7967cc8e3ab559e68cc944c44b1cf3e8-AuthorFeedback.pdf

We thank the reviewers for their thoughtful feedback and suggestions. We are encouraged to read that they found1 our work clearly written (R1, R2, R3, R4) and they appreciated the simplicity (R2, R4), generality (R1) as well as2 convincingperformance(R1,R2,R4)ofourmethod.3 Intuitively,thismeansthatrewards7 are in a sense symmetrical between agents, in that actions that work for one agent also work for another agent if8 theyswapped positions. Hence, SEAC could also be applied in some competitivetasks. However, our36 experiments indicate that the IS weights stay in a desirable range (Fig 5: [IS weights centered around 1.0+-0.5])37