Transfer Learning for LQR Control
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909598563172352 |
|---|---|
| author | Guo, Taosha Pasqualetti, Fabio |
| author_facet | Guo, Taosha Pasqualetti, Fabio |
| contents | In this paper, we study a transfer learning framework for Linear Quadratic Regulator (LQR) control, where (i) the dynamics of the system of interest (target system) are unknown and only a short trajectory of impulse responses from the target system is provided, and (ii) impulse responses are available from $N$ source systems with different dynamics. We show that the LQR controller can be learned from a sufficiently long trajectory of impulse responses. Further, a transferable mode set can be identified using the available data from source systems and the target system, enabling the reconstruction of the target system's impulse responses for controller design. By leveraging data from source systems, we show that the sample complexity for synthesizing the LQR controller can be reduced by $50 \%$. Algorithms and numerical examples are provided to demonstrate the implementation of the proposed transfer control framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06755 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transfer Learning for LQR Control Guo, Taosha Pasqualetti, Fabio Systems and Control In this paper, we study a transfer learning framework for Linear Quadratic Regulator (LQR) control, where (i) the dynamics of the system of interest (target system) are unknown and only a short trajectory of impulse responses from the target system is provided, and (ii) impulse responses are available from $N$ source systems with different dynamics. We show that the LQR controller can be learned from a sufficiently long trajectory of impulse responses. Further, a transferable mode set can be identified using the available data from source systems and the target system, enabling the reconstruction of the target system's impulse responses for controller design. By leveraging data from source systems, we show that the sample complexity for synthesizing the LQR controller can be reduced by $50 \%$. Algorithms and numerical examples are provided to demonstrate the implementation of the proposed transfer control framework. |
| title | Transfer Learning for LQR Control |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2503.06755 |