Reinforcement Learning on Walker2d MuJoCo (broken source)
4,366RewardDARAIL
Evaluation results
| Method | Links | |
|---|---|---|
| DARAILMode=Evaluation in Target2024.11 | 4,366 | |
| Optimal in TargetMode=Optimal Oracle2024.11 | 3,899 | |
| DARCMode=Training in Source2024.11 | 3,896 | |
| DARCMode=Evaluation in Target2024.11 | 2,669 |