提出单步生成的协同流模型，解决离线多智能体决策中的效率与协作矛盾。
CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making
- 用联合耦合速度场和自适应协调门控，实现单步多智能体生成。
- 60组实验中性能超越基线，在1-3步内达最优协作质量。
- 适合需要高效协同决策的多智能体系统，如游戏、机器人集群。
生成模型已成为离线多智能体强化学习的有前景范式，但现有方法需大量迭代采样。近期少步加速方法要么将联合教师蒸馏为独立学生，要么对各智能体独立应用平均速度场，导致智能体间协作受损。我们证明效率与协作的权衡并非本质：当速度场原生为联合耦合时，单步多智能体生成可保持协作。我们提出协同少步流（CoFlow），结合协同速度注意力（CVA）与自适应协调门控。有限差分一致性代理替代了耗内存的雅可比-向量乘积反向传播，仅需两次停止梯度前向传递。在涵盖MPE、MA-MuJoCo和SMAC的60个配置上，CoFlow在回合回报上匹配或超越高斯策略、基于价值的方法、Transformer策略、扩散模型及先前流基线。三个独立协作探测证实，性能提升源于智能体间协作而非单智能体容量。去噪步数扫描显示，所有配置下单步推理已足够。在集中式与分布式执行下，CoFlow均在1-3步内达到最先进协作质量。
原文摘要 · Abstract (English)
Generative models have emerged as a promising paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent few-step acceleration methods either distill a joint teacher into independent students or apply averaged velocity fields independently to each agent. Unfortunately, these few-step approaches hurt inter-agent coordination. We show that the efficiency-coordination trade-off is not inherent: single-pass multi-agent generation can preserve coordination when the velocity field is natively joint-coupled. We propose Coordinated few-step Flow (CoFlow), an architecture that combines Coordinated Velocity Attention (CVA) with Adaptive Coordination Gating. A finite-difference consistency surrogate further replaces memory-prohibitive Jacobian-vector product backpropagation through the averaged velocity field with two stop-gradient forward passes. Across 60 configurations spanning MPE, MA-MuJoCo, and SMAC, CoFlow matches or surpasses Gaussian policies, value-based methods, transformer policies, diffusion models, and prior flow baselines on episodic return. Three independent coordination probes confirm that CoFlow's improvements arise from inter-agent coordination rather than per-agent capacity. A denoising-step sweep shows that single-pass inference suffices on every configuration. CoFlow reaches state-of-the-art coordination quality in 1-3 denoising steps under both centralized and decentralized execution. Project Page: https://guowei-zou.github.io/coflow/
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。