List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl reacher-easy (random)

85.76Avg Normalized ScoreSLAC-off+S2P
31.669645.712359.75573.7977Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0985.76
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0977.43
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0975.01
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0970.45
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0952.32
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0933.75