CarPush1 on Safety Gymnasium
0.31RewardDT + SAS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DT + SASBackbone=DT, Alignment strategy (SAS)=Lyapunov-Guided2026.04 | 0.31 | 51 | |
| CDT + SASBackbone=CDT, Alignment strategy (SAS)=Lyapunov-Guided2026.04 | 0.31 | 49 | |
| CDTBackbone=CDT2026.04 | 0.31 | 40 | |
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.31 | 51 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.31 | 49 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.31 | 40 | |
| BCQ-Lag2026.04 | 0.23 | 43 | |
| COptiDICE2026.04 | 0.23 | 50 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.23 | 43 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.23 | 50 | |
| BC-All2026.04 | 0.22 | 36 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.22 | 36 | |
| BEAR-Lag2026.04 | 0.21 | 54 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.21 | 54 | |
| BC-Safe2026.04 | 0.14 | 33 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.14 | 33 | |
| CPQ2026.04 | -0.03 | 95 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | -0.03 | 95 | |
| DCRL2026.04 | -0.1 | 9 |