Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method
Inverted pendulums constitute one of the popular systems for benchmarking control algorithms. Several methods have been proposed for the control of this system, the majority of which rely on the availability of a mathematical model. However, deriving a mathematical model using physical parameters or...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sakarya University
2023-12-01
|
| Series: | Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/download/article-file/3097405 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850099796363182080 |
|---|---|
| author | Uğur Yıldıran |
| author_facet | Uğur Yıldıran |
| author_sort | Uğur Yıldıran |
| collection | DOAJ |
| description | Inverted pendulums constitute one of the popular systems for benchmarking control algorithms. Several methods have been proposed for the control of this system, the majority of which rely on the availability of a mathematical model. However, deriving a mathematical model using physical parameters or system identification techniques requires manual effort. Moreover, the designed controllers may perform poorly if system parameters change. To mitigate these problems, recently, some studies used Reinforcement Learning (RL) based approaches for the control of inverted pendulum systems. Unfortunately, these methods suffer from slow convergence and local minimum problems. Moreover, they may require hyperparameter tuning which complicates the design process significantly. To alleviate these problems, the present study proposes an LQR-based RL method for adaptive balancing control of an inverted pendulum. As shown by numerical experiments, the algorithm stabilizes the system very fast without requiring a mathematical model or extensive hyperparameter tuning. In addition, it can adapt to parametric changes online. |
| format | Article |
| id | doaj-art-636a9b43b0a74d63b6828d6b0e3419d0 |
| institution | DOAJ |
| issn | 2147-835X |
| language | English |
| publishDate | 2023-12-01 |
| publisher | Sakarya University |
| record_format | Article |
| series | Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi |
| spelling | doaj-art-636a9b43b0a74d63b6828d6b0e3419d02025-08-20T02:40:25ZengSakarya UniversitySakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi2147-835X2023-12-012761311132110.16984/saufenbilder.128639128Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR MethodUğur Yıldıran0https://orcid.org/0000-0002-8220-8723YILDIZ TEKNİK ÜNİVERSİTESİInverted pendulums constitute one of the popular systems for benchmarking control algorithms. Several methods have been proposed for the control of this system, the majority of which rely on the availability of a mathematical model. However, deriving a mathematical model using physical parameters or system identification techniques requires manual effort. Moreover, the designed controllers may perform poorly if system parameters change. To mitigate these problems, recently, some studies used Reinforcement Learning (RL) based approaches for the control of inverted pendulum systems. Unfortunately, these methods suffer from slow convergence and local minimum problems. Moreover, they may require hyperparameter tuning which complicates the design process significantly. To alleviate these problems, the present study proposes an LQR-based RL method for adaptive balancing control of an inverted pendulum. As shown by numerical experiments, the algorithm stabilizes the system very fast without requiring a mathematical model or extensive hyperparameter tuning. In addition, it can adapt to parametric changes online.https://dergipark.org.tr/tr/download/article-file/3097405reinforcement learninglqrinverted pendulumq-learningadaptive control |
| spellingShingle | Uğur Yıldıran Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi reinforcement learning lqr inverted pendulum q-learning adaptive control |
| title | Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method |
| title_full | Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method |
| title_fullStr | Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method |
| title_full_unstemmed | Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method |
| title_short | Adaptive Control of an Inverted Pendulum by a Reinforcement Learningbased LQR Method |
| title_sort | adaptive control of an inverted pendulum by a reinforcement learningbased lqr method |
| topic | reinforcement learning lqr inverted pendulum q-learning adaptive control |
| url | https://dergipark.org.tr/tr/download/article-file/3097405 |
| work_keys_str_mv | AT uguryıldıran adaptivecontrolofaninvertedpendulumbyareinforcementlearningbasedlqrmethod |