Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911768508366848 |
|---|---|
| author | Zhang, Xiangyuan Başar, Tamer |
| author_facet | Zhang, Xiangyuan Başar, Tamer |
| contents | We revisit in this paper the discrete-time linear quadratic regulator (LQR) problem from the perspective of receding-horizon policy gradient (RHPG), a newly developed model-free learning framework for control applications. We provide a fine-grained sample complexity analysis for RHPG to learn a control policy that is both stabilizing and $ε$-close to the optimal LQR solution, and our algorithm does not require knowing a stabilizing control policy for initialization. Combined with the recent application of RHPG in learning the Kalman filter, we demonstrate the general applicability of RHPG in linear control and estimation with streamlined analyses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_13144 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient Zhang, Xiangyuan Başar, Tamer Optimization and Control Artificial Intelligence Machine Learning Systems and Control We revisit in this paper the discrete-time linear quadratic regulator (LQR) problem from the perspective of receding-horizon policy gradient (RHPG), a newly developed model-free learning framework for control applications. We provide a fine-grained sample complexity analysis for RHPG to learn a control policy that is both stabilizing and $ε$-close to the optimal LQR solution, and our algorithm does not require knowing a stabilizing control policy for initialization. Combined with the recent application of RHPG in learning the Kalman filter, we demonstrate the general applicability of RHPG in linear control and estimation with streamlined analyses. |
| title | Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient |
| topic | Optimization and Control Artificial Intelligence Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2302.13144 |