QALY Optimization on Healthcare Dataset (High Risk)
19.78Most Resilient ScoreBDRL (Base)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| BDRL (Base)variant=Base2026.04 | 19.78 | 19.63 | 19.37 | |
| DRL (λ = 0)lambda=02026.04 | 19.78 | 18.64 | 17.06 | |
| Deep Q-Network2026.04 | 17.82 | 16.27 | 14.92 | |
| Q-learning2026.04 | 15.54 | 14.18 | 11.98 |