ResearchBenchmarksReinforcement Learning on AntMaze large-diverse D4RLFollow493Average Episodic ReturnGC-Oracle113.4211.95310.5409.05Mar 10, 2024Evaluation ResultsMethodMethodLinksAverage Episodic ReturnGC-Oracle2024.03493DiSPO2024.03359COMBO2024.03244GC-IQL2024.03226USFA2024.03215FB2024.03181RaMP2024.03132MOPO2024.03128