Reinforcement Learning on DMControl cheetah-run (expert)
96.28Avg Normalized ScoreCQL+S2P
Evaluation Results
| Method | Links | |
|---|---|---|
| CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.09 | 96.28 | |
| CQLBase Algorithm=CQL, S2P Augmentation=false2022.09 | 94.2 | |
| IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.09 | 87.18 | |
| IQLBase Algorithm=IQL, S2P Augmentation=false2022.09 | 79.89 | |
| SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.09 | 14.41 | |
| SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.09 | 8.92 |