AntRun on Safety Gymnasium
1.08RewardDT + SAS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 1.08 | 2.43 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.76 | 5.11 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.72 | 0.91 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.72 | 2.93 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.65 | 1.09 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.61 | 0.94 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.32 | 0.14 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.15 | 0.73 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.03 | 0.02 |