AI Agents 相关度: 9/10

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

Ziyu Cheng, Jinsheng Ren, Zhouxian Jiang, Chenzhihang Li, Rongye Shi, Bin Liang, Jun Yang
arXiv: 2603.15054v1 发布: 2026-03-16 更新: 2026-03-16

AI 摘要

IA-KRC通过可达通信和干扰预测提升多智能体强化学习中的合作效率。

主要贡献

  • 提出了一种干扰感知的K步可达通信框架(IA-KRC)
  • 设计了K步可达协议,限制消息传递在可达邻居之间
  • 引入干扰预测模块,优化伙伴选择,减少干扰

方法论

通过K步可达协议限制通信范围,并使用干扰预测模块优化通信伙伴选择,提升合作效率。

原文摘要

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.

标签

multi-agent reinforcement learning communication interference reachability

arXiv 分类

cs.AI