Policy Optimization in CMAB on 1006 2
0.1088Mean Diff (PV-loss)RegCB
Evaluation Results
| Method | Links | |
|---|---|---|
| RegCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.1088 | |
| FastCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.1227 | |
| SquareCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.1277 | |
| OPO-CMABEvaluation Protocol=Averaged-across-permutations2026.02 | 0.1541 | |
| AdaCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.1676 |