List your company

Continuous-time policy evaluation on Large scale benchmark

0.226Mean Integrated RMSEGen2
0.104120.926811.74952.57219Apr 21, 2026

Evaluation results

MethodLinks
Gen22026.040.22640.9
Bellman baseline2026.040.383—
MBLinearanchor=fitted-dynamic, protocol=logged-trajectory2026.043.25—
MBQuadraticanchor=fitted-dynamic, protocol=logged-trajectory2026.043.273—