List your company

CarGoal2 on Safety Gymnasium

0.65RewardCPQ
0.08840.23420.380.5258Apr 29, 2026

Evaluation results

MethodLinks
CPQ2026.040.653.75
CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.040.653.75
DT + SASBackbone=DT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.481.15
CDTBackbone=CDT2026.040.481.25
DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.481.15
CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.040.481.25
CDT + SASBackbone=CDT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.420.98
CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.420.98
BCQ-Lag2026.040.31.44
BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.040.31.44
BEAR-Lag2026.040.281.01
BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.040.281.01
COptiDICE2026.040.250.91
COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.040.250.91
BC-All2026.040.231.05
BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.040.231.05
BC-Safe2026.040.140.51
BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.040.140.51
DCRL2026.040.112.51