Counterfactual Policy Evaluation on Sepsis Slightly Suboptimal Path
8,000Lowest Cumulative RewardGumbel-max
Evaluation Results
| Method | Links | |
|---|---|---|
| Gumbel-max2025.02 | 8,000 | |
| ICFMDP2025.02 | -5,980 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Gumbel-max2025.02 | 8,000 | |
| ICFMDP2025.02 | -5,980 |