List your company

PointGoal on Safety Gym

0.64Normalized RewardReference policy (πref)
0.20320.31660.430.5434May 20, 2026

Evaluation results

MethodLinks
Reference policy (πref)2026.050.642.82
PPL2026.050.460.95
PREFINE2026.050.40.24
CPQ2026.050.250.2
SafeDICE2026.050.240.26
BC2026.050.220.82