ResearchBenchmarksContinuous Control on Reacher MuJoCo v5Continuous Control on Reacher MuJoCo v5Follow3Max Evaluation ReturnPPO1.962.232.52.77May 1, 2026Evaluation resultsMethodMethodLinksMax Evaluation ReturnPPOTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.053TD3Training steps=1,000,0...Training steps=1,000,000, Seeds=102026.053SAVGOTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.053SACTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.052TQCTraining steps=1,000,0...Training steps=1,000,000, Seeds=102026.052