Coordinated behavior of cooperative agents using deep reinforcement learning

Elhadji Amadou Oury Diallo, Ayumi Sugiyama, Toshiharu Sugawara

研究成果: Article

抄録

In this work, we focus on an environment where multiple agents with complementary capabilities cooperate to generate non-conflicting joint actions that achieve a specific target. The central problem addressed is how several agents can collectively learn to coordinate their actions such that they complete a given task together without conflicts. However, sequential decision-making under uncertainty is one of the most challenging issues for intelligent cooperative systems. To address this, we propose a multi-agent concurrent framework where agents learn coordinated behaviors in order to divide their areas of responsibility. The proposed framework is an extension of some recent deep reinforcement learning algorithms such as DQN, double DQN, and dueling network architectures. Then, we investigate how the learned behaviors change according to the dynamics of the environment, reward scheme, and network structures. Next, we show how agents behave and choose their actions such that the resulting joint actions are optimal. We finally show that our method can lead to stable solutions in our specific environment.

元の言語English
ジャーナルNeurocomputing
DOI
出版物ステータスPublished - 2019 1 1

Fingerprint

Reinforcement learning
Cooperative Behavior
Learning
Network architecture
Reward
Learning algorithms
Uncertainty
Decision Making
Decision making
Reinforcement (Psychology)

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

これを引用

Coordinated behavior of cooperative agents using deep reinforcement learning. / Diallo, Elhadji Amadou Oury; Sugiyama, Ayumi; Sugawara, Toshiharu.

:: Neurocomputing, 01.01.2019.

研究成果: Article

@article{1549941ded604a7180c1f581a98968d6,
title = "Coordinated behavior of cooperative agents using deep reinforcement learning",
abstract = "In this work, we focus on an environment where multiple agents with complementary capabilities cooperate to generate non-conflicting joint actions that achieve a specific target. The central problem addressed is how several agents can collectively learn to coordinate their actions such that they complete a given task together without conflicts. However, sequential decision-making under uncertainty is one of the most challenging issues for intelligent cooperative systems. To address this, we propose a multi-agent concurrent framework where agents learn coordinated behaviors in order to divide their areas of responsibility. The proposed framework is an extension of some recent deep reinforcement learning algorithms such as DQN, double DQN, and dueling network architectures. Then, we investigate how the learned behaviors change according to the dynamics of the environment, reward scheme, and network structures. Next, we show how agents behave and choose their actions such that the resulting joint actions are optimal. We finally show that our method can lead to stable solutions in our specific environment.",
keywords = "Cooperation, Coordination, Deep reinforcement learning, Multi-agent systems",
author = "Diallo, {Elhadji Amadou Oury} and Ayumi Sugiyama and Toshiharu Sugawara",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.neucom.2018.08.094",
language = "English",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - Coordinated behavior of cooperative agents using deep reinforcement learning

AU - Diallo, Elhadji Amadou Oury

AU - Sugiyama, Ayumi

AU - Sugawara, Toshiharu

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this work, we focus on an environment where multiple agents with complementary capabilities cooperate to generate non-conflicting joint actions that achieve a specific target. The central problem addressed is how several agents can collectively learn to coordinate their actions such that they complete a given task together without conflicts. However, sequential decision-making under uncertainty is one of the most challenging issues for intelligent cooperative systems. To address this, we propose a multi-agent concurrent framework where agents learn coordinated behaviors in order to divide their areas of responsibility. The proposed framework is an extension of some recent deep reinforcement learning algorithms such as DQN, double DQN, and dueling network architectures. Then, we investigate how the learned behaviors change according to the dynamics of the environment, reward scheme, and network structures. Next, we show how agents behave and choose their actions such that the resulting joint actions are optimal. We finally show that our method can lead to stable solutions in our specific environment.

AB - In this work, we focus on an environment where multiple agents with complementary capabilities cooperate to generate non-conflicting joint actions that achieve a specific target. The central problem addressed is how several agents can collectively learn to coordinate their actions such that they complete a given task together without conflicts. However, sequential decision-making under uncertainty is one of the most challenging issues for intelligent cooperative systems. To address this, we propose a multi-agent concurrent framework where agents learn coordinated behaviors in order to divide their areas of responsibility. The proposed framework is an extension of some recent deep reinforcement learning algorithms such as DQN, double DQN, and dueling network architectures. Then, we investigate how the learned behaviors change according to the dynamics of the environment, reward scheme, and network structures. Next, we show how agents behave and choose their actions such that the resulting joint actions are optimal. We finally show that our method can lead to stable solutions in our specific environment.

KW - Cooperation

KW - Coordination

KW - Deep reinforcement learning

KW - Multi-agent systems

UR - http://www.scopus.com/inward/record.url?scp=85065027331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065027331&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2018.08.094

DO - 10.1016/j.neucom.2018.08.094

M3 - Article

AN - SCOPUS:85065027331

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -