{"total":8,"rows":[{"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":"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":"2204.05477","title":"Deep Normed Embeddings for Patient Representation","created":"2022-04-12","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":"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":"2505.21596","title":"Learning optimal treatment strategies for intraoperative hypotension using deep reinforcement learning","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2602.00259","title":"Intelligent Reasoning Cues: A Framework and Case Study of the Roles of AI Information in Complex Decisions","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.04562","title":"Neetyabhas: A Framework for Uncertainty-Aware Public Policy Optimization in Rational Agent-Based Models","created":"2026-06-03","cited_by_count":0,"area":null}],"next_cursor":null}