WEKO3
アイテム
Properties of the Optimality Equation and Optimal Policies in Discrete Time Markov Decision Processes and Their Applications
https://doi.org/10.14990/00000060
https://doi.org/10.14990/0000006083fa040f-0e32-410f-811e-02ada1360d19
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
K00024 (569.8 kB)
|
|
| Item type | 紀要論文 / Departmental Bulletin Paper(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2015-03-24 | |||||
| タイトル | ||||||
| タイトル | Properties of the Optimality Equation and Optimal Policies in Discrete Time Markov Decision Processes and Their Applications | |||||
| タイトル | ||||||
| タイトル | Properties of the Optimality Equation and Optimal Policies in Discrete Time Markov Decision Processes and Their Applications | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | jpn | |||||
| キーワード | ||||||
| 主題 | Discrete time | |||||
| キーワード | ||||||
| 主題 | Markov decision processes | |||||
| キーワード | ||||||
| 主題 | Optimality equation | |||||
| キーワード | ||||||
| 主題 | Optimal policies | |||||
| キーワード | ||||||
| 主題 | Expected discounted total rewards | |||||
| キーワード | ||||||
| 主題 | Control system | |||||
| キーワード | ||||||
| 主題 | Discrete time | |||||
| キーワード | ||||||
| 主題 | Markov decision processes | |||||
| キーワード | ||||||
| 主題 | Optimality equation | |||||
| キーワード | ||||||
| 主題 | Optimal policies | |||||
| キーワード | ||||||
| 主題 | Expected discounted total rewards | |||||
| キーワード | ||||||
| 主題 | Control system | |||||
| 資源タイプ | ||||||
| 資源タイプ | departmental bulletin paper | |||||
| ID登録 | ||||||
| ID登録 | 10.14990/00000060 | |||||
| ID登録タイプ | JaLC | |||||
| 著者 |
Hu, Qiying
× Hu, Qiying× 岳, 五一× Hu, Qiying |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | This paper investigates properties of the optimaiity equation and optimal policies in discrete time Markov decision processes with expected discounted total rewards. Under conditions where the model is well defined and the optimaiity equation is true, it is shown that as a solution of the optimaiity equation, the solution called optimal value function is always the smallest one, and is also the unique one under another weak condition. Moreover, a structure of optimal policies is discussed. Finally, these properties are applied to state feedback control of discrete event systems with a numerical example. | |||||
| 書誌情報 |
甲南大学紀要. 理工学編 en : Memoirs of Konan University. Science and engineering series 巻 50, 号 1, p. 49-60, 発行日 2003-07-31 |
|||||
| 出版者 | ||||||
| 出版者 | 甲南大学 | |||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 13480383 | |||||
| 書誌レコードID | ||||||
| 収録物識別子タイプ | NCID | |||||
| 収録物識別子 | AA11561231 | |||||
| 論文ID（NAID） | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | 110000039562 | |||||
| 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 | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
