Policy Optimization in CMAB on 1062 2
0.0028Mean Diff from Supervised (PV-loss)FastCB
Evaluation Results
| Method | Links | |
|---|---|---|
| FastCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0028 | |
| OPO-CMABEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0139 | |
| AdaCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0222 | |
| RegCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0333 | |
| SquareCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0444 |