Policy Optimization in CMAB on 476 2
-0.012Mean Diff from Supervised (PV-loss)SquareCB
Evaluation Results
| Method | Links | |
|---|---|---|
| SquareCBEvaluation Protocol=Averaged-across-permutations2026.02 | -0.012 | |
| OPO-CMABEvaluation Protocol=Averaged-across-permutations2026.02 | 0.008 | |
| RegCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.022 | |
| AdaCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.038 | |
| FastCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.046 |