Reinforcement Learning on Ant 1.5 gravity MuJoCo (test)
5,320RewardOptimal in Target
Evaluation results
| Method | Links | |
|---|---|---|
| Optimal in TargetEvaluation Protocol=Target Domain Optimal2024.11 | 5,320 | |
| DARAILEvaluation Protocol=Target Domain Evaluation2024.11 | 3,472 | |
| DARCEvaluation Protocol=Source Domain Training2024.11 | 2,170 | |
| DARCEvaluation Protocol=Target Domain Evaluation2024.11 | 1,587 |