List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl cartpole-swingup (mixed)

16.36Avg Normalized ScoreSLAC-off+S2P
-5.50080.17465.8511.5254Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0916.36
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0914.76
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0914.51
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0914.49
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0914.04
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.09-4.66