ResearchBenchmarksOffline multitask Reinforcement Learning on Franka Kitchen kitchen-partialOffline multitask Reinforcement Learning on Franka Kitchen kitchen-partialFollow43Average Episodic ReturnDiSPO-1.729.8921.533.11Mar 10, 2024Evaluation resultsMethodMethodLinksAverage Episodic ReturnDiSPO2024.0343DiSPO2024.0343GC-Oracle2024.0333COMBO2024.0311COMBO2024.0311MOPO2024.038MOPO2024.038FB2024.034FB2024.034USFA2024.030RaMP2024.030USFA2024.030RaMP2024.030