ResearchBenchmarksOffline Reinforcement Learning on DMControl ball-in-cup-catch (expert)Follow38.87Normalized ScoreSLAC-off + S2P28.00230.823533.64536.4665Sep 30, 2022Evaluation ResultsMethodMethodLinksNormalized ScoreSLAC-off + S2PS2P Augmentation=trueS2P Augmentation=true2022.0938.87CQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.0928.62IQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.0928.6IQLS2P Augmentation=falseS2P Augmentation=false2022.0928.57SLAC-offS2P Augmentation=falseS2P Augmentation=false2022.0928.56CQLS2P Augmentation=falseS2P Augmentation=false2022.0928.42