PoleBalance on Walker robot
876Average ReturnHSD-3
Evaluation Results
| Method | Links | |
|---|---|---|
| HSD-3training samples=7.5M, seeds=92021.10 | 876 | |
| SD*training samples=7.5M, seeds=92021.10 | 868.2 | |
| SACtraining samples=7.5M, seeds=92021.10 | 866.8 | |
| DIAYN-Ctraining samples=7.5M, seeds=92021.10 | 839.9 | |
| SDtraining samples=7.5M, seeds=92021.10 | 789.5 | |
| Switching Ensembletraining samples=7.5M, seeds=92021.10 | 569.4 | |
| HIDIOtraining samples=7.5M, seeds=92021.10 | 117.6 | |
| HSD-Bandittraining samples=7.5M, seeds=92021.10 | 61 | |
| HIRO-SACtraining samples=7.5M, seeds=92021.10 | 23.8 |