ResearchBenchmarksLocomotion on HalfCheetah v4Follow15,789.8Mean Episode ReturnSOM5,033.2887,825.84410,618.413,410.956May 22, 2026Evaluation ResultsMethodMethodLinksMean Episode Return95% CI (Return)SOM2026.0515,789.8910.9SDAC2026.0514,820.91,049DACER2026.0514,445.8281.5DPMD2026.0514,020.6946.3QSM2026.0513,922.11,032.4DIPO2026.0511,762.11,912.9SAC2026.0511,098.71,697.4PPO2026.057,112.6576.7MFP2026.056,400.3966.5QVPO2026.055,4474,585.8