CarRun on Safety Gymnasium
8.12RewardDT + SAS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 8.12 | 1.06 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.99 | 0.65 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.97 | 0.33 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.95 | 1.79 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.94 | 0.22 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.94 | 0.15 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.87 | 0 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.72 | 0.39 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.68 | 7.78 |