ResearchBenchmarksOffline multitask Reinforcement Learning on D4RL Antmaze large-diverseFollow359Avg Episodic ReturnDiSPO118.76181.13243.5305.87Mar 10, 2024Evaluation ResultsMethodMethodLinksAvg Episodic ReturnDiSPO2024.03359COMBO2024.03244GC-IQL2024.03226USFA2024.03215FB2024.03181RaMP2024.03132MOPO2024.03128