List your company

CarButton2 on Safety Gymnasium

0.37RewardCPQ
-0.15-0.0150.120.255Apr 29, 2026

Evaluation results

MethodLinks
CPQ2026.040.3712.51
CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.040.3712.51
CDT + SASBackbone=CDT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.31.11
CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.31.11
DT + SASBackbone=DT, Alignment strategy (SAS)=Lyapunov-Guided2026.040.140.84
DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.040.140.84
CDTBackbone=CDT2026.040.131.58
CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.040.131.58
DCRL2026.040.091.42
BCQ-Lag2026.040.062.13
BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.040.062.13
BC-Safe2026.04-0.010.63
BEAR-Lag2026.04-0.012.29
BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04-0.010.63
BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04-0.012.29
COptiDICE2026.04-0.071.59
COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04-0.071.59
BC-All2026.04-0.131.24
BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04-0.131.24