{"total":73,"rows":[{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2509.00328","title":"Mechanistic interpretability for steering vision-language-action models","created":"2025-08-30","cited_by_count":31,"area":"vla"},{"id":"2306.06561","title":"Learning World Models with Identifiable Factorization","created":"2023-06-11","cited_by_count":23,"area":"wm"},{"id":"2410.14368","title":"CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic","created":"2024-10-18","cited_by_count":22,"area":"agents"},{"id":"2303.04926","title":"Automated Cyber Defence: A Review","created":"2023-03-08","cited_by_count":21,"area":null},{"id":"2405.14956","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","created":"2024-05-23","cited_by_count":18,"area":"deeprl"},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2506.01622","title":"General agents contain world models","created":"2025-06-02","cited_by_count":17,"area":"wm"},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"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":"2301.13185","title":"Optimal Decision Tree Policies for Markov Decision Processes","created":"2023-01-30","cited_by_count":8,"area":"offlinerl"},{"id":"2409.00743","title":"Interpretable Clustering: A Survey","created":"2024-09-01","cited_by_count":8,"area":null},{"id":"2508.05433","title":"Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies","created":"2025-08-07","cited_by_count":8,"area":"mllm"},{"id":"2308.01475","title":"Interpretable Machine Learning for Discovery: Statistical Challenges \\& Opportunities","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2404.17780","title":"Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning","created":"2024-04-27","cited_by_count":7,"area":"agents"},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2407.15786","title":"LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning","created":"2024-07-22","cited_by_count":5,"area":"lr"},{"id":"2505.21743","title":"Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2303.10382","title":"Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management","created":"2023-03-18","cited_by_count":4,"area":null},{"id":"2312.08466","title":"Efficiently Quantifying Individual Agent Importance in Cooperative MARL","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2407.12161","title":"Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent","created":"2024-07-16","cited_by_count":4,"area":"agents"},{"id":"2408.11632","title":"Optimizing Interpretable Decision Tree Policies for Reinforcement Learning","created":"2024-08-21","cited_by_count":4,"area":"offlinerl"},{"id":"2410.05406","title":"Synthesizing Interpretable Control Policies through Large Language Model Guided Search","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2410.14371","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2502.09417","title":"A Survey of Reinforcement Learning for Optimization in Automation","created":"2025-02-13","cited_by_count":4,"area":"deeprl"},{"id":"2512.02193","title":"From monoliths to modules: Decomposing transducers for efficient world modelling","created":"2025-12-01","cited_by_count":4,"area":"wm"},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2309.01458","title":"Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning","created":"2023-09-04","cited_by_count":3,"area":null},{"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":"2508.18380","title":"Information Templates: A New Paradigm for Intelligent Active Feature Acquisition","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2207.08651","title":"Boolean Decision Rules for Reinforcement Learning Policy Summarisation","created":"2022-07-18","cited_by_count":2,"area":null},{"id":"2208.08790","title":"Explainable Reinforcement Learning on Financial Stock Trading using SHAP","created":"2022-08-18","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":"2211.00086","title":"Disentangled (Un)Controllable Features","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2407.13518","title":"Model-based Policy Optimization using Symbolic World Model","created":"2024-07-18","cited_by_count":2,"area":"wm"},{"id":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","cited_by_count":2,"area":null},{"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":"2409.08666","title":"Towards certifiable AI in aviation: landscape, challenges, and opportunities","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2505.13182","title":"Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2,"area":"deeprl"},{"id":"2601.17168","title":"Interpreting Agentic Systems: Beyond Model Explanations to System-Level Accountability","created":"2026-01-23","cited_by_count":2,"area":"agents"},{"id":"2311.14270","title":"Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery","created":"2023-11-24","cited_by_count":1,"area":"distill"},{"id":"2312.08463","title":"How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2404.17187","title":"An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging","created":"2024-04-26","cited_by_count":1,"area":"deeprl"},{"id":"2409.03260","title":"In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search","created":"2024-09-05","cited_by_count":1,"area":null},{"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":"2501.18848","title":"Reinforcement Learning of Flexible Policies for Symbolic Instructions with Adjustable Mapping Specifications","created":"2025-01-31","cited_by_count":1,"area":"deeprl"},{"id":"2503.02961","title":"Koopman-Based Generalization of Deep Reinforcement Learning With Application to Wireless Communications","created":"2025-03-04","cited_by_count":1,"area":"deeprl"},{"id":"2503.16724","title":"Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models","created":"2025-03-20","cited_by_count":1,"area":"mllm"},{"id":"2510.19244","title":"Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments","created":"2025-10-22","cited_by_count":1,"area":"deeprl"},{"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":"2401.12662","title":"Integrating Human Expertise in Continuous Spaces: A Novel Interactive Bayesian Optimization Framework with Preference Expected Improvement","created":"2024-01-23","cited_by_count":0,"area":null},{"id":"2401.14226","title":"Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks","created":"2024-01-25","cited_by_count":0,"area":"deeprl"},{"id":"2406.02765","title":"Discovering Continuous-Time Memory-Based Symbolic Policies using Genetic Programming","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2411.05586","title":"Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs","created":"2024-11-08","cited_by_count":0,"area":"deeprl"},{"id":"2411.11457","title":"Upside-Down Reinforcement Learning for More Interpretable Optimal Control","created":"2024-11-18","cited_by_count":0,"area":"deeprl"},{"id":"2501.10698","title":"An Interpretable Neural Control Network with Adaptable Online Learning for Sample Efficient Robot Locomotion Learning","created":"2025-01-18","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":"2505.11311","title":"Explaining Strategic Decisions in Multi-Agent Reinforcement Learning for Aerial Combat Tactics","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2509.15582","title":"Momentum-constrained Hybrid Heuristic Trajectory Optimization Framework with Residual-enhanced DRL for Visually Impaired Scenarios","created":"2025-09-19","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":"2601.22052","title":"Learning to Dial-a-Ride: A Deep Graph Reinforcement Learning Approach to the Electric Dial-a-Ride Problem","created":"2026-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2602.21467","title":"Geometric Priors for Generalizable World Models via Vector Symbolic Architecture","created":"2026-02-25","cited_by_count":0,"area":"wm"},{"id":"2603.14600","title":"A Loss Landscape Visualization Framework for Interpreting Reinforcement Learning: An ADHDP Case Study","created":"2026-03-15","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":"2607.17861","title":"ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.01133","title":"Policy Optimality Measurement for Multi-Vehicle Decision-Making: From Extrinsic Indicators to Intrinsic Quality","created":"2026-08-02","cited_by_count":0,"area":"deeprl"},{"id":"2609.24025","title":"Synthesizing Reactive Character Behaviors for Continuous Games via Programmatic Policy Search","created":"2026-09-21","cited_by_count":0,"area":"agents"}],"next_cursor":null}