{"total":20,"rows":[{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116,"area":null},{"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":"2309.01038","title":"Neurosymbolic Reinforcement Learning and Planning: A Survey","created":"2023-09-02","cited_by_count":24,"area":null},{"id":"2303.04926","title":"Automated Cyber Defence: A Review","created":"2023-03-08","cited_by_count":21,"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":"2205.12449","title":"MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2502.14581","title":"A Statistical Case Against Empirical Human-AI Alignment","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2210.04723","title":"Experiential Explanations for Reinforcement Learning","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2401.00104","title":"Causal State Distillation for Explainable Reinforcement Learning","created":"2023-12-30","cited_by_count":2,"area":null},{"id":"2402.06501","title":"Scalable Interactive Machine Learning for Future Command and Control","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2212.08189","title":"Multi-Resolution Online Deterministic Annealing: A Hierarchical and Progressive Learning Architecture","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2309.13365","title":"Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2311.15838","title":"Utilizing Explainability Techniques for Reinforcement Learning Model Assurance","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2212.06967","title":"Explaining Agent's Decision-making in a Hierarchical Reinforcement Learning Scenario","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2312.08397","title":"Personalized Decision Supports based on Theory of Mind Modeling and Explainable Reinforcement Learning","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2409.10733","title":"BaTCAVe: Trustworthy Explanations for Robot Behaviors","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2503.10509","title":"From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2503.23326","title":"Exploring Explainable Multi-agent MCTS-minimax Hybrids in Board Game Using Process Mining","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2603.24350","title":"Evidence of an Emergent \"Self\" in Continual Robot Learning","created":"2026-03-25","cited_by_count":0,"area":null}],"next_cursor":null}