BallCircle on Safety Gymnasium
0.86BallCircle RewardBEAR-Lag
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.86 | 3.09 | |
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.81 | 1.41 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.77 | 1.07 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.74 | 4.71 | |
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.7 | 2.61 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.69 | 2.36 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.64 | 0.76 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.52 | 0.65 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.32 | 0.38 |