Optimistic Online Non-stochastic Control via FTRL

arXiv:2404.03309v1 Announce Type: new
Abstract: This paper brings the concept of "optimism" to the new and promising framework of online Non-stochastic Control (NSC). Namely, we study how can NSC benefit from a prediction oracle of unknown quality responsible for forecasting future costs. The posed problem is first reduced to an optimistic learning with delayed feedback problem, which is handled through the Optimistic Follow the Regularized Leader (OFTRL) algorithmic family. This reduction enables the design of OptFTRL-C, the first Disturbance Action …

abstract arxiv benefit concept control costs cs.lg forecasting framework future math.oc optimism oracle paper prediction quality responsible stochastic study type via