Reinforcement Learning on Walker2d gravity v2
5,866Average ReturnRESeL
Evaluation results
| Method | Links | |
|---|---|---|
| RESeLTime steps=2M, Number of seeds=62024.05 | 5,866 | |
| PEARLTime steps=2M, Number of seeds=62024.05 | 4,284 | |
| SAC-MLPTime steps=2M, Number of seeds=62024.05 | 3,242 | |
| ESCPTime steps=2M, Number of seeds=62024.05 | 2,983 | |
| SAC-GRUTime steps=2M, Number of seeds=62024.05 | 2,098 | |
| EPITime steps=2M, Number of seeds=62024.05 | 1,901 | |
| OSITime steps=2M, Number of seeds=62024.05 | 1,467 | |
| ProMPTime steps=2M, Number of seeds=62024.05 | 271 |