ResearchBenchmarksSensory-motor control on MountainCar Discrete GymnasiumFollow-111.54Mean Best Rewardgpt-oss-168.428-153.659-138.89-124.121Jun 5, 2025Evaluation ResultsMethodMethodLinksMean Best RewardMean Initial RewardMean Improvement Ratiogpt-ossOptimal Temperature=0....Optimal Temperature=0.8, Mean Learning Time=0.162025.06-111.54-20087qwen2.5Optimal Temperature=1....Optimal Temperature=1.6, Mean Learning Time=0.072025.06-166.24-20033