Bandit Learning on Synthetic Data Benign
318.52Mean RegretUCB
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| UCBReward Function Setting=Linear2026.02 | 318.52 | 21.2 | 352.1 | 23.09 | |
| Fair SmoothReward Function Setting=Smooth2026.02 | 344.82 | 6.61 | 0.1 | 0.3 | |
| Smooth BanditReward Function Setting=Smooth2026.02 | 412.78 | 12.28 | 939.4 | 10.32 | |
| Fair OLSReward Function Setting=Linear2026.02 | 425.28 | 19.4 | 12 | 20.41 | |
| GreedyReward Function Setting=Linear2026.02 | 625.25 | 194.08 | 785.2 | 218.79 | |
| OLS BanditReward Function Setting=Linear2026.02 | 853.25 | 93.32 | 1,083.2 | 111.54 | |
| RandomReward Function Setting=Smooth2026.02 | 2,082.66 | 24.59 | 0 | 0 | |
| RandomReward Function Setting=Linear2026.02 | 11,413.19 | 46.58 | 0 | 0 |