ResearchBenchmarksSensory-motor Control on Inverted Pendulum MuJoCoFollow829.66Mean Best Rewardqwen2.5734.9368759.5284784.12808.7116Jun 5, 2025Evaluation ResultsMethodMethodLinksMean Best RewardMean Initial RewardMean Improvement Ratioqwen2.5Optimal Temperature=1....Optimal Temperature=1.6, Mean Learning Time=0.192025.06829.665.0583gpt-ossOptimal Temperature=0....Optimal Temperature=0.0, Mean Learning Time=0.312025.06738.5812.4573