ResearchBenchmarksContinuous Control on Humanoid v4Follow4,978.5Average Cumulative RewardMA-MPPI197.5161,438.7332,679.953,921.167Sep 24, 2025Evaluation ResultsMethodMethodLinksAverage Cumulative RewardMA-MPPI2025.094,978.5MPPI2025.092,914.2MPC2025.092,784.1iLQR2025.091,927.5SAC2025.09936.7PPO2025.09612.3DDPG2025.09381.4