AntCircle on Safety Gymnasium
65RewardBEAR-Lag
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 65 | 5.48 | |
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 59 | 1.18 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 58 | 4.9 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 58 | 2.87 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 54 | 1.78 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 40 | 0.96 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 26 | 0.34 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 17 | 5.04 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0 | 0 |