ダウンロード数: 37
このアイテムのファイル:
ファイル | 記述 | サイズ | フォーマット | |
---|---|---|---|---|
18824889.2021.1936817.pdf | 2.32 MB | Adobe PDF | 見る/開く |
タイトル: | Value iteration with deep neural networks for optimal control of input-affine nonlinear systems |
著者: | Beppu, Hirofumi Maruta, Ichiro https://orcid.org/0000-0002-2246-3570 (unconfirmed) Fujimoto, Kenji https://orcid.org/0000-0001-6345-4884 (unconfirmed) |
著者名の別形: | 別府, 啓史 丸田, 一郎 藤本, 健治 |
キーワード: | Value iteration optimal control deep neural networks input-affine nonlinear systems convergence analysis |
発行日: | 2021 |
出版者: | Taylor & Francis |
誌名: | SICE Journal of Control, Measurement, and System Integration |
巻: | 14 |
号: | 1 |
開始ページ: | 140 |
終了ページ: | 149 |
抄録: | This paper proposes a new algorithm with deep neural networks to solve optimal control problems for continuous-time input nonlinear systems based on a value iteration algorithm. The proposed algorithm applies the networks to approximating the value functions and control inputs in the iterations. Consequently, the partial differential equations of the original algorithm reduce to the optimization problems for the parameters of the networks. Although the conventional algorithm can obtain the optimal control with iterative computations, each of the computations needs to be completed precisely, and it is hard to achieve sufficient precision in practice. Instead, the proposed method provides a practical method using deep neural networks and overcomes the difficulty based on a property of the networks, under which our convergence analysis shows that the proposed algorithm can achieve the minimum of the value function and the corresponding optimal controller. The effectiveness of the proposed method even with reasonable computational resources is demonstrated in two numerical simulations. |
著作権等: | © 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group This is an Open Access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
URI: | http://hdl.handle.net/2433/276711 |
DOI(出版社版): | 10.1080/18824889.2021.1936817 |
出現コレクション: | 学術雑誌掲載論文等 |
このアイテムは次のライセンスが設定されています: クリエイティブ・コモンズ・ライセンス