Distributed Multi-Agent Deep Reinforcement Learning for Robust Coordination against Noise

Yoshinari Motokawa, Toshiharu Sugawara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In multi-agent systems, noise reduction techniques are considerable for improving the overall system reliability as agents are required to rely on limited environmental information to develop cooperative and coordinated behaviors with the surrounding agents. However, previous studies have often applied centralized noise reduction methods to build robust and versatile coordination in noisy multi-agent environments, while distributed and decentralized autonomous agents are more plausible for real-world application. In this paper, we introduce a distributed attentional actor architecture model for a multi-agent system (DA3-X), using which we demonstrate that agents with DA3-X can selectively learn the noisy environment and behave cooperatively. We experimentally evaluate the effectiveness of DA3-X by comparing learning methods with and without DA3-X and show that agents with DA3-X can achieve better performance than baseline agents. Furthermore, we visualize heatmaps of attentional weights from the DA3-X to analyze how the decision-making process and coordinated behavior are influenced by noise.

Original languageEnglish
Title of host publication2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728186719
DOIs
Publication statusPublished - 2022
Event2022 International Joint Conference on Neural Networks, IJCNN 2022 - Padua, Italy
Duration: 2022 Jul 182022 Jul 23

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2022-July

Conference

Conference2022 International Joint Conference on Neural Networks, IJCNN 2022
Country/TerritoryItaly
CityPadua
Period22/7/1822/7/23

Keywords

  • Alter-exploration problem
  • Attention mechanism
  • Cooperation
  • Coordination
  • Distributed system
  • Multi-agent deep reinforcement learning
  • Noise reduction

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Distributed Multi-Agent Deep Reinforcement Learning for Robust Coordination against Noise'. Together they form a unique fingerprint.

Cite this