# Robust and Efficient Communication in Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2511.11393 · HTML: https://mlsanity.com/paper/2511.11393/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [FedKD: Communication Efficient Federated Learning via Knowledge Distillation](https://mlsanity.com/paper/2108.13323/) (2021)
- [Large AI Model-Based Semantic Communications](https://mlsanity.com/paper/2307.03492/) (2023)
- [Learning Structured Communication for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2002.04235/) (2020)
- [Multi-Agent Reinforcement Learning for Connected and Automated Vehicles Control: Recent Advancements and Future Prospects](https://mlsanity.com/paper/2312.11084/) (2023)
- [RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states](https://mlsanity.com/paper/2205.07229/) (2022)
- [Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey](https://mlsanity.com/paper/2504.21048/) (2025)
- [Goal-Oriented Semantic Communications for 6G Networks](https://mlsanity.com/paper/2210.09372/) (2022)
- [Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation](https://mlsanity.com/paper/2305.05116/) (2023)
- [Heterogeneous Embodied Multi-Agent Collaboration](https://mlsanity.com/paper/2307.13957/) (2023)
- [Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization](https://mlsanity.com/paper/2310.09833/) (2023)
- [Effective Communication with Dynamic Feature Compression](https://mlsanity.com/paper/2401.16236/) (2024)
- [The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication](https://mlsanity.com/paper/2103.13026/) (2021)
- [Multi-Agent Deep Reinforcement Learning For Persistent Monitoring With Sensing, Communication, and Localization Constraints](https://mlsanity.com/paper/2109.06831/) (2021)
- [Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox](https://mlsanity.com/paper/2212.00253/) (2022)
- [Robust Multi-agent Communication via Multi-view Message Certification](https://mlsanity.com/paper/2305.13936/) (2023)
- [Evolutionary Multi-agent Reinforcement Learning in Group Social Dilemmas](https://mlsanity.com/paper/2411.10459/) (2024)
- [DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models](https://mlsanity.com/paper/2507.09955/) (2025)
- [Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2302.09605/) (2023)
- [Denoising and Reconstruction of Nonlinear Dynamics using Truncated Reservoir Computing](https://mlsanity.com/paper/2504.13355/) (2025)

## Built on by (most cited first, 2 of 2)

- [AgentComm-Bench: Stress-Testing Cooperative Embodied AI Under Latency, Packet Loss, and Bandwidth Collapse](https://mlsanity.com/paper/2603.20285/) (2026)
- [Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2604.08728/) (2026)

## Abstract (arXiv)

Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.