List your company

CarButton1 on Safety Gymnasium

0.42RewardCPQ
-0.10.0350.170.305Apr 29, 2026

Evaluation results

MethodLinks
CPQ2026.040.429.66
CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.040.429.66
CDT + SASBackbone=CDT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.270.98
CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.270.98
CDTBackbone=CDT2026.040.211.6
CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.040.211.6
BEAR-Lag2026.040.182.72
BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.040.182.72
DT + SASBackbone=DT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.171.08
DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.171.08
DCRL2026.040.120.95
BC-Safe2026.040.070.85
BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.040.070.85
BCQ-Lag2026.040.041.63
BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.040.041.63
BC-All2026.040.031.38
BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.040.031.38
COptiDICE2026.04-0.081.68
COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04-0.081.68