WEKO3
アイテム
An Information-Theoretic Analysis of Return Maximization in Reinforcement Learning
https://hiroshima-cu.repo.nii.ac.jp/records/1824
https://hiroshima-cu.repo.nii.ac.jp/records/18245f355555-cd9e-4f06-9238-23bb3293dd9e
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
neunet11preprint_witherrata-1.pdf (146.8 kB)
|
|
| Item type | 学術雑誌論文 / Journal Article(1) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2023-03-07 | |||||||||||
| タイトル | ||||||||||||
| タイトル | An Information-Theoretic Analysis of Return Maximization in Reinforcement Learning | |||||||||||
| 言語 | ||||||||||||
| 言語 | eng | |||||||||||
| キーワード | ||||||||||||
| 主題 | Reinforcement learning | |||||||||||
| キーワード | ||||||||||||
| 主題 | Stochastic sequential decision process | |||||||||||
| キーワード | ||||||||||||
| 主題 | Information theory | |||||||||||
| キーワード | ||||||||||||
| 主題 | Asymptotic equipartition property | |||||||||||
| 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 | |||||||||||
| 著者 |
IWATA, Kazunori
× IWATA, Kazunori
× 岩田, 一貴
|
|||||||||||
| 抄録 | ||||||||||||
| 内容記述タイプ | Abstract | |||||||||||
| 内容記述 | We present a general analysis of return maximization in reinforcement learning. This analysis does not require assumptions of Markovianity, stationarity, and ergodicity for the stochastic sequential decision processes of reinforcement learning. Instead, our analysis assumes the asymptotic equipartition property fundamental to information theory, providing a substantially different view from that in the literature. As our main results, we show that return maximization is achieved by the overlap of typical and best sequence sets, and we present a class of stochastic sequential decision processes with the necessary condition for return maximization. We also describe several examples of best sequences in terms of return maximization in the class of stochastic sequential decision processes, which satisfy the necessary condition. | |||||||||||
| 書誌情報 |
Neural Networks 巻 24, 号 10, p. 1074-1081, 発行日 2011-12 |
|||||||||||
| 出版者 | ||||||||||||
| 出版者 | Elsevier | |||||||||||
| ISSN | ||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||
| 収録物識別子 | 08936080 | |||||||||||
| 書誌レコードID | ||||||||||||
| 収録物識別子タイプ | NCID | |||||||||||
| 収録物識別子 | AA10680676|AA11540311 | |||||||||||
| DOI | ||||||||||||
| 関連タイプ | isVersionOf | |||||||||||
| 識別子タイプ | DOI | |||||||||||
| 関連識別子 | info:doi/10.1016/j.neunet.2011.05.002 | |||||||||||
| 権利 | ||||||||||||
| 権利情報 | Copyright © 2011 Elsevier Ltd. All rights reserved|This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/ | |||||||||||
| 関連サイト | ||||||||||||
| 識別子タイプ | URI | |||||||||||
| 関連識別子 | http://www.sciencedirect.com/ | |||||||||||
| 関連名称 | http://www.sciencedirect.com/ | |||||||||||
| フォーマット | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | application/pdf | |||||||||||
| 著者版フラグ | ||||||||||||
| 出版タイプ | AM | |||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||||||||
