ResearchBenchmarksDynamic Algorithm Configuration on OneMax n=2,000Follow5.162Normalized ERTDDQN5.036725.882366.7287.57364Jun 8, 2026Evaluation ResultsMethodMethodLinksNormalized ERTDDQNParameter=Multi/Fact,...Parameter=Multi/Fact, Reward=AS2026.065.162IRACE2026.065.666DDQNParameter=Single, Rewa...Parameter=Single, Reward=AS2026.066.608pi_THEORY2026.066.681ONE-FIFTH2026.067.008PPOParameter=Multi/Fact,...Parameter=Multi/Fact, Reward=FS2026.068.267PPOParameter=Multi/Fact,...Parameter=Multi/Fact, Reward=Naïve2026.068.294