| Item type |
学術雑誌論文 / Journal Article(1) |
| 公開日 |
2023-02-28 |
| タイトル |
|
|
タイトル |
The Asymptotic Equipartition Property in Reinforcement Learning and its Relation to Return Maximization |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題 |
Reinforcement learning |
| キーワード |
|
|
主題 |
Markov decision process |
| キーワード |
|
|
主題 |
Information theory |
| キーワード |
|
|
主題 |
Asymptotic equipartition property |
| キーワード |
|
|
主題 |
Stochastic complexity |
| キーワード |
|
|
主題 |
Return maximization |
| 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
IKEDA, Kazushi
SAKAI, Hideaki
岩田, 一貴
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
We discuss an important property called the asymptotic equipartition property on empirical sequences in reinforcement learning. This states that the typical set of empirical sequences has probability nearly one, that all elements in the typical set are nearly equi-probable, and that the number of elements in the typical set is an exponential function of the sum of conditional entropies if the number of time steps is sufficiently large. The sum is referred to as stochastic complexity. Using the property we elucidate the fact that the return maximization depends on two factors, the stochastic complexity and a quantity depending on the parameters of environment. Here, the return maximization means that the best sequences in terms of expected return have probability one. We also examine the sensitivity of stochastic complexity, which is a qualitative guide in tuning the parameters of action-selection strategy, and show a sufficient condition for return maximization in probability. |
| 書誌情報 |
Neural Networks
巻 19,
号 1,
p. 62-75,
発行日 2006-01
|
| 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 |
| 権利 |
|
|
権利情報 |
Copyright © 2006 Elsevier Ltd. All rights reserved |
| 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 |
neunet06draft.pdf (233.6 kB)
