ResearchBenchmarksExpected Runtime Optimization on OneMax n=300 (test)Follow5.75Expected Runtime (ERT)pi_opt5.63546.408957.18257.95605Dec 3, 2025Evaluation ResultsMethodMethodLinksExpected Runtime (ERT)pi_optPolicy Type=OptimalPolicy Type=Optimal2025.125.75DDQNReward=ScaledReward=Scaled2025.126.165pi_contPolicy Type=theory-der...Policy Type=theory-derived2025.126.278pi_discPolicy Type=theory-der...Policy Type=theory-derived2025.126.298PPOReward=ScaledReward=Scaled2025.128.041PPOReward=NaïveReward=Naïve2025.128.531DDQNReward=NaïveReward=Naïve2025.128.615