ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym-MuJoCo walker2d-randomFollow12.8Normalized ScoreBEAR-0.3043.0986.59.902May 6, 2026Evaluation ResultsMethodMethodLinksNormalized ScoreBEAR2026.0512.8OneStep2026.056.9IQL2026.055.4CQL2026.055.1BCQ2026.054.9DMG2026.054.8DOSER2026.053.5DT2026.052.2TD3+BC2026.051.6BC2026.051.2AWAC2026.050.2