List your company

AntVelocity on Safety Gym

0.93Normalized RewardReference policy (πref)
0.21240.39870.5850.7713May 20, 2026

Evaluation results

MethodLinks
Reference policy (πref)2026.050.938.04
PREFINE2026.050.930.13
PPL2026.050.90.66
BC2026.050.814.23
SafeDICE2026.050.790.5
CPQ2026.050.240.1