Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation

Excerpt

arXiv:2608.16482v1 Announce Type: new Abstract: The dosing of intravenous fluids and vasopressors in sepsis is a sequential decision made under uncertainty and guided largely by clinical judgment, which makes it a natural target for reinforcement learning from historical care. Because a learned policy cannot be trialed on patients, its value must be estimated off-policy, and such estimates can be fragile and optimistic. This work advances the reliable evaluation of sepsis treatment policies by c