Multi-Agent Pattern Formation with Deep Reinforcement Learning

Elhadji Amadou Oury Diallo, Toshiharu Sugawara

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

We propose a decentralized multi-agent deep reinforcement learning architecture to investigate pattern formation under the local information provided by the agents' sensors. It consists of tasking a large number of homogeneous agents to move to a set of specified goal locations, addressing both the assignment and trajectory planning sub-problems concurrently. We then show that agents trained on random patterns can organize themselves into very complex shapes.

本文言語English
ホスト出版物のタイトルAAAI 2020 - 34th AAAI Conference on Artificial Intelligence
出版社AAAI Press
ページ13779-13780
ページ数2
ISBN(電子版)9781577358350
出版ステータスPublished - 2020
イベント34th AAAI Conference on Artificial Intelligence, AAAI 2020 - New York, United States
継続期間: 2020 2 72020 2 12

出版物シリーズ

名前AAAI 2020 - 34th AAAI Conference on Artificial Intelligence

Conference

Conference34th AAAI Conference on Artificial Intelligence, AAAI 2020
国/地域United States
CityNew York
Period20/2/720/2/12

ASJC Scopus subject areas

  • 人工知能

フィンガープリント

「Multi-Agent Pattern Formation with Deep Reinforcement Learning」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