ResearchBenchmarksOffline Reinforcement Learning on Gym-MuJoCo RandomFollow30.9HalfCheetahTD3+BC19.04422.12225.228.278Jan 26, 2026Evaluation ResultsMethodMethodLinksHalfCheetahHopperWalker2DAverage ReturnTD3+BC2026.0130.98.5213.8MoReBRAC2026.0130.919.118.922.97ReBRAC2026.0129.58.118.418.67SAC-RND2026.0127.619.618.721.97MORE2026.0127.112.29.816.37IQL2026.0119.510.111.313.63