ResearchBenchmarksOffline Reinforcement Learning on DMControl finger-spin (random)Follow30.24Normalized ScoreSLAC-off-1.38646.824315.03523.2457Sep 30, 2022Evaluation ResultsMethodMethodLinksNormalized ScoreSLAC-offS2P Augmentation=falseS2P Augmentation=false2022.0930.24SLAC-off + S2PS2P Augmentation=trueS2P Augmentation=true2022.0927.62IQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.090.46CQLS2P Augmentation=falseS2P Augmentation=false2022.09-0.01CQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.09-0.11IQLS2P Augmentation=falseS2P Augmentation=false2022.09-0.17