Skip to main content
Search

# Black-box Optimization

1 related articles

Subscribe to updates
  1. arXiv

    JEPA-PS turns optimizer memory into a measurable quantity: full trajectory pays on CartPole, nearly only the best point on rugged ground

    Black-box optimizers are usually asked only whether they beat a baseline, rarely which part of the search history they actually use. JEPA-PS is pretrained with a reward-agnostic objective on random rollouts, learning only to predict the latent representation of the next trajectory point, and at test time reads a short evaluation history and proposes the next candidate in one forward pass. Across 15 control environments and 12 optimizers it does not beat tuned classical search, but ablations show history dependence varies by problem: full history beats best-only by about 22% on CartPole, while on MountainCar the two are nearly identical.

You’re all caught up