SyncAI.news, a Varaisys broadcasting
Risk-Aware Online Conformal State Probing
PT

Pietro Talli, Petar Popovski, Osvaldo Simeone

· 1 min read

ResearcharXiv cs.AI

Risk-Aware Online Conformal State Probing

arXiv:2609.25889v1 Announce Type: cross Abstract: AI-based autonomous agents, typically hosted at data centers, must acquire state information from robots or edge devices in order to issue informed control decisions. Managing uncertainty about the state is particularly consequential in safety-critical settings, in which average-case guarantees are insufficient. In this context, we study a sequential decision maker process that jointly decides which actions to take and when to probe given access to an arbitrary state prediction model. We propose online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions. OCSP is designed to provably control the missed query error (MQE), i.e., the fraction of instances where probing would have been beneficial, while minimizing the probing rate. OCSP can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning. We validate OCSP through numerical simulations to verify theoretical guarantees and to assess performance trade-offs as a function of the calibration of the state predictor.

Original source

This story was published by arXiv cs.AI and written by Pietro Talli, Petar Popovski, Osvaldo Simeone. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News