SOURCE-LINKED INTELLIGENCE

Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Safe offline reinforcement learning assumes a cost function on every transition. We ask what remains possible when safety can be judged only by comparing short clips and occasionally asking whether an episode exceeded its budget. Certified safety curation answers with a filter-then-clone pipeline: a state-only value trained from segment comparisons scores whole trajectories, Learn-then-Test calibration certifies a selection threshold under a distribution-free $(α, δ)$ bound on the unsafe fraction of the selection, and behavior cloning follows. We are not aware of prior work certifying the comp

Read original source ↗ Open in workspace

recordType

paper

region

Global