用10%数据实现47.3%更高精度的物理系统控制
Sample-Efficient Diffusion-based Control of Complex Physics Systems
- 分离状态-控制建模与动力学分解，提升学习效率
- 在流体、电网等系统上比现有方法精度高39.5%-47.3%
- 适合需要少样本高效控制的复杂物理系统研究者
控制复杂物理系统在多个领域至关重要。尽管基于扩散的方法在实现全局轨迹一致性方面优于传统模型驱动方法和短视序列学习方法，但其样本效率较低。本文提出SEDC（样本高效扩散控制）框架，解决复杂物理系统的核心挑战：高维状态-控制空间、强非线性以及非最优训练数据与近优控制律之间的差距。该方法通过架构解耦状态-控制建模并分解动力学，结合引导式自微调过程迭代优化控制律。我们在多种复杂非线性系统上验证了SEDC的有效性，包括高维流体动力学（Burgers）、混沌同步网络（Kuramoto）及真实电力系统稳定性控制（Swing Equation）。实验表明，相比当前最优基线，本方法在仅使用10%训练样本的情况下，控制精度提升了39.5%-47.3%。代码已公开于https://anonymous.4open.science/r/DIFOCON-C019。
原文摘要 · Abstract (English)
Controlling complex physics systems is important in diverse domains. While diffusion-based methods have demonstrated advantages over classical model-based approaches and myopic sequential learning methods in achieving global trajectory consistency, they are limited by sample efficiency.This paper presents SEDC (Sample-Efficient Diffusion-based Control), a novel framework addressing core challenges in complex physics systems: high-dimensional state-control spaces, strong nonlinearities, and the gap between non-optimal training data and near-optimal control laws.Our approach introduces a novel control paradigm by architecturally decoupling state-control modeling and decomposing dynamics, while a guided self-finetuning process iteratively refines the control law towards optimality. We validate SEDC across diverse complex nonlinear systems, including high-dimensional fluid dynamics (Burgers), chaotic synchronization networks (Kuramoto), and real-world power grid stability control (Swing Equation). Our method achieves 39.5\%-47.3\% better control accuracy than state-of-the-art baselines while using only 10\% of the training samples. The implementation is available at \href{https://anonymous.4open.science/r/DIFOCON-C019}{here}.
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。