{"total":36,"rows":[{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2405.14956","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","created":"2024-05-23","cited_by_count":18,"area":"deeprl"},{"id":"2403.12451","title":"End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations","created":"2024-03-19","cited_by_count":17,"area":"deeprl"},{"id":"2404.06492","title":"Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective","created":"2024-04-09","cited_by_count":16,"area":"deeprl"},{"id":"2405.13863","title":"Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning","created":"2024-05-22","cited_by_count":15,"area":"deeprl"},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2406.06107","title":"EXPIL: Explanatory Predicate Invention for Learning in Games","created":"2024-06-10","cited_by_count":5,"area":"deeprl"},{"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":"2501.03888","title":"Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies","created":"2025-01-07","cited_by_count":4,"area":"deeprl"},{"id":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2406.03651","title":"Inductive Generalization in Reinforcement Learning from Specifications","created":"2024-06-05","cited_by_count":3,"area":"deeprl"},{"id":"2412.13053","title":"SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks","created":"2024-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2503.08322","title":"Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs","created":"2025-03-11","cited_by_count":3,"area":"deeprl"},{"id":"2408.04336","title":"KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination","created":"2024-08-08","cited_by_count":2,"area":"deeprl"},{"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":"2503.14973","title":"Behaviour Discovery and Attribution for Explainable Reinforcement Learning","created":"2025-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2601.22024","title":"SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile Networks","created":"2026-01-29","cited_by_count":2,"area":"deeprl"},{"id":"2601.22044","title":"SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control","created":"2026-01-29","cited_by_count":2,"area":"deeprl"},{"id":"2410.21940","title":"Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution","created":"2024-10-29","cited_by_count":1,"area":"deeprl"},{"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":"2603.23738","title":"BXRL: Behavior-Explainable Reinforcement Learning","created":"2026-03-24","cited_by_count":1,"area":"deeprl"},{"id":"2404.10906","title":"Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop","created":"2024-04-16","cited_by_count":0,"area":"deeprl"},{"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":"2502.15512","title":"SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning","created":"2025-02-21","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":"2506.00328","title":"BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies","created":"2025-05-31","cited_by_count":0,"area":"deeprl"},{"id":"2510.19241","title":"SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2512.05291","title":"SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning","created":"2025-12-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.09909","title":"STACHE: Local Black-Box Explanations for Reinforcement Learning Policies","created":"2025-12-10","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":"2605.18454","title":"Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2605.18508","title":"DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2607.13655","title":"Explaining Reinforcement Learning Agents via Inductive Logic Programming","created":"2026-07-15","cited_by_count":0,"area":"deeprl"},{"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"},{"id":"2608.07151","title":"Interpretable reinforcement learning with decision-tree pruning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}