Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints

• URL: http://arxiv.org/abs/2605.21085v1
• Date: Wed, 20 May 2026 12:21:08 GMT
• Title: Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
• Abstract summary: Many real-world applications, such as search-and-rescue with drone swarms, operate under severe bandwidth constraints.<n>We introduce $$, a normalised per-agent bandwidth budget that unifies sparsity, rounds, and message dimension into a single comparable constraint.<n>Second, we provide SLIM, a minimal architecture that decouples the communication pathway from the policy's latent representation.<n>Our approach achieves state-of-the-art performance and exhibits robustness under limited communication, with only marginal degradation as bandwidth is reduced.
• Score: 1.909020214605419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Reason-to-Transmit: Deliberative Adaptive Communication for Cooperative Perception [0.0]
  Reason-to-Transmit (R2T) is a framework that equips each agent with a lightweight transformer-based module.<n>R2T is evaluated against nine baselines in a multi-agent bird's-eye-view perception environment.
  arXiv  Detail & Related papers  (2026-03-19T15:54:26Z)
• Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization [2.5782420501870296]
  We present a framework that combines information bottleneck theory with vector quantization to enable selective, bandwidth-efficient communication in multi-agent environments.<n>Our approach learns to compress and discretize communication messages while preserving task-critical information through principled information-theoretic optimization.
  arXiv  Detail & Related papers  (2026-02-02T12:32:28Z)
• CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge [50.42067935605982]
  We propose a novel Compression and Combination-based Federated learning framework that unifies local memory efficiency and global communication reduction.<n>CoCo-Fed significantly outperforms state-of-the-art baselines in both memory and communication efficiency while maintaining robust convergence under non-IID settings.
  arXiv  Detail & Related papers  (2026-01-02T03:39:50Z)
• Large Speech Model Enabled Semantic Communication [58.027223937172955]
  Large Speech Model enabled Semantic Communication (LargeSC) system.<n>We exploit the rich semantic knowledge embedded in large models and enable adaptive transmission over lossy channels.<n>System supports bandwidths ranging from 550 bps to 2.06 kbps, outperforms conventional baselines in speech quality under high packet loss rates.
  arXiv  Detail & Related papers  (2025-12-04T11:58:08Z)
• Robust and Efficient Communication in Multi-Agent Reinforcement Learning [18.405707681765453]
  Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents.<n>Most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments.<n>This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints.
  arXiv  Detail & Related papers  (2025-11-14T15:23:11Z)
• Task-Oriented Multimodal Token Transmission in Resource-Constrained Multiuser Networks [19.42660454288912]
  We propose a task-oriented multimodal token transmission scheme for efficient multimodal information fusion and utilization.<n>To improve the efficiency of token transmission, we design a two-stage training algotithm, including cross-modal alignment and task-oriented fine-tuning.<n>We jointly optimize bandwidth, power allocation, and token length across users by using an alternating optimization method.
  arXiv  Detail & Related papers  (2025-05-06T14:17:05Z)
• Learning Resilient Radio Resource Management Policies with Graph Neural Networks [124.89036526192268]
  We formulate a resilient radio resource management problem with per-user minimum-capacity constraints. We show that we can parameterize the user selection and power control policies using a finite set of parameters. Thanks to such adaptation, our proposed method achieves a superior tradeoff between the average rate and the 5th percentile rate.
  arXiv  Detail & Related papers  (2022-03-07T19:40:39Z)
• Multi-agent Communication with Graph Information Bottleneck under Limited Bandwidth (a position paper) [92.11330289225981]
  In many real-world scenarios, communication can be expensive and the bandwidth of the multi-agent system is subject to certain constraints. Redundant messages who occupy the communication resources can block the transmission of informative messages and thus jeopardize the performance. We propose a novel multi-agent communication module, CommGIB, which effectively compresses the structure information and node information in the communication graph to deal with bandwidth-constrained settings.
  arXiv  Detail & Related papers  (2021-12-20T07:53:44Z)
• Distributed Adaptive Learning Under Communication Constraints [54.22472738551687]
  This work examines adaptive distributed learning strategies designed to operate under communication constraints. We consider a network of agents that must solve an online optimization problem from continual observation of streaming data.
  arXiv  Detail & Related papers  (2021-12-03T19:23:48Z)
• Communication-Efficient Split Learning Based on Analog Communication and Over the Air Aggregation [48.150466900765316]
  Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power. Standard SL algorithms assume an ideal underlying digital communication system and ignore the problem of scarce communication bandwidth. We propose a novel SL framework to solve the remote inference problem that introduces an additional layer at the agent side and constrains the choices of the weights and the biases to ensure over the air aggregation.
  arXiv  Detail & Related papers  (2021-06-02T07:49:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.