ResearchBenchmarksSensory-motor control on Pendulum GymnasiumFollow-190.31Mean Best Rewardgpt-oss-940.67-745.865-551.06-356.255Jun 5, 2025Evaluation ResultsMethodMethodLinksMean Best RewardMean Initial RewardMean Improvement Ratiogpt-ossOptimal Temperature=0....Optimal Temperature=0.8, Mean Learning Time=0.182025.06-190.31-1,725.440.96qwen2.5Optimal Temperature=0....Optimal Temperature=0.0, Mean Learning Time=0.132025.06-911.81-1,334.760.35