List your company

PointPush2 on Safety-Gymnasium

44Normalized RewardFISOR
0.3211.662334.34Apr 29, 2026

Evaluation results

MethodLinks
FISOR2026.044411
DT + SASBackbone=DT, Alignment strategy (SAS)=Lyapunov-Guided2026.04240.64
DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04240.64
BCQ-Lag2026.04230.99
BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04230.99
CDTBackbone=CDT2026.04210.65
CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04210.65
CDT+SASAlignment=SAS, Base Model=CDT2026.042053
CDT + SASBackbone=CDT, Alignment strategy (SAS)=Lyapunov-Guided2026.04200.53
CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04200.53
BC-All2026.04180.91
BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04180.91
BEAR-Lag2026.04160.89
BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04160.89
BC-Safe2026.04110.8
CPQ2026.04111.04
BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04110.8
CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04111.04
COptiDICE2026.0421.18
DCRL2026.0420.07
COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.0421.18