":0,"area":"deeprl"},{"id":"2606.19632","title":"Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.15459","title":"From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems","created":"2026-07-16","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}