- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes HiComm, a hierarchical communication framework for cooperative MARL. It introduces the HI-MDP formulation and a two-stage protocol in which each agent queries one teammate for information about a single entity, reducing communication overhead.
Experiments on CC4, SMACv2, and GRF show that HiComm outperforms communication baselines in 9 of 10 configurations while consistently reducing communication costs. Ablations validate key design choices, and theoretical analysis establishes communication complexity advantages and learning guarantees under an idealized setting, rather than the actual PPO implementation.
Critical strengths
-
The use of a shared group–entity index for targeted communication is a reasonable design choice. It enables agents to retrieve specific observations rather than exchanging generic learned messages.
-
The ablation on the number of senders provides some evidence for the single-sender design. In CC4, increasing the number of senders substantially raises communication costs without consistently improving rewards.
Critical weaknesses
-
The communication comparisons in Table 2 do not use matched bandwidth budgets. Since HiComm restricts each receiver to one sender and one entity, it is unclear whether the improvements come from hierarchical selection or simply reduced communication.
-
In SMACv2 and GRF, sender-relative positions and distances are directly inserted into the receiver's observation without coordinate transformation, potentially introducing inconsistent spatial information.
-
The auxiliary loss in Eq. (B.4) favors positive feature values. As acknowledged in Appendix B.1, this systematically biases entity selection against negative coordinates in SMACv2 and GRF.
-
Tables 3–5 evaluate key design choices only on CC4. Moreover, the experiments use just three random seeds, and several performance improvements fall within the reported standard deviations.
-
Theorem 6.1 analyzes an idealized primal-dual algorithm rather than the implemented PPO learner. The communication constraints are trivially satisfied, and the optimal-return gap remains unbounded, limiting the practical significance of the guarantees.
Questions for authors
-
In Table 2, can the authors report the rewards of CACOM and T2MAC when their communication costs are constrained to match HiComm's measured KiB per receiver per episode?
-
In SMACv2 and GRF, sender-relative coordinates are copied into the receiver's observation without transformation. How does the policy distinguish these values from observations expressed in the receiver's coordinate frame?
-
In Eq. (B.4), negative feature values contribute zero to the auxiliary targets. How do the results on SMACv2 and GRF change when using the unbiased mask-count alternative mentioned in Appendix B.1?
-
Tables 3–5 only report ablations on CC4. Does hierarchical group–entity selection outperform joint selection on SMACv2 and GRF? Can the authors provide variance estimates and statistical significance tests for the improvements in Table 2?
-
Theorem 6.1 applies to a primal-dual learner rather than PPO, and its communication constraints are trivially satisfied. What specific guarantee does this theorem provide for the implemented HiComm? Can the authors establish a non-trivial bound on the optimal-return gap Δ?