ResearchBenchmarksReinforcement Learning on AntMaze medium-diverse D4RLFollow659Avg Episodic ReturnGC-Oracle219.08333.29447.5561.71Mar 10, 2024Evaluation ResultsMethodMethodLinksAvg Episodic ReturnGC-Oracle2024.03659DiSPO2024.03631COMBO2024.03418GC-IQL2024.03403USFA2024.03394FB2024.03294RaMP2024.03266MOPO2024.03236