Sepsis Treatment Reinforcement Learning on MIMIC-III (Random (standard))
67.9FQEOPL-MT-MNAR
Evaluation results
| Method | Links | ||
|---|---|---|---|
| OPL-MT-MNARCategory=MNAR-aware + DocProcess2026.04 | 67.9 | 88.6 | |
| DDPG with Clinician SupervisionCategory=Continuous DDPG2026.04 | 52.9 | 84.4 | |
| Model-Based BNN PlannerCategory=Model-based BNN2026.04 | 49.8 | 82.6 | |
| Peng et al. 2018Category=Hybrid (kernel + deep)2026.04 | 49.3 | 82.8 | |
| AI ClinicianCategory=Tabular2026.04 | 48.7 | 81.2 | |
| Continuous State-Space DDQNCategory=Model-free DDQN2026.04 | 47.6 | 82.2 |