# Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning

arXiv: https://arxiv.org/abs/2607.27626 · HTML: https://mlsanity.com/paper/2607.27626/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Constrained Reinforcement Learning Has Zero Duality Gap](https://mlsanity.com/paper/1910.13393/) (2019)
- [Online Convex Optimization with Stochastic Constraints](https://mlsanity.com/paper/1708.03741/) (2017)
- [Age of Information: An Introduction and Survey](https://mlsanity.com/paper/2007.08564/) (2020)
- [Adaptive Algorithms for Online Convex Optimization with Long-term Constraints](https://mlsanity.com/paper/1512.07422/) (2015)
- [An Online Convex Optimization Approach to Dynamic Network Resource Allocation](https://mlsanity.com/paper/1701.03974/) (2017)
- [Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints](https://mlsanity.com/paper/2106.05135/) (2021)
- [Ultra-Reliable and Low-Latency Wireless Communication: Tail, Risk and Scale](https://mlsanity.com/paper/1801.01270/) (2018)
- [Scheduling Policies for Minimizing Age of Information in Broadcast Wireless Networks](https://mlsanity.com/paper/1801.01803/) (2018)
- [Age of Information: Whittle Index for Scheduling Stochastic Arrivals](https://mlsanity.com/paper/1801.03422/) (2018)
- [A Whittle Index Approach to Minimizing Functions of Age of Information](https://mlsanity.com/paper/1908.10438/) (2019)
- [Online Convex Optimization with Perturbed Constraints](https://mlsanity.com/paper/1906.00049/) (2019)
- [On the Role of Age of Information in the Internet of Things](https://mlsanity.com/paper/1812.08286/) (2018)
- [A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQ](https://mlsanity.com/paper/2102.09774/) (2021)
- [Noise-Adaptive High-Probability Regret Bounds for Online Convex Optimization](https://mlsanity.com/paper/2606.08028/) (2026)

## Abstract (arXiv)

Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbreviated PAoI) to stay below a hard per-slot deadline, not merely an average bound. Existing approaches meet this requirement only under restrictive assumptions: stochastic channels for Whittle-index AoI, simulator rollouts for deep reinforcement learning, or sublinear cumulative violation for long-term constrained online convex optimization. Under adversarial coefficients, OCO-PAoI-Hard guarantees zero per-slot violation of the modeled AoI state under one-step viability and O(sqrt(T)) regret against any static safe comparator; packet-level safety requires stronger service assumptions. Our key observation is that the fractional peak-AoI deadline collapses exactly to an affine half-space constraint on the resource-allocation vector, turning hard real-time scheduling into time-varying constrained online convex optimization over a polyhedral safe set. A strictly causal proposal-shield-update loop enforces feasibility through one Euclidean projection per slot, the gradient step preserves no-regret behavior, and the classical virtual queue is reduced to an a-posteriori certificate. We establish closed-form static and dynamic regret bounds, a matching Omega(sqrt(T)) minimax lower bound, a margin-safe variant against execution noise, and a deadline-induced competitive ratio. On a four-sensor adversarial fluid-model trap channel, OCO-PAoI-Hard attains zero modeled-state deadline violations across all ten seeds, while four representative baselines miss between 1.65 percent and 64.0 percent of slots, and the empirical normalized regret stays below the theoretical envelope across two orders of magnitude in T.