{"total":60,"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":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"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":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71,"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":"2305.01738","title":"Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare","created":"2023-05-02","cited_by_count":42,"area":"offlinerl"},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"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":"2303.17156","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","created":"2023-03-30","cited_by_count":18,"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":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15,"area":null},{"id":"2006.13189","title":"Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation","created":"2020-06-23","cited_by_count":14,"area":"offlinerl"},{"id":"2206.05581","title":"Federated Offline Reinforcement Learning","created":"2022-06-11","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":"2109.06312","title":"Learning-to-defer for sequential medical decision-making under uncertainty","created":"2021-09-13","cited_by_count":12,"area":null},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2405.18610","title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2103.05612","title":"Challenges for Reinforcement Learning in Healthcare","created":"2021-03-09","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":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2111.14272","title":"Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation","created":"2021-11-28","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":"2405.18556","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","created":"2024-05-28","cited_by_count":5,"area":"offlinerl"},{"id":"2305.01400","title":"Get Back Here: Robust Imitation by Return-to-Distribution Planning","created":"2023-05-02","cited_by_count":4,"area":"offlinerl"},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2103.00098","title":"Reducing Conservativeness Oriented Offline Reinforcement Learning","created":"2021-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2111.14346","title":"Pessimistic Model Selection for Offline Deep Reinforcement Learning","created":"2021-11-29","cited_by_count":3,"area":"offlinerl"},{"id":"2411.11088","title":"An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces","created":"2024-11-17","cited_by_count":3,"area":"offlinerl"},{"id":"2306.08044","title":"Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care","created":"2023-06-13","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":"2512.00919","title":"Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression","created":"2025-11-30","cited_by_count":2,"area":null},{"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":"2111.11113","title":"Case-based off-policy policy evaluation using prototype learning","created":"2021-11-22","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":"2305.12679","title":"Offline Reinforcement Learning with Additional Covering Distributions","created":"2023-05-22","cited_by_count":1,"area":"offlinerl"},{"id":"2402.02858","title":"Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning","created":"2024-02-05","cited_by_count":1,"area":"offlinerl"},{"id":"2404.03105","title":"Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation","created":"2024-04-03","cited_by_count":1,"area":"deeprl"},{"id":"2107.08988","title":"An Analysis of Reinforcement Learning for Malaria Control","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2108.10453","title":"Continuous Treatment Recommendation with Deep Survival Dose Response Function","created":"2021-08-24","cited_by_count":0,"area":null},{"id":"2110.02879","title":"Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations","created":"2021-10-06","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":"2209.08682","title":"Towards Robust Off-Policy Evaluation via Human Inputs","created":"2022-09-18","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":"2307.01519","title":"Deep Attention Q-Network for Personalized Treatment Recommendation","created":"2023-07-04","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":"2409.09169","title":"Curricula for Learning Robust Policies with Factored State Representations in Changing Environments","created":"2024-09-13","cited_by_count":0,"area":"deeprl"},{"id":"2412.07895","title":"How Should We Represent History in Interpretable Models of Clinical Policies?","created":"2024-12-10","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":"2506.00818","title":"Generalized Linear Markov Decision Process","created":"2025-06-01","cited_by_count":0,"area":"offlinerl"},{"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":"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":"2605.13054","title":"Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2606.01028","title":"A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning","created":"2026-05-31","cited_by_count":0,"area":"deeprl"},{"id":"2606.19481","title":"Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning","created":"2026-06-17","cited_by_count":0,"area":"offlinerl"},{"id":"2608.11410","title":"Unmasking Toxic Mimicry in Medical Offline Reinforcement Learning for ICU Sepsis Management via Counterfactual Clinical Audits","created":"2026-08-11","cited_by_count":0,"area":"offlinerl"},{"id":"2608.30442","title":"Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry","created":"2026-08-31","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}