Exploring Model Structures to Reduce Data Requirements for Neural ODE Learning in Control Systems
-
- Hashimoto Takanori
- Graduate School of Engineering, University of Hyogo
-
- Matsui Nobuyuki
- Graduate School of Engineering, University of Hyogo
-
- Kamiura Naotake
- Graduate School of Engineering, University of Hyogo
-
- Isokawa Teijiro
- Graduate School of Engineering, University of Hyogo
この論文をさがす
抄録
<p>In this study, we investigate model structures for neural ODEs to improve the data efficiency in learning the dynamics of control systems. We introduce two model structures and compare them with a typical baseline structure. The first structure considers the relationship between the coordinates and velocities of the control system, while the second structure adds linearity with respect to the control term to the first structure. Both of these structures can be easily implemented without requiring additional computation. In numerical experiments, we evaluate these structure on simulated simple pendulum and CartPole systems and show that incorporating these characteristics into the model structure leads to accurate learning with a smaller amount of training data compared to the baseline structure.</p>
収録刊行物
-
- Journal of Advanced Computational Intelligence and Intelligent Informatics
-
Journal of Advanced Computational Intelligence and Intelligent Informatics 27 (4), 537-542, 2023-07-20
富士技術出版株式会社
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390015354565779584
-
- NII書誌ID
- AA12042502
-
- ISSN
- 18838014
- 13430130
-
- NDL書誌ID
- 032947542
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- NDL
- Crossref
-
- 抄録ライセンスフラグ
- 使用不可