In this paper, we consider a multi-armed bandit (MAB) instance and study how to identify the best arm when arm commands are conveyed from a central learner to a distributed agent over a discrete memoryless channel (DMC). Depending on the agent capabilities, we provide communication schemes along with their analysis, which interestingly relate to the zero-error capacity of the underlying DMC.
@article{arxiv.2604.02255,
title = {Best-Arm Identification with Noisy Actuation},
author = {Merve Karakas and Osama Hanna and Lin F. Yang and Christina Fragouli},
journal= {arXiv preprint arXiv:2604.02255},
year = {2026}
}