ResearchBenchmarksOffline Reinforcement Learning on D4RL Adroit relocate-human v0Offline Reinforcement Learning on D4RL Adroit relocate-human v0Follow0.35Normalized ReturnCQL-0.326-0.15050.0250.2005Oct 4, 2021Evaluation resultsMethodMethodLinksNormalized ReturnCQLImplementation Source=...Implementation Source=Paper2021.100.35EDACImplementation Source=...Implementation Source=Ours2021.100.1BC2021.100CQLImplementation Source=...Implementation Source=Reproduced2021.100SAC-NImplementation Source=...Implementation Source=Ours2021.10-0.1SAC2021.10-0.3REM2021.10-0.3