WEKO3
アイテム
Reservoir Reinforcement Learning with Chaotic Boltzmann Machines Implemented on an FPGA
http://hdl.handle.net/10228/0002001134
http://hdl.handle.net/10228/00020011347a199c9e-8144-43cf-89e9-5be4f0a4d1ac
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
10444454.pdf (683 KB)
|
|
| Item type | 共通アイテムタイプ(1) | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2025-01-21 | |||||||||||||||||
| タイトル | ||||||||||||||||||
| タイトル | Reservoir Reinforcement Learning with Chaotic Boltzmann Machines Implemented on an FPGA | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| 著者 |
Sakino, Yamato
× Sakino, Yamato
× 田向, 権
WEKO
6059
× 森江, 隆
WEKO
1615
× Katori, Yuichi
|
|||||||||||||||||
| 著作権関連情報 | ||||||||||||||||||
| 権利情報 | Copyright(C)2020 IEICE | |||||||||||||||||
| 著作権関連情報 | ||||||||||||||||||
| 権利情報 | This work is licensed under a Creative Commons. Attribution-NonCommercial-NoDerivatives 4.0 International. | |||||||||||||||||
| 抄録 | ||||||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||||||
| 内容記述 | Reinforcement learning has led to advances in areas such as attitude control in robotics and action planning in autonomous driving systems. However, reinforcement learning algorithms often face computational bottlenecks that limit their application to edge devices. In recent years, reservoir computing has emerged as a potential solution to this problem. One of these models updates the weight matrix using Q-learning, a popular reinforcement learning algorithm. This paper introduces reservoir reinforcement learning using chaotic Boltzmann machines on a field programmable gate array. We demonstrate the efficient implementation of reservoir computing with chaotic Boltzmann machines in hardware, achieving low computational costs. To demonstrate the effectiveness of this approach, we validate the proposed model using an action planning task in a two-dimensional environment consisting of nine rooms. The result shows that the model can be implemented in digital circuits with low power consumption and hardware resource savings while maintaining problem-solving capabilities. This result suggests efficient machine learning hardware in action planning could be applied to real-world scenarios. | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| 備考 | ||||||||||||||||||
| 内容記述タイプ | Other | |||||||||||||||||
| 内容記述 | 2023 International Symposium on Nonlinear Theory and Its Applications, NOLTA2023, September 26-29, 2023, Catania and Online | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| 書誌情報 |
en : IEICE Proceeding Series 巻 76, p. 422-425, 発行日 2023-09-21 |
|||||||||||||||||
| 出版社 | ||||||||||||||||||
| 出版者 | 電子情報通信学会 | |||||||||||||||||
| 言語 | ja | |||||||||||||||||
| 言語 | ||||||||||||||||||
| 言語 | eng | |||||||||||||||||
| 資源タイプ | ||||||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||||||
| 資源タイプ | journal article | |||||||||||||||||
| 出版タイプ | ||||||||||||||||||
| 出版タイプ | VoR | |||||||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||||||
| DOI | ||||||||||||||||||
| 識別子タイプ | DOI | |||||||||||||||||
| 関連識別子 | https://doi.org/10.34385/proc.76.c1l-33 | |||||||||||||||||
| ISSN | ||||||||||||||||||
| 収録物識別子タイプ | EISSN | |||||||||||||||||
| 収録物識別子 | 2188-5079 | |||||||||||||||||
| 会議記述 | ||||||||||||||||||
| 会議名 | International Symposium on Nonlinear Theory and Its Applications | |||||||||||||||||
| 開始年 | 2023 | |||||||||||||||||
| 開始月 | 9 | |||||||||||||||||
| 開始日 | 26 | |||||||||||||||||
| 終了年 | 2023 | |||||||||||||||||
| 終了月 | 9 | |||||||||||||||||
| 終了日 | 29 | |||||||||||||||||
| 開催国 | ITA | |||||||||||||||||
| 査読の有無 | ||||||||||||||||||
| 値 | yes | |||||||||||||||||
| 研究者情報 | ||||||||||||||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/100000641_ja.html | |||||||||||||||||
| 研究者情報 | ||||||||||||||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/339_ja.html | |||||||||||||||||
| 論文ID（連携） | ||||||||||||||||||
| 値 | 10444454 | |||||||||||||||||
| 連携ID | ||||||||||||||||||
| 値 | 12663 | |||||||||||||||||
