We thank the reviewers (R1, R2, R3, R4, and R5) for their thoughtful reviews, and respond to as much as we can given

Their Theorem 2.2 gives a Given true expected regret, Lemma 2.1 allows one It is precisely this quantity which vanilla RegretNet can only approximate but which we can compute. Due to RegretNet's sensitivity to hyperparameters, we believe that reproducing optimal These changes might explain the performance differences. We agree with this and will add such discussion. As such, much of the comparison in Duetting et al. to previous work applies to our technique as well. We will add discussion briefly in 1 and as a new subsection in 2. We will explicitly clarify this assumption as well.