失敗確率伝播アルゴリズムEFPAの提案とマルチエージェント環境下での有効性の検証

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: 2016/03/01

タイトル(英語): Proposal of a Propagation Algorithm of the Expected Failure Probability and the Effectiveness on Multi-agent Environments

著者名: 村岡　宏紀（日野自動車(株) エンジン設計部），宮崎　和光（独立行政法人大学評価・学位授与機構研究開発部），小林　博明（明治大学大学院理工学研究科）

著者名(英語): Hiroki Muraoka (Engine Engineering Div., Hino Motors, Ltd.), Kazuteru Miyazaki (Research Department, National Institution for Academic Degrees and University Evaluation), Hiroaki Kobayashi (Department of Mechanical Engineering Informatics, Meiji University)

キーワード: 経験強化型学習，強化学習，マルチエージェント学習，同時学習問題　　Exploitaion-oritented Learning，Reinforcement Learning，Multi-agent learning，concurrent leraning problem

要約(英語): It is known that Improved Penalty Avoiding Rational Policy Making algorithm (IPARP) can learn policies by a reward and a penalty. IPARP aims to identify penalty rules that have a high possibility to receive a penalty. Though IPARP is effective in many cases, it needs many trial-and-error searches due to memory constraints. In this paper, we propose a method called Expected Failure Probability Algorithm (EFPA) to speed it up. In addition, we extend EFPA to multi-agent environments. In multi-agent learning, it is important to avoid concurrent learning problem that occurs when multiple agents learn simultaneously. We also propose a method to avoid the problem and confirm the effectiveness by numerical experiments.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.136 No.3 （2016） 特集：機械学習が拓くシステムイノベーション

本誌掲載ページ: 273-281 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/136/3/136_273/_article/-char/ja/