Risk-Aware Online Conformal State Probing
This work proposes online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions, and can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning.
Pietro Talli, P. Popovski, Osvaldo Simeone
· 0 citations