ResearchBenchmarksOffline Reinforcement Learning on D4RL Adroit hammer-human v0Follow3.1Normalized ReturnBC0.0840.8671.652.433Oct 4, 2021Evaluation ResultsMethodMethodLinksNormalized ReturnBC2021.103.1CQLImplementation Source=...Implementation Source=Paper2021.102.1EDACImplementation Source=...Implementation Source=Ours2021.100.8CQLImplementation Source=...Implementation Source=Reproduced2021.100.6REM2021.100.3SAC-NImplementation Source=...Implementation Source=Ours2021.100.3SAC2021.100.2