ResearchBenchmarksLocomotion on Ant v4Follow7,033.5Mean Episode ReturnSOM166.1721,949.0363,731.95,514.764May 22, 2026Evaluation ResultsMethodMethodLinksMean Episode Return95% CI (Return)SOM2026.057,033.5304.2DACER2026.056,953.51,029.7DPMD2026.055,714.1887.8SAC2026.055,711.6530.4PPO2026.055,417.2283.6MFP2026.055,150.7785.6DIPO2026.053,112640.7SDAC2026.053,067926.6QSM2026.051,671377.9QVPO2026.05430.32,277.9