# Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints

arXiv: https://arxiv.org/abs/2605.21085 · HTML: https://mlsanity.com/paper/2605.21085/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 30 of 30)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Learning Attentional Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/1805.07733/) (2018)
- [Graph Convolutional Reinforcement Learning](https://mlsanity.com/paper/1810.09202/) (2018)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [Learning to Schedule Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1902.01554/) (2019)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning](https://mlsanity.com/paper/2207.03530/) (2022)
- [Learning Efficient Multi-agent Communication: An Information Bottleneck Approach](https://mlsanity.com/paper/1911.06992/) (2019)
- [Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2006.11438/) (2020)
- [ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind](https://mlsanity.com/paper/2111.09189/) (2021)
- [Learning Individually Inferred Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/2006.06455/) (2020)
- [Learning Multi-Agent Communication from Graph Modeling Perspective](https://mlsanity.com/paper/2405.08550/) (2024)
- [Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control](https://mlsanity.com/paper/1909.02682/) (2019)
- [Learning Agent Communication under Limited Bandwidth by Message Pruning](https://mlsanity.com/paper/1912.05304/) (2019)
- [Context-aware Communication for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2312.15600/) (2023)
- [Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth](https://mlsanity.com/paper/2306.10134/) (2023)

## Abstract (arXiv)

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.