English

Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning

Artificial Intelligence 2026-03-17 v1

Abstract

Effective communication is pivotal for addressing complex collaborative tasks in multi-agent reinforcement learning (MARL). Yet, limited communication bandwidth and dynamic, intricate environmental topologies present significant challenges in identifying high-value communication partners. Agents must consequently select collaborators under uncertainty, lacking a priori knowledge of which partners can deliver task-critical information. To this end, we propose Interference-Aware K-Step Reachable Communication (IA-KRC), a novel framework that enhances cooperation via two core components: (1) a K-Step reachability protocol that confines message passing to physically accessible neighbors, and (2) an interference-prediction module that optimizes partner choice by minimizing interference while maximizing utility. Compared to existing methods, IA-KRC enables substantially more persistent and efficient cooperation despite environmental interference. Comprehensive evaluations confirm that IA-KRC achieves superior performance compared to state-of-the-art baselines, while demonstrating enhanced robustness and scalability in complex topological and highly dynamic multi-agent scenarios.

Keywords

Cite

@article{arxiv.2603.15054,
  title  = {Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning},
  author = {Ziyu Cheng and Jinsheng Ren and Zhouxian Jiang and Chenzhihang Li and Rongye Shi and Bin Liang and Jun Yang},
  journal= {arXiv preprint arXiv:2603.15054},
  year   = {2026}
}

Comments

multi-agent reinforcement learning, communication

R2 v1 2026-07-01T11:21:57.665Z