ResearchBenchmarksLocomotion on Walker2d v4Follow5,472.8Mean ReturnSOM1,157.322,277.6853,398.054,518.415May 22, 2026Evaluation ResultsMethodMethodLinksMean Return95% CI (Return)SOM2026.055,472.8526.9DIPO2026.055,425.8181.3SAC2026.055,348.6712.9DPMD2026.054,953.8707.1DACER2026.054,723.62,276.1SDAC2026.054,702.1627.4QSM2026.054,144.9575.3PPO2026.053,096.3540.3MFP2026.051,849.81,356.2QVPO2026.051,323.31,609.7