ResearchBenchmarksOffline multitask Reinforcement Learning on Hopper backwardOffline multitask Reinforcement Learning on Hopper backwardFollow596Average Episodic ReturnMOPO177.92286.46395503.54Mar 10, 2024Evaluation resultsMethodMethodLinksAverage Episodic ReturnMOPO2024.03596MOPO2024.03596DiSPO2024.03367DiSPO2024.03367FB2024.03269FB2024.03269USFA2024.03261USFA2024.03261RaMP2024.03220RaMP2024.03220COMBO2024.03194COMBO2024.03194