List your company

Policy Optimization in CMAB on 928 2

0.1565Mean Difference from Supervised (PV-loss)AdaCB
0.1538260.1720220.1902170.208413Feb 14, 2026

Evaluation results

MethodLinks
AdaCBEvaluation Protocol=Averaged-across-permutations2026.020.1565
OPO-CMABEvaluation Protocol=Averaged-across-permutations2026.020.1978
FastCBEvaluation Protocol=Averaged-across-permutations2026.020.2
SquareCBEvaluation Protocol=Averaged-across-permutations2026.020.2152
RegCBEvaluation Protocol=Averaged-across-permutations2026.020.2239