Self organizing optimization and phase transition in reinforcement learning minority game system
作者机构：Key Laboratory of Biomedical Information Engineering of Ministry of EducationKey Laboratory of Neuro-informatics&Rehabilitation Engineering of Ministry of Civil Affairsand Institute of Health and Rehabilitation ScienceSchool of Life Science and TechnologyXi’an Jiaotong UniversityXi’an 710049China Lanzhou Center for Theoretical Physics and Key Laboratory of Theoretical Physics of Gansu ProvinceLanzhou UniversityLanzhou 730000China
出 版 物：《Frontiers of physics》 (物理学前沿（英文版）)
年 卷 期：2024年第19卷第4期
页 面：297-309页
核心收录：
学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：This work was supported by the National Natural Science Foundation of China(Grant No.12105213) China Postdoctoral Science Foundation(No.2020M673363) the Natural Science Basic Research Program of Shaanxi(No.2021JQ-007)
主 题：oscillatory evolution collective behaviors phase transition reinforcement learning minority game
摘 要：Whether the complex game system composed of a large number of artificial intelligence(AI)agents empowered with reinforcement learning can produce extremely favorable collective behaviors just through the way of agent self-exploration is a matter of practical *** this paper,we address this question by combining the typical theoretical model of resource allocation system,the minority game model,with reinforcement *** individual participating in the game is set to have a certain degree of intelligence based on reinforcement learning *** particular,we demonstrate that as AI agents gradually becomes familiar with the unknown environment and tries to provide optimal actions to maximize payoff,the whole system continues to approach the optimal state under certain parameter combinations,herding is effectively suppressed by an oscillating collective behavior which is a self-organizing pattern without any external *** interesting phenomenon is that a first-order phase transition is revealed based on some numerical results in our multi-agents system with reinforcement *** order to further understand the dynamic behavior of agent learning,we define and analyze the conversion path of belief mode,and find that the self-organizing condensation of belief modes appeared for the given trial and error rates in the AI ***,we provide a detection method for period-two oscillation collective pattern emergence based on the Kullback–Leibler divergence and give the parameter position where the period-two appears.
维普期刊数据库