Counterfactual Audits Reveal Toxic Mimicry in ICU Sepsis RL Policies
Standard offline RL metrics like MSE and FQE only test imitation and overlook “toxic mimicry,” where agents reproduce harmful treatment patterns. Using a Counterfactual Clinical Audit on MIMIC‑III, the authors show a Medical Decision Transformer cut vasopressor dosage as lactate rose—directly contradicting SSC guidelines—while a causally shielded model stayed clinically consistent.