MADDPG: an efficient multi-agent reinforcement learning algorithm

Xinyu Song

doi:10.1117/12.2637060

15 June 2022 MADDPG: an efficient multi-agent reinforcement learning algorithm

Xinyu Song

Proceedings Volume 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022); 1228509 (2022) https://doi.org/10.1117/12.2637060
Event: International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 2022, Zhuhai, China

Abstract

Reinforcement learning has made great progress in solving single agent problems in recent years. However, the development of multi-agent reinforcement learning is much slower. Many existing algorithms perform not very well in the field of multi-agent reinforcement learning. To train a multi-agent reinforcement learning model efficiently, the MADDPG algorithm based on deep neural networks is proposed in this paper. The structure of the neural networks of MADDPG is based on the Actor-Critic framework, which contains centralized critic networks and decentralized actor networks. The result shows that the three agents in the experimental environment learn to cooperate and compete well in just 50 thousand episodes. Although the model of MADDPG algorithm has high computational complexity if the number of agents is too high, it can still perform well in a multi-agent environment.

Citation Download Citation

Xinyu Song "MADDPG: an efficient multi-agent reinforcement learning algorithm", Proc. SPIE 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 1228509 (15 June 2022); https://doi.org/10.1117/12.2637060

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Neural networks

Machine learning

Robotics

Software engineering

RELATED CONTENT

Research on manipulators controlling and planning based on transfer learning
Proceedings of SPIE (July 05 2024)

Using deep learning to detect network intrusions and malware in...
Proceedings of SPIE (May 01 2017)

Navigation and collision avoidance with human augmented supervisory training and...
Proceedings of SPIE (May 13 2019)

Learning optimal actions with imperfect images
Proceedings of SPIE (June 04 2019)

Robotic path planning using evolutionary neural network
Proceedings of SPIE (June 01 2020)

Experimental approach for the evaluation of neural network classifier algorithms
Proceedings of SPIE (September 30 2003)

Unsupervised learning for autonomous systems
Proceedings of SPIE (March 01 1992)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years