Reinforcement Learning on Walker2d 0.5 gravity (target)
2,830RewardOptimal in Target
Evaluation Results
| Method | Links | |
|---|---|---|
| Optimal in Target2024.11 | 2,830 | |
| DARCProtocol=Training2024.11 | 936 | |
| DARAIL2024.11 | 878 | |
| DARCProtocol=Evaluation2024.11 | 706 |
Loading the SOTA2 catalog…