Learning Efficient Coordination Strategy for Multi-step Tasks in Multi-agent Systems using Deep Reinforcement Learning

Zean Zhu, Elhadji Amadou Oury Diallo, Toshiharu Sugawara

研究成果

抄録

We investigated whether a group of agents could learn the strategic policy with different sizes of input by deep Q-learning in a simulated takeout platform environment. Agents are often required to cooperate and/or coordinate with each other to achieve their goals, but making appropriate sequential decisions for coordinated behaviors based on dynamic and complex states is one of the challenging issues for the study of multi-agent systems. Although it is already investigated that intelligent agents could learn the coordinated strategies using deep Q-learning to efficiently execute simple one-step tasks, they are also expected to generate a certain coordination regime for more complex tasks, such as multi-step coordinated ones, in dynamic environments. To solve this problem, we introduced the deep reinforcement learning framework with two kinds of distributions of the neural networks, centralized and decentralized deep Q-networks (DQNs). We examined and compared the performances using these two DQN network distributions with various sizes of the agents’ views. The experimental results showed that these networks could learn coordinated policies to manage agents by using local view inputs, and thus, could improve their entire performance. However, we also showed that their behaviors of multiple agents seemed quite different depending on the network distributions.

本文言語English
ホスト出版物のタイトルICAART 2020 - Proceedings of the 12th International Conference on Agents and Artificial Intelligence
編集者Ana Rocha, Luc Steels, Jaap van den Herik
出版社SciTePress
ページ287-294
ページ数8
ISBN(電子版)9789897583957
出版ステータスPublished - 2020
イベント12th International Conference on Agents and Artificial Intelligence, ICAART 2020 - Valletta, Malta
継続期間: 2020 2 222020 2 24

出版物シリーズ

名前ICAART 2020 - Proceedings of the 12th International Conference on Agents and Artificial Intelligence
1

Conference

Conference12th International Conference on Agents and Artificial Intelligence, ICAART 2020
国/地域Malta
CityValletta
Period20/2/2220/2/24

ASJC Scopus subject areas

  • 人工知能
  • ソフトウェア

フィンガープリント

「Learning Efficient Coordination Strategy for Multi-step Tasks in Multi-agent Systems using 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