ResearchBenchmarksLocomotion on Hopper v3Follow3,728.5Average ReturnQVPO2,091.7482,516.6742,941.63,366.526May 25, 2024Evaluation ResultsMethodMethodLinksAverage ReturnQVPOtraining iterations=1e6training iterations=1e62024.053,728.5DIPOtraining iterations=1e6training iterations=1e62024.053,295.4TD3training iterations=1e6training iterations=1e62024.053,267.5PPOtraining iterations=1e6training iterations=1e62024.053,154.3SACtraining iterations=1e6training iterations=1e62024.052,996.6SPOtraining iterations=1e6training iterations=1e62024.052,212.8QSMtraining iterations=1e6training iterations=1e62024.052,154.7