ResearchBenchmarksContinuous Control on Hopper v4Follow3,515.3Maximum Average ReturnSD32,151.55842,505.60672,859.6553,213.7033May 6, 2025Evaluation ResultsMethodMethodLinksMaximum Average ReturnSD32025.053,515.3CSAC2025.053,458.22TD32025.053,296.8SAC2025.053,037.19PPO2025.052,204.01