Reinforcement Learning on DMControl cheetah-run (mixed)
93.16Avg Normalized ScoreCQL+S2P
Evaluation Results
| Method | Links | |
|---|---|---|
| CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.09 | 93.16 | |
| CQLBase Algorithm=CQL, S2P Augmentation=false2022.09 | 92.63 | |
| IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.09 | 88.53 | |
| IQLBase Algorithm=IQL, S2P Augmentation=false2022.09 | 41.68 | |
| SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.09 | 26.39 | |
| SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.09 | 16.63 |