Flickering Multi-Armed Bandits
Abstract
We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the agent's current choice. We formalize these constraints through stochastically evolving graphs where actions are limited to local neighborhoods. This mobility-constrained structure imposes a dual challenge: the statistical requirement of information acquisition and the physical overhead of navigation. We analyze FMAB under i.i.d. Erd\H{o}s--R'enyi and Edge-Markovian process, proposing a two-phase lazy random walk algorithm for robust exploration. We establish high-probability sublinear regret bounds and prove near-optimality via a matching information-theoretic lower bound. Our results characterize the intrinsic cost of learning under local-move constraints, complemented by a robotic disaster-response simulation.
Cite
@article{arxiv.2602.17315,
title = {Flickering Multi-Armed Bandits},
author = {Sourav Chakraborty and Amit Kiran Rege and Claire Monteleoni and Lijun Chen},
journal= {arXiv preprint arXiv:2602.17315},
year = {2026}
}