ResearchBenchmarksAcrobot Control on AcrobotFollow100Success RatePPO–MPPI-4235077Dec 18, 2025Evaluation ResultsMethodMethodLinksSuccess RateEpisode Length (Steps)Cumulative RewardMin Episode StepsPPO–MPPIInfluence ratio (ρ)=0Influence ratio (ρ)=02025.1210082.6-92.6—PPO–MPPIInfluence ratio (ρ)=0.3Influence ratio (ρ)=0.32025.1210090.7-103.1—PPO2025.1240332.6-347.1—SAC2025.120500-500—MoH2025.05———88.76ReEvo2025.05———99.65