ResearchBenchmarksExpected Runtime Optimization on OneMax n=50 (test)Follow4.928ERTpi_opt4.903765.067385.2315.39462Dec 3, 2025Evaluation ResultsMethodMethodLinksERTpi_optPolicy Type=OptimalPolicy Type=Optimal2025.124.928DDQNReward=ScaledReward=Scaled2025.125.105DDQNReward=NaïveReward=Naïve2025.125.428pi_contPolicy Type=theory-der...Policy Type=theory-derived2025.125.448pi_discPolicy Type=theory-der...Policy Type=theory-derived2025.125.48PPOReward=ScaledReward=Scaled2025.125.526PPOReward=NaïveReward=Naïve2025.125.534