Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Off-policy policy selection on Ring environment 100 batches

0.84Max Utility Difference

NORBU

0.46560.56280.660.7572May 27, 2021
Updated 2mo ago

Evaluation Results

MethodLinks
2021.05
0.840.030-0.71
2021.05
0.820.010-0.82
2021.05
0.82-0.26-0.27-0.96
2021.05
0.74-0.010-0.82
2021.05
0.72-0.27-0.33-0.96
2021.05
0.71-0.040-0.82
2021.05
0.61-0.29-0.31-0.78
2021.05
0.48-0.28-0.34-0.68