Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Off-policy Evaluation on DOPE averaged (three tasks)

0.37Normalized Value Gap

GALILEO

0.35640.44820.540.6318Jun 10, 2022
Updated 4d ago

Evaluation Results

MethodLinks
2022.06
0.370.440.09
2022.06
0.480.150.42
2022.06
0.54-0.190.34
0.57-0.140.33
2022.06
0.67-0.40.36
2022.06
0.710.290.17