List your company

Off-policy Evaluation on DOPE averaged (three tasks)

0.37Normalized Value GapGALILEO
0.35640.44820.540.6318Jun 10, 2022

Evaluation results

MethodLinks
GALILEO2022.060.370.440.09
Best DICE2022.060.480.150.42
FQE (L2)2022.060.54-0.190.34
Doubly Rubost2022.060.57-0.140.33
IS2022.060.67-0.40.36
VPM2022.060.710.290.17