提出新通信框架，让智能体在复杂环境中更高效地选择合作对象。
Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning
- 限定消息只传给物理可达的邻居，减少无效通信。
- 预测干扰并优先选低干扰、高价值的合作对象。
- 在动态复杂场景中表现更稳定，适合大规模多智能体系统。
有效通信对多智能体强化学习中的复杂协作任务至关重要。然而，有限的通信带宽和动态复杂的环境拓扑给识别高价值通信伙伴带来了挑战。智能体必须在缺乏先验知识的情况下，在不确定性中选择协作对象。为此，我们提出干扰感知的K步可达通信（IA-KRC）框架，包含两个核心组件：(1) 基于K步可达性的协议，将消息传递限制在物理可达的邻居范围内；(2) 干扰预测模块，通过最小化干扰并最大化收益来优化伙伴选择。与现有方法相比，IA-KRC 在存在环境干扰的情况下仍能实现更持久高效的协作。全面评估表明，该方法优于当前最先进基线，在复杂拓扑和高度动态的多智能体场景中表现出更强的鲁棒性和可扩展性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。