arXiv Open Access 2026

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

Ziyu Cheng Jinsheng Ren Zhouxian Jiang Chenzhihang Li Rongye Shi +2 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (7)

Z

Ziyu Cheng

J

Jinsheng Ren

Z

Zhouxian Jiang

C

Chenzhihang Li

R

Rongye Shi

B

Bin Liang

J

Jun Yang

Format Sitasi

Cheng, Z., Ren, J., Jiang, Z., Li, C., Shi, R., Liang, B. et al. (2026). Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning. https://arxiv.org/abs/2603.15054

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓