ResearchBenchmarksLocomotion on Humanoid v4Follow7,365.7Mean Episode ReturnSOM16.541,924.4953,832.455,740.405May 22, 2026Evaluation ResultsMethodMethodLinksMean Episode Return95% CISOM2026.057,365.7493.3DIPO2026.056,139.4645.9SDAC2026.055,803.5520.6SAC2026.055,179.5335DPMD2026.054,968.41,991.1MFP2026.054,862.2603.1DACER2026.053,915.53,006.2QSM2026.052,082.9842.4QVPO2026.051,127.1937.4PPO2026.05299.2119