ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym-MuJoCo hopper-randomFollow31.2Normalized ScoreDOSER2.80810.17917.5524.921May 6, 2026Evaluation ResultsMethodMethodLinksNormalized ScoreDOSER2026.0531.2DMG2026.0520.4AWAC2026.059.2TD3+BC2026.058.5CQL2026.057.9IQL2026.057.9BCQ2026.057.8OneStep2026.055.6DT2026.055.4BC2026.054.1BEAR2026.053.9