Co-evolution of synchronization and cooperation with multi-agent Q-learning

被引：5

作者：

Zhu, Peican ^{[1
]}

Cao, Zhaoheng ^{[2
]}

Liu, Chen ^{[3
]}

Chu, Chen ^{[4
]}

Wang, Zhen ^{[5
]}

机构：

[1] Northwestern Polytech Univ, Sch Artificial Intelligence Opt & Elect iOPEN, Xian 710072, Peoples R China

[2] Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Peoples R China

[3] Northwestern Polytech Univ, Sch Ecol & Environm, Xian 710072, Peoples R China

[4] Yunnan Univ Finance & Econ, Sch Stat & Math, Kunming 650221, Peoples R China

[5] Northwestern Polytech Univ, Sch Cybersecur, Xian 710072, Peoples R China

来源：

CHAOS | 2023年 / 33卷 / 03期

基金：

中国国家自然科学基金;

关键词：

DILEMMA; REPUTATION; EVOLUTION; KURAMOTO; STRATEGY;

D O I：

10.1063/5.0141824

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

Cooperation is a widespread phenomenon in human society and plays a significant role in achieving synchronization of various systems. However, there has been limited progress in studying the co-evolution of synchronization and cooperation. In this manuscript, we investigate how reinforcement learning affects the evolution of synchronization and cooperation. Namely, the payoff of an agent depends not only on the cooperation dynamic but also on the synchronization dynamic. Agents have the option to either cooperate or defect. While cooperation promotes synchronization among agents, defection does not. We report that the dynamic feature, which indicates the action switching frequency of the agent during interactions, promotes synchronization. We also find that cooperation and synchronization are mutually reinforcing. Furthermore, we thoroughly analyze the potential reasons for synchronization promotion due to the dynamic feature from both macro- and microperspectives. Additionally, we conduct experiments to illustrate the differences in the synchronization-promoting effects of cooperation and dynamic features.

引用

页数：8

共 50 条

[31] Multi-Agent Q-Learning with Joint State Value Approximation
Chen Gang
Cao Weihua
Chen Xin
Wu Min
[J]. 2011 30TH CHINESE CONTROL CONFERENCE (CCC), 2011, : 4878 - 4882
[32] Extending Q-Learning to general adaptive multi-agent systems
Tesauro, G
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 16, 2004, 16 : 871 - 878
[33] Continuous strategy replicator dynamics for multi-agent Q-learning
Galstyan, Aram
[J]. AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2013, 26 (01) : 37 - 53
[34] Minimax fuzzy Q-learning in cooperative multi-agent systems
Kilic, A
Arslan, A
[J]. ADVANCES IN INFORMATION SYSTEMS, 2002, 2457 : 264 - 272
[35] Continuous strategy replicator dynamics for multi-agent Q-learning
Aram Galstyan
[J]. Autonomous Agents and Multi-Agent Systems, 2013, 26 : 37 - 53
[36] A theoretical analysis of cooperative behaviorin multi-agent Q-learning
Waltman, Ludo
Kaymak, Uzay
[J]. 2007 IEEE INTERNATIONAL SYMPOSIUM ON APPROXIMATE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING, 2007, : 84 - +
[37] Multi-Agent Q-Learning for Power Allocation in Interference Channel
Wongphatcharatham, Tanutsorn
Phakphisut, Watid
Wijitpornchai, Thongchai
Areeprayoonkij, Poonlarp
Jaruvitayakovit, Tanun
Hannanta-Anan, Pimkhuan
[J]. 2022 37TH INTERNATIONAL TECHNICAL CONFERENCE ON CIRCUITS/SYSTEMS, COMPUTERS AND COMMUNICATIONS (ITC-CSCC 2022), 2022, : 876 - 879
[38] Multi-Agent Reward-Iteration Fuzzy Q-Learning
Lixiong Leng
Jingchen Li
Jinhui Zhu
Kao-Shing Hwang
Haobin Shi
[J]. International Journal of Fuzzy Systems, 2021, 23 : 1669 - 1679
[39] A distributed Q-learning algorithm for multi-agent team coordination
Huang, J
Yang, B
Liu, DY
[J]. Proceedings of 2005 International Conference on Machine Learning and Cybernetics, Vols 1-9, 2005, : 108 - 113
[40] Modular Production Control with Multi-Agent Deep Q-Learning
Gankin, Dennis
Mayer, Sebastian
Zinn, Jonas
Vogel-Heuser, Birgit
Endisch, Christian
[J]. 2021 26TH IEEE INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGIES AND FACTORY AUTOMATION (ETFA), 2021,

← 1 2 3 4 5 →