Policy Optimization in CMAB on 339_3
0.0361Mean Diff from Supervised (PV-loss)AdaCB
Evaluation Results
| Method | Links | |
|---|---|---|
| AdaCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0361 | |
| FastCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0528 | |
| OPO-CMABEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0639 | |
| SquareCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.0694 | |
| RegCBEvaluation Protocol=Averaged-across-permutations2026.02 | 0.1083 |