DroneCircle on Safety Gymnasium
0.82RewardDT + SAS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.82 | 1.55 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.8 | 3.07 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.78 | 3.68 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.72 | 3.03 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.63 | 0.98 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.56 | 0.57 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.51 | 0.42 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.26 | 1.02 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | -0.22 | 1.28 |