{"total":18,"rows":[{"id":"2106.05142","title":"Neighborhood Contrastive Learning Applied to Online Patient Monitoring","created":"2021-06-09","cited_by_count":32,"area":null},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"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":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2306.03929","title":"Finding Counterfactually Optimal Action Sequences in Continuous State Spaces","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2312.05933","title":"Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression","created":"2023-12-10","cited_by_count":10,"area":null},{"id":"2301.05089","title":"Approximate Information States for Worst-Case Control and Learning in Uncertain Systems","created":"2023-01-12","cited_by_count":3,"area":null},{"id":"2304.01366","title":"Enabling A Network AI Gym for Autonomous Cyber Agents","created":"2023-04-03","cited_by_count":3,"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":"2507.06628","title":"Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2508.07681","title":"MORE-CLEAR: Multimodal Offline Reinforcement learning for Clinical notes Leveraged Enhanced State Representation","created":"2025-08-11","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":"2204.05477","title":"Deep Normed Embeddings for Patient Representation","created":"2022-04-12","cited_by_count":1,"area":null},{"id":"2310.09462","title":"A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading","created":"2023-10-14","cited_by_count":1,"area":null},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","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":"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":"2509.03393","title":"Exploring a Graph-based Approach to Offline Reinforcement Learning for Sepsis Treatment","created":"2025-09-03","cited_by_count":0,"area":null}],"next_cursor":null}