Reinforcement Learning on Ant-gravity v2
5,949Average ReturnRESeL
Evaluation Results
| Method | Links | |
|---|---|---|
| RESeLTime steps=2M, Number of seeds=62024.05 | 5,949 | |
| PEARLTime steps=2M, Number of seeds=62024.05 | 4,065 | |
| ESCPTime steps=2M, Number of seeds=62024.05 | 3,403 | |
| SAC-MLPTime steps=2M, Number of seeds=62024.05 | 1,840 | |
| ProMPTime steps=2M, Number of seeds=62024.05 | 1,253 | |
| OSITime steps=2M, Number of seeds=62024.05 | 878 | |
| EPITime steps=2M, Number of seeds=62024.05 | 854 | |
| SAC-GRUTime steps=2M, Number of seeds=62024.05 | 738 |