ResearchBenchmarksOptimal Control on LQR 4DFollow1.056Evaluation CostSDPI0.98961.43781.8862.3342May 8, 2026Evaluation ResultsMethodMethodLinksEvaluation CostSDPIDynamics Knowledge=knownDynamics Knowledge=known2026.051.056PPO2026.051.057SAC2026.051.115MBPO2026.051.637SDPIDynamics Knowledge=unk...Dynamics Knowledge=unknown2026.052.716