ResearchBenchmarksContinuous Control on InvertedPendulum v2Follow1,000Average ReturnIRA963.6973.05982.5991.95Jan 27, 2026Evaluation ResultsMethodMethodLinksAverage ReturnIRA2026.011,000TD32026.01987PEER2026.01983DDPG2026.01982ALH2026.01980PPO2026.01977MBPO2026.01965