{"total":101,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370,"area":"offlinerl"},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2010.11895","title":"What are the Statistical Limits of Offline RL with Linear Function Approximation?","created":"2020-10-22","cited_by_count":136,"area":"offlinerl"},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71,"area":"offlinerl"},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62,"area":"offlinerl"},{"id":"2205.15512","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","created":"2022-05-31","cited_by_count":55,"area":"offlinerl"},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51,"area":"offlinerl"},{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44,"area":null},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2105.01876","title":"Change Matters: Medication Change Prediction with Recurrent Residual Networks","created":"2021-05-05","cited_by_count":38,"area":null},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2202.06588","title":"Conditional Generation Net for Medication Recommendation","created":"2022-02-14","cited_by_count":30,"area":null},{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2303.02569","title":"Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching","created":"2023-03-05","cited_by_count":24,"area":"offlinerl"},{"id":"2208.04560","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","created":"2022-08-09","cited_by_count":22,"area":"offlinerl"},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2310.00678","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","created":"2023-10-01","cited_by_count":18,"area":"offlinerl"},{"id":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"2511.12120","title":"Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy","created":"2025-11-15","cited_by_count":15,"area":"deeprl"},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13,"area":"offlinerl"},{"id":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"area":"offlinerl"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2505.19785","title":"medDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support","created":"2025-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2304.02169","title":"Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model","created":"2023-04-04","cited_by_count":8,"area":null},{"id":"2310.16336","title":"SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2310.20663","title":"Offline RL with Observation Histories: Analyzing and Improving Sample Complexity","created":"2023-10-31","cited_by_count":7,"area":"offlinerl"},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2305.12594","title":"Modeling User Satisfaction Dynamics in Dialogue via Hawkes Process","created":"2023-05-21","cited_by_count":6,"area":null},{"id":"2308.09780","title":"Event-based Dynamic Graph Representation Learning for Patent Application Trend Prediction","created":"2023-08-04","cited_by_count":6,"area":null},{"id":"2404.10635","title":"Compressed Federated Reinforcement Learning with a Generative Model","created":"2024-03-26","cited_by_count":6,"area":"deeprl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2205.09852","title":"Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes","created":"2022-05-19","cited_by_count":5,"area":null},{"id":"2402.04398","title":"Learning under Temporal Label Noise","created":"2024-02-06","cited_by_count":5,"area":null},{"id":"2405.18556","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","created":"2024-05-28","cited_by_count":5,"area":"offlinerl"},{"id":"2407.05302","title":"Mamba Hawkes Process","created":"2024-07-07","cited_by_count":5,"area":"ssm"},{"id":"2204.07124","title":"Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2410.07525","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2501.07166","title":"Natural Language-Assisted Multi-modal Medication Recommendation","created":"2025-01-13","cited_by_count":4,"area":null},{"id":"2103.00098","title":"Reducing Conservativeness Oriented Offline Reinforcement Learning","created":"2021-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2112.14479","title":"Universal Transformer Hawkes Process with Adaptive Recursive Iteration","created":"2021-12-29","cited_by_count":3,"area":null},{"id":"2407.00364","title":"Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes","created":"2024-06-29","cited_by_count":3,"area":"deeprl"},{"id":"2505.20621","title":"Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning","created":"2025-05-27","cited_by_count":3,"area":"offlinerl"},{"id":"2508.00201","title":"RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation Systems","created":"2025-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2302.14833","title":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":2,"area":"offlinerl"},{"id":"2303.02265","title":"Learning to Influence Human Behavior with Offline Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":"offlinerl"},{"id":"2308.03882","title":"Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations","created":"2023-08-07","cited_by_count":2,"area":"offlinerl"},{"id":"2406.14054","title":"Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing","created":"2024-06-20","cited_by_count":2,"area":"offlinerl"},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2511.06111","title":"Guardian-regularized Safe Offline Reinforcement Learning for Smart Weaning of Mechanical Circulatory Devices","created":"2025-11-08","cited_by_count":2,"area":"offlinerl"},{"id":"2512.18957","title":"Online Robust Reinforcement Learning with General Function Approximation","created":"2025-12-22","cited_by_count":2,"area":"deeprl"},{"id":"2602.06603","title":"The hidden risks of temporal resampling in clinical reinforcement learning","created":"2026-02-06","cited_by_count":2,"area":"offlinerl"},{"id":"2102.09599","title":"Privacy-Preserving Kickstarting Deep Reinforcement Learning with Privacy-Aware Learners","created":"2021-02-18","cited_by_count":1,"area":"distill"},{"id":"2209.07303","title":"Differentially Private Estimation of Hawkes Process","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2210.12693","title":"Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation","created":"2022-10-23","cited_by_count":1,"area":null},{"id":"2212.11890","title":"Decoding surface codes with deep reinforcement learning and probabilistic policy reuse","created":"2022-12-22","cited_by_count":1,"area":null},{"id":"2212.12517","title":"NARS vs. Reinforcement learning: ONA vs. Q-Learning","created":"2022-12-23","cited_by_count":1,"area":null},{"id":"2303.08115","title":"Human-Inspired Framework to Accelerate Reinforcement Learning","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2304.12828","title":"A optimization framework for herbal prescription planning based on deep reinforcement learning","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2406.02510","title":"Fairness-Optimized Synthetic EHR Generation for Arbitrary Downstream Predictive Tasks","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2407.08910","title":"PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization","created":"2024-07-12","cited_by_count":1,"area":"offlinerl"},{"id":"2409.15377","title":"Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2505.09114","title":"Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer","created":"2025-05-14","cited_by_count":1,"area":"offlinerl"},{"id":"2506.06649","title":"SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2508.19900","title":"Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning","created":"2025-08-27","cited_by_count":1,"area":"offlinerl"},{"id":"2511.12075","title":"Treatment Stitching with Schr\\\"odinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies","created":"2025-11-15","cited_by_count":1,"area":"offlinerl"},{"id":"2107.08988","title":"An Analysis of Reinforcement Learning for Malaria Control","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2112.13058","title":"Tri-Transformer Hawkes Process: Three Heads are better than one","created":"2021-12-24","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2203.10629","title":"Explicit User Manipulation in Reinforcement Learning Based Recommender Systems","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2211.04583","title":"Wall Street Tree Search: Risk-Aware Planning for Offline Reinforcement Learning","created":"2022-11-06","cited_by_count":0,"area":"offlinerl"},{"id":"2302.13268","title":"Revolutionizing Genomics with Reinforcement Learning Techniques","created":"2023-02-26","cited_by_count":0,"area":null},{"id":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2305.18412","title":"Short-term Temporal Dependency Detection under Heterogeneous Event Dynamic with Hawkes Processes","created":"2023-05-28","cited_by_count":0,"area":null},{"id":"2307.01519","title":"Deep Attention Q-Network for Personalized Treatment Recommendation","created":"2023-07-04","cited_by_count":0,"area":null},{"id":"2308.05385","title":"Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent Classification","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2310.14976","title":"Reinforcement learning in large, structured action spaces: A simulation study of decision support for spinal cord injury rehabilitation","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2408.01445","title":"MiranDa: Mimicking the Learning Processes of Human Doctors to Achieve Causal Inference for Medication Recommendation","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2408.09410","title":"BernGraph: Probabilistic Graph Neural Networks for EHR-based Medication Recommendations","created":"2024-08-18","cited_by_count":0,"area":null},{"id":"2502.10473","title":"Diverse Transformer Decoding for Offline Reinforcement Learning Using Financial Algorithmic Approaches","created":"2025-02-13","cited_by_count":0,"area":"offlinerl"},{"id":"2601.09220","title":"From Hawkes Processes to Attention: Time-Modulated Mechanisms for Event Sequences","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2604.21235","title":"Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.09818","title":"Learning to Compress Time-to-Control: A Reinforcement Learning Framework for Chronic Disease Management","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}