集中型マルチエージェント強化学習法の高速化

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2020/02/01

タイトル(英語): Acceleration Methods for Centralized Multiagent Reinforcement Learning

著者名: 赤羽根　拓真（京都工芸繊維大学），飯間　等（京都工芸繊維大学）

著者名(英語): Takuma Akahane (Kyoto Institute of Technology), Hitoshi Iima (Kyoto Institute of Technology)

キーワード: 機械学習，強化学習，マルチエージェント　　machine learning，reinforcement learning，multiagent

要約(英語): For multiagent environments, a centralized reinforcement learner can find optimal policies, but it is time-consuming. A method is proposed for finding the optimal policies acceleratingly. The method basically uses the centralized learner and supplementarily uses independent learners in the former phase. The independent learners transfer their learning results to the centralized learner, but excessive transfers cause the failure of learning. Therefore the independent learners should stop according to an appropriate condition. However, it is difficult for this method to find optimal policies for environments in which initial states are far from termination states. In order to find the optimal policies acceleratingly for such environments, this paper proposes multiagent reinforcement learning methods introducing new stop conditions.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.140 No.2 （2020）　特集：エネルギーデータを対象としたIoT，AI活用技術

本誌掲載ページ: 242-248 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/140/2/140_242/_article/-char/ja/