Sample-Efficient Diffusion-based Control of Complex Physics Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911412526252032 |
|---|---|
| author | Chen, Hongyi Ding, Jingtao Shu, Jianhai Yu, Xinchun Liang, Xiaojun Li, Yong Zhang, Xiao-Ping |
| author_facet | Chen, Hongyi Ding, Jingtao Shu, Jianhai Yu, Xinchun Liang, Xiaojun Li, Yong Zhang, Xiao-Ping |
| contents | 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}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17893 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sample-Efficient Diffusion-based Control of Complex Physics Systems Chen, Hongyi Ding, Jingtao Shu, Jianhai Yu, Xinchun Liang, Xiaojun Li, Yong Zhang, Xiao-Ping Systems and Control Artificial Intelligence Machine Learning 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}. |
| title | Sample-Efficient Diffusion-based Control of Complex Physics Systems |
| topic | Systems and Control Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.17893 |