Autoregressive Bandits

arXiv:2212.06251v2 Announce Type: replace
Abstract: Autoregressive processes naturally arise in a large variety of real-world scenarios, including stock markets, sales forecasting, weather prediction, advertising, and pricing. When facing a sequential decision-making problem in such a context, the temporal dependence between consecutive observations should be properly accounted for guaranteeing convergence to the optimal policy. In this work, we propose a novel online learning setting, namely, Autoregressive Bandits (ARBs), in which the observed reward is governed by an autoregressive process of order …

abstract advertising arxiv context convergence cs.lg decision forecasting making markets policy prediction pricing processes sales stat.ml stock stock markets temporal type weather weather prediction work world