CarCircle1 on Safety Gymnasium
0.76RewardBEAR-Lag
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.76 | 5.46 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.73 | 5.25 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.72 | 4.39 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.7 | 5.72 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.6 | 1.73 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.47 | 0.52 | |
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.41 | 1.84 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.37 | 1.38 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.02 | 2.29 |