Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear Models
Reinforcement learning (RL) agents can learn to control a nonlinear system without using a model of the system. However, having a model brings benefits, mainly in terms of a reduced number of unsuccessful trials before achieving acceptable control performance. Several modelling approaches have been...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/6617309 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832551580669313024 |
|---|---|
| author | Martin Brablc Jan Žegklitz Robert Grepl Robert Babuška |
| author_facet | Martin Brablc Jan Žegklitz Robert Grepl Robert Babuška |
| author_sort | Martin Brablc |
| collection | DOAJ |
| description | Reinforcement learning (RL) agents can learn to control a nonlinear system without using a model of the system. However, having a model brings benefits, mainly in terms of a reduced number of unsuccessful trials before achieving acceptable control performance. Several modelling approaches have been used in the RL domain, such as neural networks, local linear regression, or Gaussian processes. In this article, we focus on techniques that have not been used much so far: symbolic regression (SR), based on genetic programming and local modelling. Using measured data, symbolic regression yields a nonlinear, continuous-time analytic model. We benchmark two state-of-the-art methods, SNGP (single-node genetic programming) and MGGP (multigene genetic programming), against a standard incremental local regression method called RFWR (receptive field weighted regression). We have introduced modifications to the RFWR algorithm to better suit the low-dimensional continuous-time systems we are mostly dealing with. The benchmark is a nonlinear, dynamic magnetic manipulation system. The results show that using the RL framework and a suitable approximation method, it is possible to design a stable controller of such a complex system without the necessity of any haphazard learning. While all of the approximation methods were successful, MGGP achieved the best results at the cost of higher computational complexity. Index Terms–AI-based methods, local linear regression, nonlinear systems, magnetic manipulation, model learning for control, optimal control, reinforcement learning, symbolic regression. |
| format | Article |
| id | doaj-art-096c940cdf9d49c5b732b33c5ce7535b |
| institution | Kabale University |
| issn | 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-096c940cdf9d49c5b732b33c5ce7535b2025-02-03T06:01:00ZengWileyComplexity1099-05262021-01-01202110.1155/2021/6617309Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear ModelsMartin Brablc0Jan Žegklitz1Robert Grepl2Robert Babuška3Institute of Solid Mechanics, Mechatronics and BiomechanicsCzech Institute of Informatics, Robotics and CyberneticsInstitute of Solid Mechanics, Mechatronics and BiomechanicsCzech Institute of Informatics, Robotics and CyberneticsReinforcement learning (RL) agents can learn to control a nonlinear system without using a model of the system. However, having a model brings benefits, mainly in terms of a reduced number of unsuccessful trials before achieving acceptable control performance. Several modelling approaches have been used in the RL domain, such as neural networks, local linear regression, or Gaussian processes. In this article, we focus on techniques that have not been used much so far: symbolic regression (SR), based on genetic programming and local modelling. Using measured data, symbolic regression yields a nonlinear, continuous-time analytic model. We benchmark two state-of-the-art methods, SNGP (single-node genetic programming) and MGGP (multigene genetic programming), against a standard incremental local regression method called RFWR (receptive field weighted regression). We have introduced modifications to the RFWR algorithm to better suit the low-dimensional continuous-time systems we are mostly dealing with. The benchmark is a nonlinear, dynamic magnetic manipulation system. The results show that using the RL framework and a suitable approximation method, it is possible to design a stable controller of such a complex system without the necessity of any haphazard learning. While all of the approximation methods were successful, MGGP achieved the best results at the cost of higher computational complexity. Index Terms–AI-based methods, local linear regression, nonlinear systems, magnetic manipulation, model learning for control, optimal control, reinforcement learning, symbolic regression.http://dx.doi.org/10.1155/2021/6617309 |
| spellingShingle | Martin Brablc Jan Žegklitz Robert Grepl Robert Babuška Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear Models Complexity |
| title | Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear Models |
| title_full | Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear Models |
| title_fullStr | Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear Models |
| title_full_unstemmed | Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear Models |
| title_short | Control of Magnetic Manipulator Using Reinforcement Learning Based on Incrementally Adapted Local Linear Models |
| title_sort | control of magnetic manipulator using reinforcement learning based on incrementally adapted local linear models |
| url | http://dx.doi.org/10.1155/2021/6617309 |
| work_keys_str_mv | AT martinbrablc controlofmagneticmanipulatorusingreinforcementlearningbasedonincrementallyadaptedlocallinearmodels AT janzegklitz controlofmagneticmanipulatorusingreinforcementlearningbasedonincrementallyadaptedlocallinearmodels AT robertgrepl controlofmagneticmanipulatorusingreinforcementlearningbasedonincrementallyadaptedlocallinearmodels AT robertbabuska controlofmagneticmanipulatorusingreinforcementlearningbasedonincrementallyadaptedlocallinearmodels |