Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Off-policy evaluation on ScienceWorld (ETO)
Loading...
0.97
Rho
WIS
-0.0388
0.2231
0.485
0.7469
Jun 4, 2026
Rho
CI95
P-Value
Updated 1mo ago
Evaluation Results
Method
Method
Links
Rho
CI95
P-Value
WIS
n=5
2026.06
0.97
-
-
ADWM
n=5
2026.06
0.82
0
0.089
FQE
n=5
2026.06
0.21
-
-
DR
n=5
2026.06
0.21
-
-
IS
n=5
2026.06
0.21
-
-
DM
n=5
2026.06
0
-
-
Feedback
Search any
task
Search any
task
