ResearchBenchmarksOffline Reinforcement Learning on DMControl cheetah-run (random)Follow18.23Normalized ScoreSLAC-off-1.17643.86188.913.9382Sep 30, 2022Evaluation ResultsMethodMethodLinksNormalized ScoreSLAC-offS2P Augmentation=falseS2P Augmentation=false2022.0918.23SLAC-off + S2PS2P Augmentation=trueS2P Augmentation=true2022.0917.38IQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.0912.64CQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.0910.44IQLS2P Augmentation=falseS2P Augmentation=false2022.0910.28CQLS2P Augmentation=falseS2P Augmentation=false2022.09-0.43