既学習モジュールの切替による未知環境探索エージェントの行動制御

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: 2018/02/01

タイトル(英語): Controlling an Autonomous Agent for Exploring Unknown Environments using Switching Prelearned Modules

著者名: 畠　崇人（横浜国立大学大学院環境情報学府），菅沼　雅徳（横浜国立大学大学院環境情報学府），長尾　智晴（横浜国立大学大学院環境情報学府）

著者名(英語): Takahito Hata (Graduate School of Environment and Information Sciences, Yokohama National University), Masanori Suganuma (Graduate School of Environment and Information Sciences, Yokohama National University), Tomoharu Nagao (Graduate School of Environmen

キーワード: 自律エージェント，モジュール化，汎用化，自動プログラミング，遺伝的プログラミング　　autonomous agent，modulalization，generalization，automatic programming，genetic programming

要約(英語): In this paper, we try to acquire various behavior patterns of autonomous exploration agent using several learning environments. In case of previous learning methods using a single behavior rule set, it is hard to acquire the behavior that covers all learning environments. In our method, we divide learning environments into some primitive environments whose properties differ each other, and then generate modules that are specialized for each primitive environment. To optimize behavior rules of agents, we adopt Graph Structured Program Evolution (GRAPE) which can automatically generates graph structured programs. In unknown environments, each module is switched by a program named “switcher”. The switcher selects the module that acts better in a neighboring environment. Through several experiments, our method achieved higher exploration rate in unknown environments compared to simple GRAPE, random search, and the method that switches modules randomly.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.138 No.2 （2018） 特集：電磁波応用を加速するための高周波回路・計測・システム技術

本誌掲載ページ: 157-164 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/138/2/138_157/_article/-char/ja/