ResearchBenchmarksOffline multitask Reinforcement Learning on Hopper hopper-forwardOffline multitask Reinforcement Learning on Hopper hopper-forwardFollow982Average Episodic ReturnCOMBO430.8573.9717860.1Mar 10, 2024Evaluation resultsMethodMethodLinksAverage Episodic ReturnCOMBO2024.03982DiSPO2024.03566MOPO2024.03493USFA2024.03487RaMP2024.03470FB2024.03452