Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority Game

The Minority Game (MG) is a paradigmatic model in econophysics, widely used to study inductive reasoning and self-organization in multi-agent systems. Traditionally, coordinated phases in the MG are associated with spontaneous symmetry breaking, where agents differentiate into polarized roles. Recen...

Full description

Saved in:
Bibliographic Details
Main Authors: Chunqiang Shao, Wenjia Rao, Wangfang Xu, Longbao Wei
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/27/7/676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418563127869440
author Chunqiang Shao
Wenjia Rao
Wangfang Xu
Longbao Wei
author_facet Chunqiang Shao
Wenjia Rao
Wangfang Xu
Longbao Wei
author_sort Chunqiang Shao
collection DOAJ
description The Minority Game (MG) is a paradigmatic model in econophysics, widely used to study inductive reasoning and self-organization in multi-agent systems. Traditionally, coordinated phases in the MG are associated with spontaneous symmetry breaking, where agents differentiate into polarized roles. Recent work shows that policy-based reinforcement-learning can give rise to a new form of symmetric coordination—one achieved without role segregation or strategy specialization. In this study, we thoroughly analyze this novel coordination using tools from complex networks. By constructing the correlation networks among agents, we carry out a structural, functional, and temporal analysis of the emergent symmetric coordination. Our results confirm the preservation of symmetry at the collective level, and reveal a consistent and robust form of distributed coordination, demonstrating the power of network-based approaches in understanding the emergent order in adaptive multi-agent systems.
format Article
id doaj-art-afa7e25e5f214b06a496dfb4eef086ca
institution Kabale University
issn 1099-4300
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-afa7e25e5f214b06a496dfb4eef086ca2025-08-20T03:32:26ZengMDPI AGEntropy1099-43002025-06-0127767610.3390/e27070676Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority GameChunqiang Shao0Wenjia Rao1Wangfang Xu2Longbao Wei3School of Sciences, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Sciences, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Accounting, Zhejiang University of Finance and Economics, Hangzhou 310018, ChinaChina Academy for Rural Development, School of Public Affairs, Zhejiang University, Hangzhou 310058, ChinaThe Minority Game (MG) is a paradigmatic model in econophysics, widely used to study inductive reasoning and self-organization in multi-agent systems. Traditionally, coordinated phases in the MG are associated with spontaneous symmetry breaking, where agents differentiate into polarized roles. Recent work shows that policy-based reinforcement-learning can give rise to a new form of symmetric coordination—one achieved without role segregation or strategy specialization. In this study, we thoroughly analyze this novel coordination using tools from complex networks. By constructing the correlation networks among agents, we carry out a structural, functional, and temporal analysis of the emergent symmetric coordination. Our results confirm the preservation of symmetry at the collective level, and reveal a consistent and robust form of distributed coordination, demonstrating the power of network-based approaches in understanding the emergent order in adaptive multi-agent systems.https://www.mdpi.com/1099-4300/27/7/676minority gamereinforcement learningcomplex network
spellingShingle Chunqiang Shao
Wenjia Rao
Wangfang Xu
Longbao Wei
Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority Game
Entropy
minority game
reinforcement learning
complex network
title Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority Game
title_full Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority Game
title_fullStr Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority Game
title_full_unstemmed Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority Game
title_short Network Analysis on the Symmetric Coordination in a Reinforcement-Learning-Based Minority Game
title_sort network analysis on the symmetric coordination in a reinforcement learning based minority game
topic minority game
reinforcement learning
complex network
url https://www.mdpi.com/1099-4300/27/7/676
work_keys_str_mv AT chunqiangshao networkanalysisonthesymmetriccoordinationinareinforcementlearningbasedminoritygame
AT wenjiarao networkanalysisonthesymmetriccoordinationinareinforcementlearningbasedminoritygame
AT wangfangxu networkanalysisonthesymmetriccoordinationinareinforcementlearningbasedminoritygame
AT longbaowei networkanalysisonthesymmetriccoordinationinareinforcementlearningbasedminoritygame