ResearchBenchmarksExpected Runtime Optimization on OneMax n=200 (test)Follow5.609ERTpi_opt5.521126.114316.70757.30069Dec 3, 2025Evaluation ResultsMethodMethodLinksERTpi_optPolicy Type=OptimalPolicy Type=Optimal2025.125.609pi_contPolicy Type=theory-der...Policy Type=theory-derived2025.126.167pi_discPolicy Type=theory-der...Policy Type=theory-derived2025.126.244DDQNReward=ScaledReward=Scaled2025.126.822DDQNReward=NaïveReward=Naïve2025.127.045PPOReward=ScaledReward=Scaled2025.127.406PPOReward=NaïveReward=Naïve2025.127.806