ResearchBenchmarksCart-Double Pendulum Stabilization ControlFollow0Position Violation Rate (Last 100 steps)PPO-EAL-0.01920.11040.240.3696Jun 26, 2026Evaluation ResultsMethodMethodLinksPosition Violation Rate (Last 100 steps)Position Violation Rate (End Value)Velocity Violation Rate (Last 100 steps)Velocity Violation Rate (End Value)Reward (Last 100 steps)Reward (End Value)Success RatePPO-EAL2026.06000.950.95576.3574.92—PPO-EAL-m2026.060.0570.0550.830.84577.28577.65—PPO-L2026.060.240.251.11575.26575.18—P3O2026.060.350.311563.38563.06—PPO2026.060.410.391.71.7577.26576.99—PPO-AL2026.060.480.460.920.93565.77565.81—