List your company

Continuous-time policy evaluation on benchmark Medium scale

0.024Mean Integrated RMSEMBQuadratic
0.004280.137390.27050.40361Apr 21, 2026

Evaluation results

MethodLinks
MBQuadraticanchor=fitted-dynamic, protocol=logged-trajectory2026.040.024—
Gen22026.040.05947.8
Bellman baseline2026.040.113—
MBLinearanchor=fitted-dynamic, protocol=logged-trajectory2026.040.517—