ResearchBenchmarksLocomotion on Humanoid v3Follow5,353.5Average ReturnTD3528.1081,780.8543,033.64,286.346May 25, 2024Evaluation ResultsMethodMethodLinksAverage ReturnTD3training iterations=1e6training iterations=1e62024.055,353.5QVPOtraining iterations=1e6training iterations=1e62024.055,306.6SACtraining iterations=1e6training iterations=1e62024.055,159.7DIPOtraining iterations=1e6training iterations=1e62024.054,945.5QSMtraining iterations=1e6training iterations=1e62024.054,793.1SPOtraining iterations=1e6training iterations=1e62024.05797.4PPOtraining iterations=1e6training iterations=1e62024.05713.7