Multi-Agent Reinforcement Learning with Communication-Constrained Priors
Not on the map. Why?
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 3 Dec 2025.
Builds on
22 of 33 references.
References · 22
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
- 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
- 2015Deep Learning and the Information Bottleneck Principlecited by 793
- 2018MINE: Mutual Information Neural Estimationcited by 680
- 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
- 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
- 2019A Review of Cooperative Multi-Agent Deep Reinforcement Learningcited by 147
- 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 103
- 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 89
- 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 85
- 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 81
- 2024Learning Multi-Agent Communication from Graph Modeling Perspectivecited by 47
10 more
- 2019Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Controlcited by 46
- 2020Learning Optimal Representations with the Decodable Information Bottleneckcited by 32
- 2019Learning Agent Communication under Limited Bandwidth by Message Pruningcited by 31
- 2020Succinct and Robust Multi-Agent Communication With Temporal Message Controlcited by 29
- 2021PAC-Bayes Information Bottleneckcited by 28
- 2022PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaborationcited by 23
- 2019Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learningcited by 17
- 2022DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learningcited by 9
- 2023Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networkscited by 9
- 2023Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Controlcited by 8
Built on by
Citing papers per year: 2026: 3.
3 papers.