{"total":48,"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":"2405.13863","title":"Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning","created":"2024-05-22","cited_by_count":15,"area":"deeprl"},{"id":"2405.15994","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","created":"2024-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2403.00172","title":"Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control","created":"2024-02-29","cited_by_count":5,"area":"deeprl"},{"id":"2403.14328","title":"Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression","created":"2024-03-21","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":"2410.14371","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","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":"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":"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":"2402.12685","title":"XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques","created":"2024-02-20","cited_by_count":2,"area":"deeprl"},{"id":"2402.13785","title":"Composing Reinforcement Learning Policies, with Formal Guarantees","created":"2024-02-21","cited_by_count":2,"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":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2407.08250","title":"Gradient Boosting Reinforcement Learning","created":"2024-07-11","cited_by_count":1,"area":"deeprl"},{"id":"2407.14714","title":"Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming","created":"2024-07-20","cited_by_count":1,"area":"deeprl"},{"id":"2501.04068","title":"Explainable Reinforcement Learning for Formula One Race Strategy","created":"2025-01-07","cited_by_count":1,"area":"deeprl"},{"id":"2501.17077","title":"Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning","created":"2025-01-28","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":"2401.07263","title":"BET: Explaining Deep Reinforcement Learning through The Error-Prone Decisions","created":"2024-01-14","cited_by_count":0,"area":"deeprl"},{"id":"2403.16293","title":"Interpretable Modeling of Deep Reinforcement Learning Driven Scheduling","created":"2024-03-24","cited_by_count":0,"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":"2506.09499","title":"A Unified Theory of Compositionality, Modularity, and Interpretability in Markov Decision Processes","created":"2025-06-11","cited_by_count":0,"area":"deeprl"},{"id":"2510.18478","title":"Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation","created":"2025-10-21","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":"2603.14589","title":"Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning","created":"2026-03-15","cited_by_count":0,"area":"deeprl"},{"id":"2604.09452","title":"SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning","created":"2026-04-10","cited_by_count":0,"area":"deeprl"},{"id":"2605.04254","title":"Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies","created":"2026-05-05","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":"2606.00561","title":"Interpretable Policy Distillation for Power Grid Topology Control","created":"2026-05-30","cited_by_count":0,"area":"deeprl"},{"id":"2606.04634","title":"Explainably Safe Reinforcement Learning","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2607.07235","title":"ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2607.11959","title":"Calibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses","created":"2026-07-12","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":"2607.24672","title":"Explainable Reinforcement Learning via Physics-Aware Policy Distillation","created":"2026-07-27","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"},{"id":"2609.28581","title":"Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2610.07640","title":"Towards the Automatic Synthesis of Interpretable Chess Tactics","created":"2026-10-06","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}