Limbo on Walker robot
12.2Average ReturnSD*
Evaluation Results
| Method | Links | |
|---|---|---|
| SD*training samples=7.5M, seeds=92021.10 | 12.2 | |
| HSD-3training samples=7.5M, seeds=92021.10 | 11.7 | |
| SDtraining samples=7.5M, seeds=92021.10 | 11 | |
| DIAYN-Ctraining samples=7.5M, seeds=92021.10 | 7.5 | |
| HSD-Bandittraining samples=7.5M, seeds=92021.10 | 2.4 | |
| Switching Ensembletraining samples=7.5M, seeds=92021.10 | 1.9 | |
| HIRO-SACtraining samples=7.5M, seeds=92021.10 | 0.9 | |
| SACtraining samples=7.5M, seeds=92021.10 | -0.1 | |
| HIDIOtraining samples=7.5M, seeds=92021.10 | -0.1 |