To Reviewer # 1 in [16], while we think the considered problem and the definitions of the individual intrinsic reward and proxy value are

We thank the reviewers for all of these valuable comments. We provide point by point responses below. Q2: "Another paper...'Optimal rewards for cooperative agents'..." A: We have carefully read the paper and we We will provide more discussions in the revision. Q3: "...why the authors did not choose all the tasks used in the COMA paper..." A: We think 8M, 2S3Z and 3S5Z Actually, all these settings are based on the SMAC framework. Q4: "...deeper analyses of the learned intrinsic reward..." A: Thanks for the comments.