List your company
ResearchFormerly WizWand

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

38.87Avg Normalized ScoreSLAC-off+S2P
28.00230.823533.64536.4665Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0938.87
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0928.62
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0928.6
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0928.57
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0928.56
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0928.42