Multi-Agent Pattern Formation: A Distributed Model-Free Deep Reinforcement Learning Approach

Elhadji Amadou Oury Diallo, Toshiharu Sugawara

研究成果: Conference contribution

抄録

In this paper, we investigate how a large-scale system of independently learning agents can collectively form acceptable two-dimensional patterns (pattern formation) from any initial configuration. We propose a decentralized multi-agent deep reinforcement learning architecture MAPF-DQN (Multi-Agent Pattern Formation DQN) in which a set of independent and distributed agents capture their local visual field and learn how to act so as to collectively form target shapes. Agents exploit their individual networks with a central replay memory and target networks that are used to store and update the representation of the environment as well as learning the dynamics of the other agents. We then show that agents trained on random patterns using MAPF-DQN can organize themselves into very complex shapes in large-scale environments. Our results suggest that the proposed framework achieves zero-shot generalization on most of the environments independently of the depth of view of agents.

本文言語English
ホスト出版物のタイトル2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781728169262
DOI
出版ステータスPublished - 2020 7
イベント2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom
継続期間: 2020 7 192020 7 24

出版物シリーズ

名前Proceedings of the International Joint Conference on Neural Networks

Conference

Conference2020 International Joint Conference on Neural Networks, IJCNN 2020
CountryUnited Kingdom
CityVirtual, Glasgow
Period20/7/1920/7/24

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

フィンガープリント 「Multi-Agent Pattern Formation: A Distributed Model-Free Deep Reinforcement Learning Approach」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