Policy Optimization in CMAB on 848_2
0.0368Mean Diff from Supervised (PV-loss)RegCB
Evaluation Results
| Method | Links | |
|---|---|---|
| RegCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0368 | |
| AdaCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0842 | |
| SquareCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0895 | |
| FastCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0947 | |
| OPO-CMABEvaluation Protocol=Averaged-across-permutations2026.02 | 0.1421 |