Reinforcement Learning on Ant 0.5 gravity (target)
3,380Total RewardOptimal in Target
Evaluation Results
| Method | Links | |
|---|---|---|
| Optimal in Target2024.11 | 3,380 | |
| DARCProtocol=Evaluation2024.11 | 2,058 | |
| DARAIL2024.11 | 990 | |
| DARCProtocol=Training2024.11 | 348 |
Loading the SOTA2 catalog…