List your company

CarPush1 on Safety Gymnasium

0.31RewardDT + SAS
-0.1164-0.00570.1050.2157Apr 29, 2026

Evaluation results

MethodLinks
DT + SASBackbone=DT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.3151
CDT + SASBackbone=CDT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.3149
CDTBackbone=CDT2026.040.3140
DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.3151
CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.3149
CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.040.3140
BCQ-Lag2026.040.2343
COptiDICE2026.040.2350
BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.040.2343
COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.040.2350
BC-All2026.040.2236
BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.040.2236
BEAR-Lag2026.040.2154
BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.040.2154
BC-Safe2026.040.1433
BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.040.1433
CPQ2026.04-0.0395
CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04-0.0395
DCRL2026.04-0.19