提出一种稳定高效的多智能体通信框架，提升机器人协作性能。
SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication
- 用低维隐变量学习任务相关的规划与交通信息，分离通信与策略优化。
- 在标准基准和真实仓库场景中，通信质量与任务表现均优于现有方法。
- 适合需要高效协作的多机器人系统，尤其适用于动态环境下的持续学习。
涌现通信使部分可观测的自主移动机器人（AMRs）在去中心化多智能体强化学习（MARL）中实现有效协调。然而，现有方法常面临通信协议不稳定、消息语义无意义以及通信学习与策略优化相互干扰的问题，导致协作能力随时间退化。我们提出SCALE-COMM（共享、对比对齐的潜在嵌入用于通信），一种自监督框架，用于学习紧凑、稳定且与策略相关联的通信表征。该方法通过训练低维潜在消息来捕捉任务相关的规划与交通信息，同时在各智能体间和时间上保持一致性，从而将通信学习与策略优化解耦。在标准MARL基准和一个真实的仓库协调任务中，SCALE-COMM在表征质量和任务性能上均持续优于现有通信框架。所学通信空间在策略微调下表现出更好的稳定性、样本效率和吞吐量，验证了基于表征的通信在可扩展多智能体协调中的有效性。
原文摘要 · Abstract (English)
Emergent communication enables partially observant Autonomous Mobile Robots (AMRs) to coordinate effectively in decentralized multi-agent reinforcement learning (MARL) settings. However, existing approaches often struggle with unstable communication protocols, ungrounded message semantics, and interference between communication learning and policy optimization, leading to degraded coordination over time. We propose SCALE-COMM (Shared, Contrastively-Aligned Latent Embeddings for COMMunication), a self-supervised framework for learning compact, stable, and policy-relevant communication representations. SCALE-COMM decouples communication learning from policy optimization by training low-dimensional latent messages that capture task-relevant planning and traffic information, while enforcing consistency across agents and time. Across standard MARL benchmarks and a realistic warehouse coordination task, SCALE-COMM consistently outperforms existing communication frameworks in both representation quality and task performance. The learned communication space yields improved stability, sample efficiency, and throughput under policy fine-tuning, demonstrating the effectiveness of representation-driven communication for scalable multi-agent coordination.
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。