Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.04721 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929522573574144 |
|---|---|
| author | Sun, Zhongshi Jia, Guangyan |
| author_facet | Sun, Zhongshi Jia, Guangyan |
| contents | In this article, we study a continuous-time stochastic $H_\infty$ control problem based on reinforcement learning (RL) techniques that can be viewed as solving a stochastic linear-quadratic two-person zero-sum differential game (LQZSG). First, we propose an RL algorithm that can iteratively solve stochastic game algebraic Riccati equation based on collected state and control data when all dynamic system information is unknown. In addition, the algorithm only needs to collect data once during the iteration process. Then, we discuss the robustness and convergence of the inner and outer loops of the policy iteration algorithm, respectively, and show that when the error of each iteration is within a certain range, the algorithm can converge to a small neighborhood of the saddle point of the stochastic LQZSG problem. Finally, we applied the proposed RL algorithm to two simulation examples to verify the effectiveness of the algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04721 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robust policy iteration for continuous-time stochastic $H_\infty$ control problem with unknown dynamics Sun, Zhongshi Jia, Guangyan Optimization and Control In this article, we study a continuous-time stochastic $H_\infty$ control problem based on reinforcement learning (RL) techniques that can be viewed as solving a stochastic linear-quadratic two-person zero-sum differential game (LQZSG). First, we propose an RL algorithm that can iteratively solve stochastic game algebraic Riccati equation based on collected state and control data when all dynamic system information is unknown. In addition, the algorithm only needs to collect data once during the iteration process. Then, we discuss the robustness and convergence of the inner and outer loops of the policy iteration algorithm, respectively, and show that when the error of each iteration is within a certain range, the algorithm can converge to a small neighborhood of the saddle point of the stochastic LQZSG problem. Finally, we applied the proposed RL algorithm to two simulation examples to verify the effectiveness of the algorithm. |
| title | Robust policy iteration for continuous-time stochastic $H_\infty$ control problem with unknown dynamics |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2402.04721 |