ResearchBenchmarksSensory-motor control on Acrobot GymnasiumFollow-77.3Mean Best Rewardgpt-oss-109.4776-101.1238-92.77-84.4162Jun 5, 2025Evaluation ResultsMethodMethodLinksMean Best RewardMean Initial RewardMean Improvement Ratiogpt-ossOptimal Temperature=0....Optimal Temperature=0.8, Mean Learning Time=0.032025.06-77.3-50099qwen2.5Optimal Temperature=1....Optimal Temperature=1.6, Mean Learning Time=0.042025.06-108.24-50092