Reinforcement Learning on Reacher 1.5 gravity MuJoCo (test)
-8.3RewardOptimal in Target
Evaluation results
| Method | Links | |
|---|---|---|
| Optimal in TargetEvaluation Protocol=Target Domain Optimal2024.11 | -8.3 | |
| DARAILEvaluation Protocol=Target Domain Evaluation2024.11 | -9.5 | |
| DARCEvaluation Protocol=Source Domain Training2024.11 | -17.2 | |
| DARCEvaluation Protocol=Target Domain Evaluation2024.11 | -55.3 |