Interval POMDP Shielding for Imperfect-Perception Agents

The paper introduces Interval POMDP Shielding for agents with imperfect perception, aiming to prevent unsafe actions when sensor readings may be misclassified. By estimating perception uncertainty from finite labeled data, the authors construct confidence intervals and model the system as a finite Interval Partially Observable Markov Decision Process. They propose an algorithm that computes a conservative belief set, enabling a runtime shield that guarantees, with high probability, that any action allowed by the shield meets a specified safety lower bound. Experiments on four case studies demonstrate that this shielding approach outperforms state‑of‑the‑art baselines in safety.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• reinforcement-learning
• benchmarks
• safety