It is demonstrated that under specific underloaded conditions, a system initialized without queues will remain queue-free indefinitely, which allows us to transform a complex, infinite-dimensional continuous-time optimal control problem into a tractable, finite-dimensional algebraic optimization.
Nameer Fawwaz Ahmed, Cody H. Fleming, Yasser Shoukry· 0 citations
Frozen vision-language models increasingly provide safety signals for reinforcement learning. Their use assumes that similarity to language describing danger indicates the hazard itself. Yet policy return and collision rate cannot reveal whether a score detects hazards or responds to correlated features of the scene. V...
VLM-Safe-RL is proposed, a framework that integrates frozen CLIP signals into PPO-Lagrangian through reward shaping and an augmented multiplier update, and shows a conditional reduction in observed catastrophe rate without evidence of collision anticipation.
A plant-property lower bound is proved on the minimum jam count required for an immediate hold-last medium-access-control adversary to force a crash against a self-triggered controller (STC) satisfying a Lyapunov contract, and a certificate-level analog of the consecutive-grouping optimality of prior count-budget DoS s...
Adam Haroon, Erick J. Rodríguez-Seda, Tristan K. Schuler et al.· 0 citations
This workCertified 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 bound on the unsafe fraction of the selection, and behavior cloning follows.
This work presents Constitutional Meta-STPA, an LLM-assisted STPA tool built around a closed loop, which takes seriously the question the field has skipped -- who analyses the analyser?
Samuel T. K. Tetteh, Udip Shrestha, J. Waite et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
