ResearchBenchmarksOffline Reinforcement Learning on D4RL AntMaze Large-Play v0Follow73.2Avg Normalized ScoreQIPO-Diff-2.92816.83636.656.364Jun 12, 2021Mar 3, 2022Nov 22, 2022Aug 13, 2023May 3, 2024Jan 22, 2025Oct 13, 2025Evaluation ResultsMethodMethodLinksAvg Normalized ScoreQIPO-Diff2025.1073.2QIPO-OT2025.1055.5GTP2025.1053.5TD3+BCEvaluations=final 10,...Evaluations=final 10, Seeds=5, State feature normalization=false2021.060