Multi-Agents Reinforcement Learning: Technical Analysis and Optimization

DOI

10.2991/978-94-6463-823-3_6How to use a DOI?

Keywords

Automated Driving; Multi-agent Reinforcement Learning; Path Planning; Vehicle Dispatching; Mixed Traffic Environment

Abstract

With the advancement of autonomous driving technology and the integration of intelligent transportation systems, the need for multi-agent collaborative decision-making in complex traffic scenarios has become prominent. This report thoroughly analyzes how Multi-Agent Reinforcement Learning (MARL) technology is applied in autonomous driving systems. It looks into optimization problems for self - driving cars in different traffic situations. These situations include path planning, vehicle coordination and scheduling, traffic signal control, and inter - city strategy transfer. By combining multiple research results, this article compares the pros and cons of different MARL methods in mixed traffic settings. It also analyzes how MARL can enhance the safety, efficiency, and adaptability of autonomous driving systems in complex traffic systems that coexist with human - driven vehicles (HDVs). Studies indicate that MARL holds notable application potential in the autonomous driving sector. However, it still encounters specific challenges in scalability, human - autonomous vehicle interaction, and privacy protection.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Dayu Tao
PY  - 2025
DA  - 2025/08/31
TI  - Multi-Agents Reinforcement Learning: Technical Analysis and Optimization
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 58
EP  - 66
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_6
DO  - 10.2991/978-94-6463-823-3_6
ID  - Tao2025
ER  -