This paper proposes multi-agent hierarchical RL method to the target coverage problems in directional sensor networks. Empirical results are provided to show the advantage of their method against state of the art MARL algorithms as well as optimization techniques specific to the target coverage problem. There are some concerns among the reviewers regarding whether RL is the right tool for the problem, insufficient comparison with non-learning heuristics, and the value of the work to the RL community. I share the first reviewer’s positive sentiment on the application of RL to sensor networks. It is nice to see RL moving from games to real-world applications. I also agree with the first reviewer that the proposed method do have promise in comparison with non-learning heuristics and the same approach could be applied to other MA problems.