ResearchBenchmarksOffline Multitask Reinforcement Learning on Hopper jumpFollow832Average Episodic ReturnDiSPO644.8693.4742790.6Mar 10, 2024Evaluation ResultsMethodMethodLinksAverage Episodic ReturnDiSPO2024.03832MOPO2024.03753USFA2024.03746FB2024.03726COMBO2024.03670RaMP2024.03652