BallRun on Safety Gymnasium
0.99RewardDT + SAS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.99 | 1.6 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.76 | 3.91 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.6 | 5.08 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.59 | 3.52 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.39 | 1.16 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.27 | 1.46 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.22 | 1.27 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.04 | 0.29 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | -0.47 | 5.03 |