Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.02619 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917382550716416 |
|---|---|
| author | Wang, Shanting Sun, Weihao Malikopoulos, Andreas A. |
| author_facet | Wang, Shanting Sun, Weihao Malikopoulos, Andreas A. |
| contents | In this paper, we present an online learning approach for two-player zero-sum linear quadratic games with unknown dynamics. We develop a framework combining regularized least squares model estimation, high probability confidence sets, and surrogate model selection to maintain a regular model for policy updates. We apply a shrinkage step at each episode to identify a surrogate model in the region where the generalized algebraic Riccati equation admits a stabilizing saddle point solution. We then establish regret analysis on algorithm convergence, followed by a numerical example to illustrate the convergence performance and verify the regret analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02619 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Online Learning Approach for Two-Player Zero-Sum Linear Quadratic Games Wang, Shanting Sun, Weihao Malikopoulos, Andreas A. Systems and Control In this paper, we present an online learning approach for two-player zero-sum linear quadratic games with unknown dynamics. We develop a framework combining regularized least squares model estimation, high probability confidence sets, and surrogate model selection to maintain a regular model for policy updates. We apply a shrinkage step at each episode to identify a surrogate model in the region where the generalized algebraic Riccati equation admits a stabilizing saddle point solution. We then establish regret analysis on algorithm convergence, followed by a numerical example to illustrate the convergence performance and verify the regret analysis. |
| title | An Online Learning Approach for Two-Player Zero-Sum Linear Quadratic Games |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2604.02619 |