Weak Regret Minimization on Dueling Bandits
2Regret BoundTG-ITE-WEAK
Evaluation Results
| Method | Links | |
|---|---|---|
| TG-ITE-WEAKIdentify-Then-Exploit Policy=constant TREEASCENT warm start, then SCREENANDREPLACE2026.06 | 2 |
| Method | Links | |
|---|---|---|
| TG-ITE-WEAKIdentify-Then-Exploit Policy=constant TREEASCENT warm start, then SCREENANDREPLACE2026.06 | 2 |