WEKO3
アイテム
Dependency of Parameter Values in Reinforcement Learning for Navigation of a Mobile Robot on the Environment
http://hdl.handle.net/10228/00007656
http://hdl.handle.net/10228/00007656f91c3627-704b-423e-8a93-d252287631fd
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
NIP-LR10_219.pdf (509.7 kB)
|
|
| アイテムタイプ | 学術雑誌論文 = Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2020-03-11 | |||||
| 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 | |||||
| タイトル | ||||||
| タイトル | Dependency of Parameter Values in Reinforcement Learning for Navigation of a Mobile Robot on the Environment | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 著者 |
Kamei, Keiji
× Kamei, Keiji× 石川, 眞澄 |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | Reinforcement learning is suitable for navigation of a mobile robot due to its ability without supervised information. Reinforcement learning, however, has difficulties. One is its slow learning, and the other is the necessity of specifying its parameter values without prior information. We proposed to introduce sensory signals into reinforcement learning to improve its learning performance, and to optimize its parameter values by a genetic algorithm with inheritance. The latter has to specify the parameter values for every environment, which is impractical due to huge computational time. In this paper, we propose to analyze the dependency and sensitivity of the values of parameters on the environment for predicting the values of parameters for a novel environment without optimization process. We examine the dependency and the sensitivity of the values of parameters of the environment. The computer experiments clarify the dependency of the values of parameters on the environment and provide their sensitivities. | |||||
| 言語 | en | |||||
| 書誌情報 |
Neural Information Processing - Letters and Reviews 巻 10, 号 8-9, p. 219-226, 発行日 2006-10 |
|||||
| 出版社 | ||||||
| 出版者 | Korea Advanced Institute of Science and Technology | |||||
| ISSN | ||||||
| 収録物識別子タイプ | PISSN | |||||
| 収録物識別子 | 1738-2572 | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | reinforcement learning | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | genetic algorithm | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | navigation of a mobile robot | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | parameter dependency | |||||
| 出版タイプ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
| 査読の有無 | ||||||
| 値 | yes | |||||
| 研究者情報 | ||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/3_ja.html | |||||
| 論文ID（連携） | ||||||
| 値 | 10007480 | |||||
| 連携ID | ||||||
| 値 | 119 | |||||
