ResearchBenchmarksOffline Reinforcement Learning on DMControl ball-in-cup-catch (random)Follow85.76Normalized ScoreSLAC-off + S2P50.982460.011269.0478.0688Sep 30, 2022Evaluation ResultsMethodMethodLinksNormalized ScoreSLAC-off + S2PS2P Augmentation=trueS2P Augmentation=true2022.0985.76IQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.0982.28SLAC-offS2P Augmentation=falseS2P Augmentation=false2022.0977.43CQL + S2PS2P Augmentation=trueS2P Augmentation=true2022.0975.01IQLS2P Augmentation=falseS2P Augmentation=false2022.0974.77CQLS2P Augmentation=falseS2P Augmentation=false2022.0952.32