Review for NeurIPS paper: Neurosymbolic Transformers for Multi-Agent Communication

Weaknesses: - The method relies on each agent having observations of other agents (o {i,j}). This seems like a very strong assumption, given that the motivation for this work was to lower the communication bandwidth necessary. The authors should comment on how this requirement could be weakened to allow scaling to more complex environments. The "loss" in Figure 2 is not clearly defined, and it would be much clearer to use "reward" as the y-axis in these Figures. The overlapping error bars in many of the results call into question the significance of the findings.