# Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2512.11179 · HTML: https://mlsanity.com/paper/2512.11179/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 26 of 26)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Actor-Attention-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1810.02912/) (2018)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [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)
- [Deep Coordination Graphs](https://mlsanity.com/paper/1910.00091/) (2019)
- [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)
- [Multi-Agent Game Abstraction via Graph Attention Neural Network](https://mlsanity.com/paper/1911.10715/) (2019)
- [Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2006.11438/) (2020)
- [Learning Multi-Agent Communication from Graph Modeling Perspective](https://mlsanity.com/paper/2405.08550/) (2024)
- [Learning Agent Communication under Limited Bandwidth by Message Pruning](https://mlsanity.com/paper/1912.05304/) (2019)
- [Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards](https://mlsanity.com/paper/2405.13459/) (2024)
- [Self-Organized Polynomial-Time Coordination Graphs](https://mlsanity.com/paper/2112.03547/) (2021)
- [Multi-Agent Coordination via Multi-Level Communication](https://mlsanity.com/paper/2209.12713/) (2022)
- [Learning Robust Spectral Dynamics for Temporal Domain Generalization](https://mlsanity.com/paper/2505.12585/) (2025)
- [Drift-aware Collaborative Assistance Mixture of Experts for Heterogeneous Multistream Learning](https://mlsanity.com/paper/2508.01598/) (2025)
- [Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples](https://mlsanity.com/paper/2210.00728/) (2022)
- [Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing](https://mlsanity.com/paper/2402.05027/) (2024)
- [Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes](https://mlsanity.com/paper/2212.02055/) (2022)
- [Resilient Contrastive Pre-training under Non-Stationary Drift](https://mlsanity.com/paper/2502.07620/) (2025)

## Built on by (most cited first, 3 of 3)

- [VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation](https://mlsanity.com/paper/2602.07399/) (2026)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication](https://mlsanity.com/paper/2604.25972/) (2026)
- [Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.17393/) (2026)

## Abstract (arXiv)

Graph-based multi-agent reinforcement learning (MARL) enables coordinated behavior under partial observability by modeling agents as nodes and communication links as edges. While recent methods excel at learning sparse coordination graphs-determining who communicates with whom-they do not address what information should be transmitted under hard bandwidth constraints. We study this bandwidth-limited regime and show that naive dimensionality reduction consistently degrades coordination performance. Hard bandwidth constraints force selective encoding, but deterministic projections lack mechanisms to control how compression occurs. We introduce Bandwidth-constrained Variational Message Encoding (BVME), a lightweight module that treats messages as samples from learned Gaussian posteriors regularized via KL divergence to an uninformative prior. BVME's variational framework provides principled, tunable control over compression strength through interpretable hyperparameters, directly constraining the representations used for decision-making. Across SMACv1, SMACv2, and MPE benchmarks, BVME achieves comparable or superior performance while using 67--83% fewer message dimensions, with gains most pronounced on sparse graphs where message quality critically impacts coordination. Ablations reveal U-shaped sensitivity to bandwidth, with BVME excelling at extreme ratios while adding minimal overhead.