PointCircle2 on Safety Gymnasium
0.85RewardCOptiDICE
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| COptiDICEcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.85 | 8.61 | |
| BC-Allcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.66 | 4.17 | |
| BCQ-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.66 | 2.6 | |
| CDTcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.64 | 1.05 | |
| CDT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.63 | 0.47 | |
| BEAR-Lagcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.63 | 4.27 | |
| BC-Safecost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.48 | 0.99 | |
| DT + SAScost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.42 | 1.69 | |
| CPQcost thresholds=3, evaluation episodes=20, random seeds=32026.04 | 0.24 | 3.58 |