List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl reacher-easy (expert)

58.19Averaged Normalized ScoreIQL+S2P
25.346833.873442.450.9266Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0958.19
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0957.68
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0952.13
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0942.85
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0932.54
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0926.61