Regret Minimization on KL-regularized Bandits Preference w/ Linear Reward
2RegretOnline Iterative GSHF
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Online Iterative GSHFType=Upper Bound2026.03 | 2 | — | — |
Loading the SOTA2 catalog…
| Method | Links | |||
|---|---|---|---|---|
| Online Iterative GSHFType=Upper Bound2026.03 | 2 | — | — |