List your company

Reinforcement Learning on DMControl finger-spin (expert)

98.42Averaged Normalized ScoreIQL
21.803241.694161.58581.4759Sep 30, 2022

Evaluation results

MethodLinks
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0998.42
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0997.25
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0994.42
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0981.05
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0973.07
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0924.75