List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl walker-walk (random)

18.23Avg Normalized ScoreSLAC-off
-1.17643.86188.913.9382Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0918.23
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0917.38
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0910.44
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.094.03
IQLBase Algorithm=IQL, S2P Augmentation=false2022.09-0.28
CQLBase Algorithm=CQL, S2P Augmentation=false2022.09-0.43