Data-Driven Robust Control Using Reinforcement Learning
This paper proposes a robust control design method using reinforcement learning for controlling partially-unknown dynamical systems under uncertain conditions. The method extends the optimal reinforcement learning algorithm with a new learning technique based on the robust control theory. By learnin...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/4/2262 |
| _version_ | 1797482954246586368 |
|---|---|
| author | Phuong D. Ngo Miguel Tejedor Fred Godtliebsen |
| author_facet | Phuong D. Ngo Miguel Tejedor Fred Godtliebsen |
| author_sort | Phuong D. Ngo |
| collection | DOAJ |
| description | This paper proposes a robust control design method using reinforcement learning for controlling partially-unknown dynamical systems under uncertain conditions. The method extends the optimal reinforcement learning algorithm with a new learning technique based on the robust control theory. By learning from the data, the algorithm proposes actions that guarantee the stability of the closed-loop system within the uncertainties estimated also from the data. Control policies are calculated by solving a set of linear matrix inequalities. The controller was evaluated using simulations on a blood glucose model for patients with Type 1 diabetes. Simulation results show that the proposed methodology is capable of safely regulating the blood glucose within a healthy level under the influence of measurement and process noises. The controller has also significantly reduced the post-meal fluctuation of the blood glucose. A comparison between the proposed algorithm and the existing optimal reinforcement learning algorithm shows the improved robustness of the closed-loop system using our method. |
| first_indexed | 2024-03-09T22:39:58Z |
| format | Article |
| id | doaj.art-af6bed5de2f44137929e46fb13c608fe |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:39:58Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-af6bed5de2f44137929e46fb13c608fe2023-11-23T18:41:58ZengMDPI AGApplied Sciences2076-34172022-02-01124226210.3390/app12042262Data-Driven Robust Control Using Reinforcement LearningPhuong D. Ngo0Miguel Tejedor1Fred Godtliebsen2Norwegian Centre for E-Health Research, 9019 Tromsø, NorwayNorwegian Centre for E-Health Research, 9019 Tromsø, NorwayDepartment of Mathematics and Statistics, Faculty of Science and Technology, UiT The Arctic University of Norway, 9019 Tromsø, NorwayThis paper proposes a robust control design method using reinforcement learning for controlling partially-unknown dynamical systems under uncertain conditions. The method extends the optimal reinforcement learning algorithm with a new learning technique based on the robust control theory. By learning from the data, the algorithm proposes actions that guarantee the stability of the closed-loop system within the uncertainties estimated also from the data. Control policies are calculated by solving a set of linear matrix inequalities. The controller was evaluated using simulations on a blood glucose model for patients with Type 1 diabetes. Simulation results show that the proposed methodology is capable of safely regulating the blood glucose within a healthy level under the influence of measurement and process noises. The controller has also significantly reduced the post-meal fluctuation of the blood glucose. A comparison between the proposed algorithm and the existing optimal reinforcement learning algorithm shows the improved robustness of the closed-loop system using our method.https://www.mdpi.com/2076-3417/12/4/2262reinforcement learningrobust controldata-driven |
| spellingShingle | Phuong D. Ngo Miguel Tejedor Fred Godtliebsen Data-Driven Robust Control Using Reinforcement Learning Applied Sciences reinforcement learning robust control data-driven |
| title | Data-Driven Robust Control Using Reinforcement Learning |
| title_full | Data-Driven Robust Control Using Reinforcement Learning |
| title_fullStr | Data-Driven Robust Control Using Reinforcement Learning |
| title_full_unstemmed | Data-Driven Robust Control Using Reinforcement Learning |
| title_short | Data-Driven Robust Control Using Reinforcement Learning |
| title_sort | data driven robust control using reinforcement learning |
| topic | reinforcement learning robust control data-driven |
| url | https://www.mdpi.com/2076-3417/12/4/2262 |
| work_keys_str_mv | AT phuongdngo datadrivenrobustcontrolusingreinforcementlearning AT migueltejedor datadrivenrobustcontrolusingreinforcementlearning AT fredgodtliebsen datadrivenrobustcontrolusingreinforcementlearning |