{"total":71,"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":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68,"area":"offlinerl"},{"id":"2203.06369","title":"The Health Gym: Synthetic Health-Related Datasets for the Development of Reinforcement Learning Algorithms","created":"2022-03-12","cited_by_count":19,"area":null},{"id":"2302.07549","title":"Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications","created":"2023-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2101.08477","title":"Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment","created":"2021-01-21","cited_by_count":16,"area":null},{"id":"2210.02552","title":"Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning","created":"2022-10-05","cited_by_count":16,"area":"offlinerl"},{"id":"2302.00662","title":"Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders","created":"2023-02-01","cited_by_count":13,"area":"offlinerl"},{"id":"2306.03929","title":"Finding Counterfactually Optimal Action Sequences in Continuous State Spaces","created":"2023-06-06","cited_by_count":13,"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":"1905.09710","title":"Inverse Reinforcement Learning in Contextual MDPs","created":"2019-05-23","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":"2303.12281","title":"Synthetic Health-related Longitudinal Data with Mixed-type Variables Generated using Diffusion Models","created":"2023-03-22","cited_by_count":11,"area":"diffusion"},{"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":"2306.05637","title":"On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2103.05612","title":"Challenges for Reinforcement Learning in Healthcare","created":"2021-03-09","cited_by_count":7,"area":null},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2312.10385","title":"Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning","created":"2023-12-16","cited_by_count":7,"area":null},{"id":"2402.13147","title":"SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning","created":"2024-02-20","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":"2406.05646","title":"ICU-Sepsis: A Benchmark MDP Built from Real Medical Data","created":"2024-06-09","cited_by_count":6,"area":"deeprl"},{"id":"2203.13884","title":"A Conservative Q-Learning approach for handling distribution shift in sepsis treatment strategies","created":"2022-03-25","cited_by_count":5,"area":null},{"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":"2302.09212","title":"HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare","created":"2023-02-18","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":"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":"2206.11190","title":"Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2405.03082","title":"Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning","created":"2024-05-05","cited_by_count":4,"area":"deeprl"},{"id":"2409.04224","title":"Advancing Multi-Organ Disease Care: A Hierarchical Multi-Agent Reinforcement Learning Framework","created":"2024-09-06","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":"2505.09496","title":"Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data","created":"2025-05-14","cited_by_count":4,"area":"offlinerl"},{"id":"2104.10258","title":"Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning","created":"2021-04-20","cited_by_count":3,"area":"offlinerl"},{"id":"2108.04087","title":"Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2206.14198","title":"Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2211.06138","title":"Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2402.06367","title":"TEE4EHR: Transformer Event Encoder for Better Representation Learning in Electronic Health Records","created":"2024-02-09","cited_by_count":3,"area":null},{"id":"2404.13792","title":"Counterfactual Reasoning Using Predicted Latent Personality Dimensions for Optimizing Persuasion Outcome","created":"2024-04-21","cited_by_count":3,"area":null},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"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":"2502.07836","title":"Advancing Precision Oncology Through Modeling of Longitudinal and Multimodal Data","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2503.16544","title":"Causal Discovery and Counterfactual Reasoning to Optimize Persuasive Dialogue Policies","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2105.00568","title":"InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem","created":"2021-05-02","cited_by_count":2,"area":null},{"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":"2504.13904","title":"Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2510.24500","title":"MIMIC-Sepsis: A Curated Benchmark for Modeling and Learning from Sepsis Trajectories in the ICU","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2605.14723","title":"Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model","created":"2026-05-14","cited_by_count":2,"area":"wm"},{"id":"2607.08793","title":"EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2105.02580","title":"Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2204.05477","title":"Deep Normed Embeddings for Patient Representation","created":"2022-04-12","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":"2411.07372","title":"Identifying Differential Patient Care Through Inverse Intent Inference","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2512.10973","title":"TECM*: A Data-Driven Assessment to Reinforcement Learning Methods and Application to Heparin Treatment Strategy for Surgical Sepsis","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2202.09508","title":"Who Are the Best Adopters? User Selection Model for Free Trial Item Promotion","created":"2022-02-19","cited_by_count":0,"area":null},{"id":"2207.08040","title":"Reinforcement Learning For Survival, A Clinically Motivated Method For Critically Ill Patients","created":"2022-07-17","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":"2308.06094","title":"Reinforcement Logic Rule Learning for Temporal Point Processes","created":"2023-08-11","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":"2402.11123","title":"Optimizing Warfarin Dosing Using Contextual Bandit: An Offline Policy Learning and Evaluation Method","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2402.15826","title":"Reward Design for Justifiable Sequential Decision-Making","created":"2024-02-24","cited_by_count":0,"area":"alignment"},{"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":"2410.20017","title":"Off-Policy Selection for Initiating Human-Centric Experimental Design","created":"2024-10-26","cited_by_count":0,"area":null},{"id":"2506.23040","title":"Treatment, evidence, imitation, and chat","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2510.08350","title":"DeepEN: A Deep Reinforcement Learning Framework for Personalized Enteral Nutrition in Critical Care","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.12810","title":"Control of dynamical systems with neural networks","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2606.04632","title":"VentAgent: When LLMs Learn to Breathe -- Multi-Objective Arbitration for ARDS Ventilation","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.20206","title":"Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random","created":"2026-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2609.22232","title":"CNA: An AI-Oriented Comprehensive Normalized Assessment for Healthy Status and Application to Optimize RRT Strategies by Reinforcement Learning","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}