Sample Complexity of Linear Quadratic Regulator Without Initial Stability
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916988967714816 |
|---|---|
| author | Moghaddam, Amirreza Neshaei Olshevsky, Alex Gharesifard, Bahman |
| author_facet | Moghaddam, Amirreza Neshaei Olshevsky, Alex Gharesifard, Bahman |
| contents | Inspired by REINFORCE, we introduce a novel receding-horizon algorithm for the Linear Quadratic Regulator (LQR) problem with unknown dynamics. Unlike prior methods, our algorithm avoids reliance on two-point gradient estimates while maintaining the same order of sample complexity. Furthermore, it eliminates the restrictive requirement of starting with a stable initial policy, broadening its applicability. Beyond these improvements, we introduce a refined analysis of error propagation through the contraction of the Riccati operator under the Riemannian distance. This refinement leads to a better sample complexity and ensures improved convergence guarantees. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14210 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sample Complexity of Linear Quadratic Regulator Without Initial Stability Moghaddam, Amirreza Neshaei Olshevsky, Alex Gharesifard, Bahman Optimization and Control Machine Learning Systems and Control Inspired by REINFORCE, we introduce a novel receding-horizon algorithm for the Linear Quadratic Regulator (LQR) problem with unknown dynamics. Unlike prior methods, our algorithm avoids reliance on two-point gradient estimates while maintaining the same order of sample complexity. Furthermore, it eliminates the restrictive requirement of starting with a stable initial policy, broadening its applicability. Beyond these improvements, we introduce a refined analysis of error propagation through the contraction of the Riccati operator under the Riemannian distance. This refinement leads to a better sample complexity and ensures improved convergence guarantees. |
| title | Sample Complexity of Linear Quadratic Regulator Without Initial Stability |
| topic | Optimization and Control Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2502.14210 |