ResearchBenchmarksCartPole Stabilization on CartPole Stabilization T=5000 long-horizon 1.0CartPole Stabilization on CartPole Stabilization T=5000 long-horizon 1.0Follow-0.08Average Stability ScoreA2DEPT-26,711.0656-19,776.4828-12,841.9-5,907.3172Apr 27, 2026Evaluation resultsMethodMethodLinksAverage Stability ScoreA2DEPTHorizon (T)=5000Horizon (T)=50002026.04-0.08LQRHorizon (T)=5000Horizon (T)=50002026.04-0.09Bang-BangHorizon (T)=5000Horizon (T)=50002026.04-4,881.07PIDHorizon (T)=5000Horizon (T)=50002026.04-22,299.76SMCHorizon (T)=5000Horizon (T)=50002026.04-25,683.72