書誌事項
- タイトル別名
-
- Controlling an Autonomous Agent for Exploring Unknown Environments using Switching Prelearned Modules
- キガクシュウ モジュール ノ キリカエ ニ ヨル ミチ カンキョウ タンサク エージェント ノ コウドウ セイギョ
この論文をさがす
抄録
<p>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.</p>
収録刊行物
-
- 電気学会論文誌C(電子・情報・システム部門誌)
-
電気学会論文誌C(電子・情報・システム部門誌) 138 (2), 157-164, 2018
一般社団法人 電気学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390282679588498688
-
- NII論文ID
- 130006329300
-
- NII書誌ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL書誌ID
- 028846937
-
- 本文言語コード
- ja
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可