ResearchBenchmarksOptimal Control on LQR 32DFollow17.72Evaluation CostSDPI16.5759624.2982332.020539.74277May 8, 2026Evaluation ResultsMethodMethodLinksEvaluation CostSDPIDynamics Knowledge=unk...Dynamics Knowledge=unknown2026.0517.72SDPIDynamics Knowledge=knownDynamics Knowledge=known2026.0518.146PPO2026.0526.1SAC2026.0533.3MBPO2026.0546.321