# Multi-Agent Reinforcement Learning with Communication-Constrained Priors

arXiv: https://arxiv.org/abs/2512.03528 · HTML: https://mlsanity.com/paper/2512.03528/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Builds on (most cited first, 22 of 22)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [A Review of Cooperative Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1908.03963/) (2019)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [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)
- [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 Optimal Representations with the Decodable Information Bottleneck](https://mlsanity.com/paper/2009.12789/) (2020)
- [Learning Agent Communication under Limited Bandwidth by Message Pruning](https://mlsanity.com/paper/1912.05304/) (2019)
- [Succinct and Robust Multi-Agent Communication With Temporal Message Control](https://mlsanity.com/paper/2010.14391/) (2020)
- [PAC-Bayes Information Bottleneck](https://mlsanity.com/paper/2109.14509/) (2021)
- [PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration](https://mlsanity.com/paper/2203.08553/) (2022)
- [Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1902.06527/) (2019)
- [DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.01619/) (2022)
- [Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control](https://mlsanity.com/paper/2308.02345/) (2023)
- [Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networks](https://mlsanity.com/paper/2309.06021/) (2023)

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

- [Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies](https://mlsanity.com/paper/2602.18291/) (2026)
- [Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2604.08728/) (2026)
- [Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies](https://mlsanity.com/paper/2610.01882/) (2026)

## Abstract (arXiv)

Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a prevalent issue. Existing multi-agent reinforcement learning with communication, due to their limited scalability and robustness, struggles to apply to complex and dynamic real-world environments. To address these challenges, we propose a generalized communication-constrained model to uniformly characterize communication conditions across different scenarios. Based on this, we utilize it as a learning prior to distinguish between lossy and lossless messages for specific scenarios. Additionally, we decouple the impact of lossy and lossless messages on distributed decision-making, drawing on a dual mutual information estimatior, and introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward. Finally, we validate the effectiveness of our approach across several communication-constrained benchmarks.