連続値環境のためのクラシファイアシステムの開発
連続値環境のためのクラシファイアシステムの開発
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: 2019/07/01
タイトル(英語): Development of a classifier system for a continuous environment
著者名: 林田 智弘(広島大学),西崎 一郎(広島大学),関崎 真也(広島大学),小笠原 祐輝(広島大学)
著者名(英語): Tomohiro Hayashida (Hiroshima University), Ichiro Nishizaki (Hiroshima University), Shinya Sekizaki (Hiroshima University), Yuki Ogasawara (Hiroshima University)
キーワード: 機械学習,ニューラルネットワーク,クラシファイアシステム,連続値環境 machine learning,neural networks,classifier system,continuous value environment
要約(英語): A learning classifier system is an adaptive system that obtains a set of appropriate action rules that adapts to multi-step problems by training action rules defined in if-then form by trial and error process, in a similar framework as reinforcement learning. Because of that the input signals of the classifier system are encoded into binary values, bit strings are often lengthened when dealing with such a problem that the state of the environment continuously changes. A neural network can treat with real values as input signal, however, it cannot be applied to multi-step problems. This paper proposes a system that responds to problems such that the state of the environment continuously changes by combining a neural network and a classifier system, and actions are selected from multiple options, so that output can be defined as discrete values. In order to verify the effectiveness of the proposed system, this paper conducts several numerical experiments using benchmarks corresponding to muti-step problems defined by continuous values.
本誌: 電気学会論文誌C(電子・情報・システム部門誌) Vol.139 No.7 (2019) 特集:平成30年電子・情報・システム部門大会
本誌掲載ページ: 835-842 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/139/7/139_835/_article/-char/ja/
受取状況を読み込めませんでした
