Empirical coverage estimation on RiverSwim episode length T=100
94.9Q* Coverage (1, 0)
Model-based bootstrap with percentile CI
Updated 21d ago
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 94.9 | 95.3 | 97.5 | 94.9 | 95.1 | 95.3 | 95.5 | 96.3 | 96.7 | ||
| 94.2 | 94.4 | 95.2 | 94.2 | 93.8 | 94.4 | 94.1 | 94.8 | 95.3 | ||
| 90.2 | 90.7 | 91.8 | 90.2 | 90.5 | 90.7 | 90.6 | 90.3 | 89.6 | ||
| 84.2 | 84.2 | 83.8 | 84.2 | 84.3 | 84.2 | 82.9 | 81.8 | 82.3 | ||
| 68.9 | 69.3 | 56.6 | 68.9 | 69.1 | 69.3 | 69.2 | 69.5 | 61.1 | ||
2026.05 | 52 | 90.8 | 93.3 | 52 | 89.1 | 90.8 | 92.6 | 93.2 | 93.3 | |
| 50.2 | 84.2 | 90.2 | 50.2 | 72.4 | 83 | 88.7 | 90.7 | 90.8 | ||
2026.05 | 49.9 | 87.5 | 91.5 | 49.9 | 80.8 | 87.5 | 89.7 | 91 | 90.4 | |
| 48.2 | 75.9 | 85.3 | 48.2 | 65.5 | 74.2 | 80.8 | 86.3 | 87.2 | ||
| 47.6 | 80.8 | 85.5 | 47.6 | 70 | 79.7 | 84.4 | 86.7 | 86.8 | ||
| 42.2 | 68.9 | 74.2 | 42.2 | 58.9 | 67.3 | 71.9 | 76 | 76.4 | ||
2026.05 | 36.6 | 56 | 57.1 | 36.6 | 48.2 | 56 | 57.5 | 56.1 | 54.4 | |
| 35 | 54.9 | 52.4 | 35 | 52.1 | 54.9 | 52.7 | 54.5 | 49.2 | ||
| 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ||
| 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |