ResearchBenchmarksOffline Reinforcement Learning on D4RL AntMaze Large-Diverse (AM-LD)Offline Reinforcement Learning on D4RL AntMaze Large-Diverse (AM-LD)Follow71Normalized ScoreSPAR30.54441.04751.5562.053Oct 13, 2025Nov 19, 2025Dec 27, 2025Feb 3, 2026Mar 12, 2026Apr 19, 2026May 27, 2026Evaluation resultsMethodMethodLinksNormalized ScoreSPAR2026.0571GTP2025.1071DAC2026.0560QIPO-Diff2025.1040.5FQL2026.0540QIPO2026.0540QIPO-OT2025.1032.1