arXiv · 2611.20970
Hilbert States for Decision-Making under Partial Observability
Abstract
Decision-making under partial observability can be fundamentally limited by information, even with known dynamics: distinct physical states can induce the same observation history while favoring different actions. We study three questions: when is full-state optimality unattainable, what information exactly preserves the best observation-based decision, and how does finite-data learning affect reliability? First, we characterize decision ambiguity through conditional action preferences. We give a zero-regret criterion, a positive lower bound for conflicting uniquely optimal actions on positive-probability regions with uniformly positive cost gaps, and an exact binary-action regret formula. This also shows why physical-state ambiguity alone need not cause decision loss. Second, for two actions and squared terminal-goal costs in the plane, we derive an exact inner-product representation of conditional expected cost differences using three conditional moment contrasts and a goal-dependent feature. This Hilbert state preserves observation-optimal actions without hidden-state reconstruction. Under nondegenerate history and goal variation, its three-dimensional form is minimal among exact bilinear cost-contrast representations. Third, we relate finite-data state errors to excess decision regret via goal-projected errors, action margins, and goal geometry. Physics-based simulations verify information-limited regret, exact action preservation, and the role of second moments. Held-out real-SAR experiments demonstrate feasible goal-conditioned decisions from masked images, while finite-data evaluations reveal goal-dependent reliability. Together, these results separate irreducible information loss, exact representation sufficiency, and learning-induced excess regret.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Zibo Meng, Andrew C. M. Austin, Alin Achim. 2026-11-16. Hilbert States for Decision-Making under Partial Observability. https://searcharxiv.com/abs/2611.20970
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.