ResearchBenchmarksExpected Runtime Optimization on OneMax n=100 (test)Follow5.313ERTpi_opt5.258725.625115.99156.35789Dec 3, 2025Evaluation ResultsMethodMethodLinksERTpi_optPolicy Type=OptimalPolicy Type=Optimal2025.125.313pi_contPolicy Type=theory-der...Policy Type=theory-derived2025.125.826DDQNReward=ScaledReward=Scaled2025.125.836pi_discPolicy Type=theory-der...Policy Type=theory-derived2025.125.934PPOReward=ScaledReward=Scaled2025.126.401DDQNReward=NaïveReward=Naïve2025.126.437PPOReward=NaïveReward=Naïve2025.126.67