loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Zean Zhu ; Elhadji Amadou Oury Diallo and Toshiharu Sugawara

Affiliation: Department of Computer Science and Communication Engineering, Waseda University, 3-4-1 Okubo, Shinjuku-ku, Tokyo 169-8555, Japan

Keyword(s): Multi-agent System, Deep Reinforcement Learning, Coordination, Cooperation.

Abstract: 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. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.212.102.174

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Zhu, Z.; Diallo, E. and Sugawara, T. (2020). Learning Efficient Coordination Strategy for Multi-step Tasks in Multi-agent Systems using Deep Reinforcement Learning. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-395-7; ISSN 2184-433X, SciTePress, pages 287-294. DOI: 10.5220/0009160102870294

@conference{icaart20,
author={Zean Zhu. and Elhadji Amadou Oury Diallo. and Toshiharu Sugawara.},
title={Learning Efficient Coordination Strategy for Multi-step Tasks in Multi-agent Systems using Deep Reinforcement Learning},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2020},
pages={287-294},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009160102870294},
isbn={978-989-758-395-7},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - Learning Efficient Coordination Strategy for Multi-step Tasks in Multi-agent Systems using Deep Reinforcement Learning
SN - 978-989-758-395-7
IS - 2184-433X
AU - Zhu, Z.
AU - Diallo, E.
AU - Sugawara, T.
PY - 2020
SP - 287
EP - 294
DO - 10.5220/0009160102870294
PB - SciTePress