List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl walker-walk (expert)

97.97Averaged Normalized ScoreCQL+S2P
8.259631.549854.8478.1302Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0997.97
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0995.43
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0994.97
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0994.34
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0970.95
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0911.71