Reinforcement Learning on Reacher target 0.5 gravity
-7.2RewardOptimal in Target
Evaluation Results
| Method | Links | |
|---|---|---|
| Optimal in Target2024.11 | -7.2 | |
| DARCProtocol=Training2024.11 | -11 | |
| DARAIL2024.11 | -12.2 | |
| DARCProtocol=Evaluation2024.11 | -13 |
Loading the SOTA2 catalog…