Bandit Learning on Synthetic Data Attack
1,382.96Regret (Mean)Robust Fair Smooth
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Robust Fair SmoothReward Function Setting=Smooth2026.02 | 1,382.96 | 47.95 | 147.7 | 62.55 | |
| Smooth BanditReward Function Setting=Smooth2026.02 | 1,634.61 | 40.5 | 2,994.7 | 99.57 | |
| Fair SmoothReward Function Setting=Smooth2026.02 | 1,933.4 | 107.22 | 3,043.2 | 250.21 | |
| Robust Fair OLSReward Function Setting=Linear2026.02 | 2,770.77 | 75.02 | 446.1 | 174.63 | |
| UCBReward Function Setting=Linear2026.02 | 3,525.15 | 744.49 | 3,902.4 | 523.55 | |
| RandomReward Function Setting=Smooth2026.02 | 4,161.99 | 26.69 | 0 | 0 | |
| GreedyReward Function Setting=Linear2026.02 | 5,192.26 | 76.94 | 5,053.9 | 75.53 | |
| OLS BanditReward Function Setting=Linear2026.02 | 6,673.63 | 1,133.66 | 5,575.2 | 256.5 | |
| Fair OLSReward Function Setting=Linear2026.02 | 7,069.32 | 2,120.75 | 4,752.1 | 590.15 | |
| RandomReward Function Setting=Linear2026.02 | 22,859.78 | 131.63 | 0 | 0 |