Reinforcement Learning on HalfCheetah gravity v2
8,705Average ReturnRESeL
Evaluation Results
| Method | Links | |
|---|---|---|
| RESeLTime steps=2M, Number of seeds=62024.05 | 8,705 | |
| ESCPTime steps=2M, Number of seeds=62024.05 | 7,805 | |
| SAC-GRUTime steps=2M, Number of seeds=62024.05 | 7,022 | |
| OSITime steps=2M, Number of seeds=62024.05 | 6,874 | |
| SAC-MLPTime steps=2M, Number of seeds=62024.05 | 6,225 | |
| EPITime steps=2M, Number of seeds=62024.05 | 6,053 | |
| PEARLTime steps=2M, Number of seeds=62024.05 | 5,453 | |
| ProMPTime steps=2M, Number of seeds=62024.05 | 885 |