ResearchBenchmarksOffline Reinforcement Learning on AntMaze umaze-diverse (Normalized Average Return)Offline Reinforcement Learning on AntMaze umaze-diverse (Normalized Average Return)Follow84Normalized Average ReturnCQL-3.3619.324264.68Apr 16, 2025Jun 22, 2025Aug 29, 2025Nov 5, 2025Jan 11, 2026Mar 20, 2026May 27, 2026Evaluation resultsMethodMethodLinksNormalized Average ReturnCQL2026.0584QT2026.0583.7DC2026.0578.5VIPO-LEQ2025.0474.8Q-ALIGN DT2026.0573.2IQL-TD-MPC2025.0472.6QCS2026.0572.3TD3+BC2026.0571.4LEQ2025.0471CGDT2026.0571RVS2026.0570.1IQL2026.0562.2DT2026.0551.2MOBILE2025.040