Reinforcement Learning on Reacher MuJoCo (broken source)
-7.2RewardOptimal in Target
Evaluation results
| Method | Links | |
|---|---|---|
| Optimal in TargetMode=Optimal Oracle2024.11 | -7.2 | |
| DARCMode=Training in Source2024.11 | -11.2 | |
| DARAILMode=Evaluation in Target2024.11 | -13.7 | |
| DARCMode=Evaluation in Target2024.11 | -26.3 |