Reinforcement Learning on HalfCheetah 0.5 gravity (target)
7,559RewardOptimal in Target
Evaluation Results
| Method | Links | |
|---|---|---|
| Optimal in Target2024.11 | 7,559 | |
| DARCProtocol=Training2024.11 | 5,721 | |
| DARAIL2024.11 | 5,485 | |
| DARCProtocol=Evaluation2024.11 | 1,686 |
Loading the SOTA2 catalog…