ResearchBenchmarksContinuous Control on Swimmer MuJoCo v5Continuous Control on Swimmer MuJoCo v5Follow114Max ReturnPPO75.5285.5195.5105.49May 1, 2026Evaluation resultsMethodMethodLinksMax ReturnPPOTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.05114TQCTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.05106TD3Training steps=1,000,0...Training steps=1,000,000, Seeds=102026.05102SAVGOTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.0588SACTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.0577