ResearchBenchmarksOffline Reinforcement Learning on Adroit human-total v1Follow80.9Average Normalized ScoreTSRL6.64425.92245.264.478Jun 7, 2023Evaluation ResultsMethodMethodLinksAverage Normalized ScoreTSRLRatio=1, Size=5kRatio=1, Size=5k2023.0680.9IQLRatio=1, Size=5kRatio=1, Size=5k2023.0677.3CQLRatio=1, Size=5kRatio=1, Size=5k2023.0652.2DOGERatio=1, Size=5kRatio=1, Size=5k2023.0639BCRatio=1, Size=5kRatio=1, Size=5k2023.0636.4TD3+BCRatio=1, Size=5kRatio=1, Size=5k2023.0610.6MOPORatio=1, Size=5kRatio=1, Size=5k2023.069.5