IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v14y2021i1p17-d714777.html
   My bibliography  Save this article

The Important Role of Global State for Multi-Agent Reinforcement Learning

Author

Listed:
  • Shuailong Li

    (State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
    Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
    University of Chinese Academy of Sciences, Beijing 100049, China)

  • Wei Zhang

    (State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
    University of Chinese Academy of Sciences, Beijing 100049, China)

  • Yuquan Leng

    (Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China
    Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China)

  • Xiaohui Wang

    (State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
    Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
    University of Chinese Academy of Sciences, Beijing 100049, China)

Abstract

Environmental information plays an important role in deep reinforcement learning (DRL). However, many algorithms do not pay much attention to environmental information. In multi-agent reinforcement learning decision-making, because agents need to make decisions combined with the information of other agents in the environment, this makes the environmental information more important. To prove the importance of environmental information, we added environmental information to the algorithm. We evaluated many algorithms on a challenging set of StarCraft II micromanagement tasks. Compared with the original algorithm, the standard deviation (except for the VDN algorithm) was smaller than that of the original algorithm, which shows that our algorithm has better stability. The average score of our algorithm was higher than that of the original algorithm (except for VDN and COMA), which shows that our work significantly outperforms existing multi-agent RL methods.

Suggested Citation

  • Shuailong Li & Wei Zhang & Yuquan Leng & Xiaohui Wang, 2021. "The Important Role of Global State for Multi-Agent Reinforcement Learning," Future Internet, MDPI, vol. 14(1), pages 1-9, December.
    • Handle: RePEc:gam:jftint:v:14:y:2021:i:1:p:17-:d:714777
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/14/1/17/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1999-5903/14/1/17/
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jftint:v:14:y:2021:i:1:p:17-:d:714777. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.