{"total":17,"rows":[{"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":"2102.09907","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","created":"2021-02-19","cited_by_count":35,"area":"offlinerl"},{"id":"2206.00810","title":"Offline Reinforcement Learning with Differential Privacy","created":"2022-06-02","cited_by_count":20,"area":"offlinerl"},{"id":"2203.09365","title":"Semi-Markov Offline Reinforcement Learning for Healthcare","created":"2022-03-17","cited_by_count":18,"area":"offlinerl"},{"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":"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":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2106.03833","title":"Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning","created":"2021-06-07","cited_by_count":4,"area":"offlinerl"},{"id":"2505.16242","title":"Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies","created":"2025-05-22","cited_by_count":4,"area":"offlinerl"},{"id":"2402.07344","title":"Measurement Scheduling for ICU Patients with Offline Reinforcement Learning","created":"2024-02-12","cited_by_count":3,"area":"offlinerl"},{"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":"2602.06603","title":"The hidden risks of temporal resampling in clinical reinforcement learning","created":"2026-02-06","cited_by_count":2,"area":"offlinerl"},{"id":"2306.14063","title":"Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data","created":"2023-06-24","cited_by_count":0,"area":"offlinerl"},{"id":"2602.03305","title":"medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functions","created":"2026-02-03","cited_by_count":0,"area":"offlinerl"},{"id":"2605.24405","title":"Generative OOD-regularized Model-based Policy Optimization","created":"2026-05-23","cited_by_count":0,"area":"offlinerl"},{"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"}],"next_cursor":null}