NeurIPS 2020

Making Non-Stochastic Control (Almost) as Easy as Stochastic

Meta Review

The reviewers liked the technical aspect of the paper. Perhaps the main concern is about the presentation style and the target audience, which at the moment is a relatively small crowd that are interested in both online learning and control. The reviewers made a number of useful suggestions for improving this aspect and the rebuttal also outlines a plan that seems reasonable to me. Please do make a serious effort to revise the paper for the final version. Otherwise, nice work!