ResearchBenchmarksContinuous Control on InvertedDouble v2Follow9,359Average ReturnMBPO6,990.927,605.718,220.58,835.29Jan 27, 2026Evaluation ResultsMethodMethodLinksAverage ReturnMBPO2026.019,359IRA2026.019,203DDPG2026.018,749PPO2026.018,506ALH2026.018,320PEER2026.018,319TD32026.017,082