ResearchBenchmarksOffline Reinforcement Learning on D4RL Adroit door-human v0Follow10.7Normalized ReturnEDAC-0.742.235.28.17Oct 4, 2021Evaluation ResultsMethodMethodLinksNormalized ReturnEDACImplementation Source=...Implementation Source=Ours2021.1010.7CQLImplementation Source=...Implementation Source=Paper2021.109.1BC2021.102.8CQLImplementation Source=...Implementation Source=Reproduced2021.101.2SAC2021.10-0.3REM2021.10-0.3SAC-NImplementation Source=...Implementation Source=Ours2021.10-0.3