QALY Optimization on Healthcare Dataset Intermediate Risk
26.63Most Resilient ValueBDRL (Base)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BDRL (Base)variant=Base2026.04 | 26.63 | 26.35 | 26.26 | |
| DRL (λ = 0)lambda=02026.04 | 26.63 | 26.08 | 24.46 | |
| Deep Q-Network2026.04 | 25.11 | 24.05 | 22.47 | |
| Q-learning2026.04 | 22.57 | 21.09 | 19.43 |