ResearchBenchmarksContinuous Control on Ant MuJoCo v5Continuous Control on Ant MuJoCo v5Follow4,653Maximum ReturnSAVGO-173.641,079.432,332.53,585.57May 1, 2026Evaluation resultsMethodMethodLinksMaximum ReturnSAVGOTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.054,653TD3Training steps=1,000,0...Training steps=1,000,000, Seeds=102026.054,366SACTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.054,086TQCTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.053,041PPOTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.0512