ResearchBenchmarksLocomotion on Ant v3Follow6,425.1Average ReturnQVPO1,927.2043,094.9274,262.655,430.373May 25, 2024Evaluation ResultsMethodMethodLinksAverage ReturnQVPOtraining iterations=1e6training iterations=1e62024.056,425.1DIPOtraining iterations=1e6training iterations=1e62024.055,665.9SACtraining iterations=1e6training iterations=1e62024.055,030.9TD3training iterations=1e6training iterations=1e62024.054,583.8PPOtraining iterations=1e6training iterations=1e62024.052,781.9SPOtraining iterations=1e6training iterations=1e62024.052,100.2