| title | Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints |
|---|---|
| authors | Alexi Canesse, Benoît Goupil, Jesse Read, Sonia Vanier |
| date | 2026-05-20 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.21085 |
| affiliation | Orailix |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Communication enables coordination in multi-agent reinforcement learning (MARL), but many real-world applications, e.g., search-and-rescue with drone swarms, operate under severe bandwidth constraints. Many communication architectures still expose a coupled bottleneck in which a shared latent representation is used for both policy execution and inter-agent communication. Consequently, reducing message size directly limits the policy's latent space, often leading to significant performance degradation. We address this with two contributions. First, we introduce β, a normalised per-agent bandwidth budget that unifies sparsity, rounds, and message dimension into a single comparable constraint. Second, we provide SLIM, a minimal architecture that decouples the communication pathway from the policy's latent representation, allowing us to isolate the effect of bandwidth from the effect of policy capacity while benefiting from in-step communication. We evaluate our method on several partially-observable MARL benchmarks, where communication is essential. Our approach achieves state-of-the-art performance and exhibits scalability and robustness under limited communication, with only marginal degradation as bandwidth is reduced. |
cite
@misc{canesse2026decoupling,
title={Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints},
author={Alexi Canesse and Benoît Goupil and Jesse Read and Sonia Vanier},
year={2026},
eprint={2605.21085},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.21085}
}