ResearchBenchmarksLocomotion on HalfCheetah v3Follow11,385.6Average ReturnQVPO3,588.3045,612.6027,636.99,661.198May 25, 2024Evaluation ResultsMethodMethodLinksAverage ReturnQVPOtraining iterations=1e6training iterations=1e62024.0511,385.6SACtraining iterations=1e6training iterations=1e62024.0510,616.9TD3training iterations=1e6training iterations=1e62024.0510,388.6DIPOtraining iterations=1e6training iterations=1e62024.059,590.5PPOtraining iterations=1e6training iterations=1e62024.054,773.5SPOtraining iterations=1e6training iterations=1e62024.054,008.2QSMtraining iterations=1e6training iterations=1e62024.053,888.2