CarCircle on Safety Gymnasium
0.85RewardDT + SAS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.85 | 1.76 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.75 | 0.95 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.74 | 2.18 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.71 | 0.33 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.63 | 1.89 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.58 | 3.74 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.5 | 0.84 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.49 | 3.14 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.19 | 0.22 |