List your company
ResearchFormerly WizWand

Reinforcement Learning on DMControl cartpole-swingup (expert)

20.43Averaged Normalized ScoreIQL
10.8113.307515.80518.3025Sep 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
IQLBase Algorithm=IQL, S2P Augmentation=false2022.0920.43
CQLBase Algorithm=CQL, S2P Augmentation=false2022.0919.35
CQL+S2PBase Algorithm=CQL, S2P Augmentation=true2022.0918.54
IQL+S2PBase Algorithm=IQL, S2P Augmentation=true2022.0918.37
SLAC-offBase Algorithm=SLAC-off, S2P Augmentation=false2022.0914.11
SLAC-off+S2PBase Algorithm=SLAC-off, S2P Augmentation=true2022.0911.18