Reinforcement Learning on Ant MuJoCo (broken source)
6,183RewardOptimal in Target
Evaluation results
| Method | Links | |
|---|---|---|
| Optimal in TargetMode=Optimal Oracle2024.11 | 6,183 | |
| DARAILMode=Evaluation in Target2024.11 | 5,357 | |
| DARCMode=Training in Source2024.11 | 5,197 | |
| DARCMode=Evaluation in Target2024.11 | 4,280 |