通过谱分解实现多智能体参数共享，兼顾多样性和效率。
Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning
- 用奇异值分解在频谱域共享参数，保留方向一致
- 各智能体学习不同奇异值掩码，实现行为差异化
- 适合追求高效且多样化的多智能体系统设计
参数共享是多智能体强化学习中提升可扩展性的关键策略，但传统全共享架构常导致智能体行为同质化。近期方法通过聚类、剪枝或掩码引入多样性，但通常牺牲资源效率。本文提出Prism，一种在频谱域通过奇异值分解（SVD）实现参数共享的框架：所有智能体共享奇异向量方向，同时各自学习不同的奇异值掩码。该机制促进智能体间行为多样性，并保持高可扩展性。在同质（LBF、SMACv2）与异质（MaMuJoCo）基准上的大量实验表明，Prism在性能上达到竞争水平，且资源效率更优。
原文摘要 · Abstract (English)
Parameter sharing is a key strategy in multi-agent reinforcement learning (MARL) for improving scalability, yet conventional fully shared architectures often collapse into homogeneous behaviors. Recent methods introduce diversity through clustering, pruning, or masking, but typically compromise resource efficiency. We propose Prism, a parameter sharing framework that induces inter-agent diversity by representing shared networks in the spectral domain via singular value decomposition (SVD). All agents share the singular vector directions while learning distinct spectral masks on singular values. This mechanism encourages inter-agent diversity and preserves scalability. Extensive experiments on both homogeneous (LBF, SMACv2) and heterogeneous (MaMuJoCo) benchmarks show that Prism achieves competitive performance with superior resource efficiency.
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。