The paper is modelling MARL problems under the angle of social dilemma, and tries to tackle the problem of common-pool resource management. The authors do not introduce a novel method, instead this paper is a comparison of a wide range of existing relevant algorithms on a single problem (water management). The experiments are well motivated and in general, the paper is very clear. My understanding is that although the paper focuses on a water management, it is aimed as a more general survey of the quality of current MARL algorithms on common-pool resource management. The authors argue that water management is a good example to study because it is critical and life-supporting, and safety issues are very relevant. One weakness is that only one problem is studied, although the paper is presented as studying a problem that is more general than water management. The problem is also small scale, although reviewers disagree on whether this is too small to be meaningful. Reviewers also point out that some baselines are missing. Reviewers also pointed out that the paper does not attempt to analyse the results (especially on NeurComm, which seems to be better at finding a stable equilibrium), but the authors have addressed it in their author feedback and have included more analysis to that end. Meta-reviewers suggest that the authors should flesh out their broader impact statement to consider what the implications would be if a deployed MARL algorithm were to fail.