Coordination structures generated by deep reinforcement learning in distributed task executions

Yuki Miyashita, Toshiharu Sugawara

研究成果: Conference contribution

抄録

We investigate the coordination structures generated by deep Q-network (DQN) in a distributed task execution. Cooperation and coordination are the crucial issues in multi-agent systems, and very sophisticated design or learning is required in order to achieve effective structures or regimes of coordination. In this paper, we show the results that agents establish the division of labor in a bottom-up manner by determining their implicit responsible area when input structure for DQN is constituted by their own observation and absolute location.

本文言語English
ホスト出版物のタイトル18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
出版社International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
ページ2129-2131
ページ数3
ISBN(電子版)9781510892002
出版ステータスPublished - 2019
イベント18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 - Montreal, Canada
継続期間: 2019 5 132019 5 17

出版物シリーズ

名前Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
4
ISSN(印刷版)1548-8403
ISSN(電子版)1558-2914

Conference

Conference18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019
国/地域Canada
CityMontreal
Period19/5/1319/5/17

ASJC Scopus subject areas

  • 人工知能
  • ソフトウェア
  • 制御およびシステム工学

フィンガープリント

「Coordination structures generated by deep reinforcement learning in distributed task executions」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル