List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl ball-in-cup-catch (mixed)

51.28Averaged Normalized ScoreCQL+S2P
27.630433.770239.9146.0498Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0951.28
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0941.94
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0940.41
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0937.79
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0930.82
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0928.54