Reinforcement Learning on Walker2d 1.5 gravity MuJoCo (test)
4,409RewardDARAIL
Evaluation results
| Method | Links | |
|---|---|---|
| DARAILEvaluation Protocol=Target Domain Evaluation2024.11 | 4,409 | |
| Optimal in TargetEvaluation Protocol=Target Domain Optimal2024.11 | 4,254 | |
| DARCEvaluation Protocol=Source Domain Training2024.11 | 4,130 | |
| DARCEvaluation Protocol=Target Domain Evaluation2024.11 | 257 |