Off-policy Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.735Cumulative Reward
72
May 14, 2026
55.7Qπ(1, 0) Coverage
20
May 13, 2026
0.617Downstream OPE RMSE
12
May 29, 2026
0.001MSE
12
Feb 26, 2026
0.007Interval Length
11
Jun 15, 2026
40.07Interval Length
11
Jun 15, 2026
-0.4Interval Length
11
Jun 15, 2026
-428.51Point Estimate Error
9
Jun 15, 2026
0.719Confidence Interval
8
Jun 15, 2026
1,820.79Confidence Interval
8
Jun 15, 2026
-0.001Confidence Interval
8
Jun 15, 2026
-2,209.73Confidence Interval
8
Jun 15, 2026
20.02V_hat(pi)
6
Jun 19, 2026
10,667.9V_hat(pi)
6
Jun 19, 2026
9.55V_hat(pi)
6
Jun 19, 2026
10,408.2V_hat(pi)
6
Jun 19, 2026
0.81Correlation Coefficient (rho)
6
Jun 5, 2026
0.9rho
6
Jun 5, 2026
0.8Rho
6
Jun 5, 2026
0.82Rho
6
Jun 5, 2026
0.97Rho
6
Jun 5, 2026
0.9Rho
6
Jun 5, 2026
0.001MSE
6
Feb 26, 2026
0.012MSE
6
Feb 26, 2026
0.002MSE
6
Feb 26, 2026