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

Off-Policy Learning on Wiki10-31K Synthetic tau=1 (test)

55.72P@5

UIPS

34.566440.058245.5551.0418Mar 11, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.03
55.7215.7160.74
2023.03
55.2615.6560.07
2023.03
55.2615.6160.16
2023.03
55.115.6159.95
2023.03
55.0215.5160
2023.03
54.9915.4560.4
2023.03
52.8214.9157.91
2023.03
52.7914.9257.81
2023.03
47.3413.2553.26
2023.03
39.0410.9647.49
2023.03
38.9610.9647.39
2023.03
38.9410.9547.41
2023.03
36.1610.1945.22
2023.03
35.389.8741.44