Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2406.19817 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910506122477568 |
|---|---|
| author | Nagel, Tobias Huber, Marco F. |
| author_facet | Nagel, Tobias Huber, Marco F. |
| contents | The identification of a mathematical dynamics model is a crucial step in the designing process of a controller. However, it is often very difficult to identify the system's governing equations, especially in complex environments that combine physical laws of different disciplines. In this paper, we present a new approach that allows identifying an ordinary differential equation by means of a physics-informed machine learning algorithm. Our method introduces a special neural network that allows exploiting prior human knowledge to a certain degree and extends it autonomously, so that the resulting differential equations describe the system as accurately as possible. We validate the method on a Duffing oscillator with simulation data and, additionally, on a cascaded tank example with real-world data. Subsequently, we use the developed algorithm in a model-based reinforcement learning framework by alternately identifying and controlling a system to a target state. We test the performance by swinging-up an inverted pendulum on a cart. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_19817 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Identifying Ordinary Differential Equations for Data-efficient Model-based Reinforcement Learning Nagel, Tobias Huber, Marco F. Systems and Control The identification of a mathematical dynamics model is a crucial step in the designing process of a controller. However, it is often very difficult to identify the system's governing equations, especially in complex environments that combine physical laws of different disciplines. In this paper, we present a new approach that allows identifying an ordinary differential equation by means of a physics-informed machine learning algorithm. Our method introduces a special neural network that allows exploiting prior human knowledge to a certain degree and extends it autonomously, so that the resulting differential equations describe the system as accurately as possible. We validate the method on a Duffing oscillator with simulation data and, additionally, on a cascaded tank example with real-world data. Subsequently, we use the developed algorithm in a model-based reinforcement learning framework by alternately identifying and controlling a system to a target state. We test the performance by swinging-up an inverted pendulum on a cart. |
| title | Identifying Ordinary Differential Equations for Data-efficient Model-based Reinforcement Learning |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2406.19817 |