List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl cheetah-run (mixed)

93.16Avg Normalized ScoreCQL+S2P
13.568834.231954.89575.5581Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0993.16
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0992.63
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0988.53
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0941.68
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0926.39
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0916.63