Recent studies have shown that introducing communication between agents can significantly improve overall performance in cooperative Multi-agent reinforcement learning (MARL). However, existing communication schemes often require agents to exchange an excessive number of messages at run-time under a reliable communication channel, which hinders its practicality in many real-world situations.

Weaknesses: I do not understand the purpose of halting training process. Without the convergence, how to assess the real benefit of the proposed method. The two regularizers serve mainly for communication reduction, and it is not directly correlated with the objective of RL. So, why does TMC QMIX perform AC, as both use full communication in training). This is not clear, and even counter-intuitive.

All of the reviewers had some positive points to mention in line 2 (Strengths) such as "this is an important topic" and "I like the idea," while R3 argued against the setting. R3 also critiqued the use of heuristics that were not well justified. Correctness was favorable for R1, while R3 said the experiments did not fully support the claims. Clarity and Prior Art coverage were generally good. Reproducibility was also generally thought to be good, except for R1.

Recent studies have shown that introducing communication between agents can significantly improve overall performance in cooperative Multi-agent reinforcement learning (MARL). However, existing communication schemes often require agents to exchange an excessive number of messages at run-time under a reliable communication channel, which hinders its practicality in many real-world situations. TMC applies a temporal smoothing technique to drastically reduce the amount of information exchanged between agents. Experiments show that TMC can significantly reduce inter-agent communication overhead without impacting accuracy. Furthermore, TMC demonstrates much better robustness against transmission loss than existing approaches in lossy networking environments.