Sec. 3.2 a novel contribution [...] 4) l. 139: Is the teacher's reward the same as the reward previously defined for the

Thank you for your in-depth and constructive reviews, they will give us an excellent chance to further improve the paper. We address the reviewers concerns individually below. Minor Concerns: We will address these concerns in the revision. Empirically, then, it makes sense to compare to other mini-batch methods, like IS. 'mean' is the correct one. For O1, you are correct in your understanding.

In our comments we address the reviews in the order of the reviewer number. The reviewer notes that on page 4 line 152, the phrase "no limitation is needed on the receptive field size" would benefit DGCNN than to PointNet as it also uses graph convolutions. The FoldingNet decoder alone has 1.05M parameters. Unfortunately the parameters count of the encoder are not stated, but the code indicates around 0.65M parameters The reviewer points out that some additional ablation study might be beneficial.