Acceleration of reinforcement learning with incomplete prior information

Kento Terashima, Hirotaka Takano, Junichi Murata

研究成果: Contribution to journalArticle査読

5 被引用数 (Scopus)

抄録

Reinforcement learning is applicable to complex or unknown problems because the solution search process is done by trial-and-error. However, the calculation time for the trial-and-error search becomes larger as the scale of the problem increases. Therefore, in order to decrease calculation time, some methods have been proposed using the prior information on the problem. This paper improves a previously proposed method utilizing options as prior information. In order to increase the learning speed even with wrong options, methods for option correction by forgetting the policy and extending initiation sets are proposed.

本文言語英語
ページ(範囲)721-730
ページ数10
ジャーナルJournal of Advanced Computational Intelligence and Intelligent Informatics
17
5
DOI
出版ステータス出版済み - 1 1 2013

All Science Journal Classification (ASJC) codes

  • 人間とコンピュータの相互作用
  • コンピュータ ビジョンおよびパターン認識
  • 人工知能

フィンガープリント

「Acceleration of reinforcement learning with incomplete prior information」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル