| Self organizing optimization and phase transition in reinforcement learning minority game system | |
| Zhang, Si-Ping1,2; Dong, Jia-Qi3,4; Zhang, Hui-Yu1,2; Lu, Yi-Xuan1,2; Wang, Jue1,2; Huang, Zi-Gang1,2 | |
| 2024-08 | |
| Source Publication | Frontiers of Physics Impact Factor & Quartile Of Published Year The Latest Impact Factor & Quartile |
| ISSN | 2095-0462 |
| EISSN | 2095-0470 |
| Volume | 19Issue:4 |
| page numbers | 13 |
| Abstract | 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 importance. In this paper, we address this question by combining the typical theoretical model of resource allocation system, the minority game model, with reinforcement learning. Each individual participating in the game is set to have a certain degree of intelligence based on reinforcement learning algorithm. In 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 interference. An interesting phenomenon is that a first-order phase transition is revealed based on some numerical results in our multi-agents system with reinforcement learning. In 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 system. Finally, 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. |
| Keyword | oscillatory evolution collective behaviors phase transition reinforcement learning minority game |
| Publisher | HIGHER EDUCATION PRESS |
| DOI | 10.1007/s11467-023-1378-z |
| Indexed By | SCIE |
| Language | 英语 |
| WOS Research Area | Physics |
| WOS Subject | Physics, Multidisciplinary |
| WOS ID | WOS:001148312900004 |
| Original Document Type | Article |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | https://ir.lzu.edu.cn/handle/262010/583469 |
| Collection | 兰州大学 物理科学与技术学院 |
| Affiliation | 1.Xi An Jiao Tong Univ, Key Lab Biomed Informat Engn, Key Lab Neuroinformat & Rehabil Engn, Minist Educ,Minist Civil Affairs, Xian 710049, Peoples R China; 2.Xi An Jiao Tong Univ, Inst Hlth & Rehabil Sci, Sch Life Sci & Technol, Xian 710049, Peoples R China; 3.Lanzhou Univ, Lanzhou Ctr Theoret Phys, Lanzhou 730000, Peoples R China; 4.Lanzhou Univ, Key Lab Theoret Phys Gansu Prov, Lanzhou 730000, Peoples R China |
| Recommended Citation GB/T 7714 | Zhang, Si-Ping,Dong, Jia-Qi,Zhang, Hui-Yu,et al. Self organizing optimization and phase transition in reinforcement learning minority game system[J]. Frontiers of Physics,2024,19(4). |
| APA | Zhang, Si-Ping,Dong, Jia-Qi,Zhang, Hui-Yu,Lu, Yi-Xuan,Wang, Jue,&Huang, Zi-Gang.(2024).Self organizing optimization and phase transition in reinforcement learning minority game system.Frontiers of Physics,19(4). |
| MLA | Zhang, Si-Ping,et al."Self organizing optimization and phase transition in reinforcement learning minority game system".Frontiers of Physics 19.4(2024). |
| Files in This Item: | There are no files associated with this item. | ||||
