PointCircle1 on Safety Gymnasium
0.86RewardCOptiDICE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.86 | 5.51 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.79 | 3.98 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.73 | 3.28 | |
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.69 | 1.81 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.59 | 0.69 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.54 | 0.21 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.54 | 2.38 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.43 | 0.75 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.41 | 0.16 |