CarCircle2 on Safety Gymnasium
0.77RewardCOptiDICE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.77 | 7.99 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.76 | 6.44 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.74 | 6.82 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.72 | 6.58 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.66 | 2.53 | |
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.63 | 1.69 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.56 | 0.62 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.54 | 3.38 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.44 | 2.69 |