Reinforcement Learning on HalfCheetah 1.5 gravity MuJoCo (test)
6,894RewardOptimal in Target
Evaluation results
| Method | Links | |
|---|---|---|
| Optimal in TargetEvaluation Protocol=Target Domain Optimal2024.11 | 6,894 | |
| DARCEvaluation Protocol=Source Domain Training2024.11 | 4,897 | |
| DARAILEvaluation Protocol=Target Domain Evaluation2024.11 | 4,093 | |
| DARCEvaluation Protocol=Target Domain Evaluation2024.11 | 653 |