ResearchBenchmarksOffline multitask Reinforcement Learning on D4RL Antmaze umazeFollow593Average Episodic ReturnDiSPO445.32483.66522560.34Mar 10, 2024Evaluation ResultsMethodMethodLinksAverage Episodic ReturnDiSPO2024.03593COMBO2024.03574GC-IQL2024.03571FB2024.03469USFA2024.03462RaMP2024.03459MOPO2024.03451