Reinforcement Learning on Humanoid gravity v2
6,360Average ReturnRESeL
Evaluation Results
| Method | Links | |
|---|---|---|
| RESeLTime steps=2M, Number of seeds=62024.05 | 6,360 | |
| ESCPTime steps=2M, Number of seeds=62024.05 | 3,857 | |
| PEARLTime steps=2M, Number of seeds=62024.05 | 3,849 | |
| OSITime steps=2M, Number of seeds=62024.05 | 3,518 | |
| SAC-MLPTime steps=2M, Number of seeds=62024.05 | 3,491 | |
| SAC-GRUTime steps=2M, Number of seeds=62024.05 | 3,064 | |
| EPITime steps=2M, Number of seeds=62024.05 | 2,673 | |
| ProMPTime steps=2M, Number of seeds=62024.05 | 423 |