List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl walker-walk (mixed)

97.84Avg Normalized ScoreCQL+S2P
26.267244.848663.4382.0114Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0997.84
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0997.18
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0996.07
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0995.49
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0992.6
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0929.02