Reinforcement learning meets minority game: Toward optimal resource allocation
文献类型：期刊论文
| 作者 | Zhang, SP; Dong, JQ; Liu, L1; Huang, ZG; Huang, L4; Lai, YC |
| 刊名 | PHYSICAL REVIEW E
 |
| 出版日期 | 2019 |
| 卷号 | 99期号:3页码:32302 |
| 关键词 | HERD BEHAVIOR PINNING CONTROL NETWORKS MARKET ORGANIZATION COOPERATION MEMORY MODEL |
| ISSN号 | 2470-0045 |
| DOI | 10.1103/PhysRevE.99.032302 |
| 英文摘要 | The main point of this paper is to provide an affirmative answer through exploiting reinforcement learning (RL) in artificial intelligence (AI) for eliminating herding without any external control in complex resource allocation systems. In particular, we demonstrate that when agents are empowered with RL (e.g., the popular Q-learning algorithm in AI) in that they get familiar with the unknown game environment gradually and attempt to deliver the optimal actions to maximize the payoff, herding can effectively be eliminated. Furthermore, computations reveal the striking phenomenon that, regardless of the initial state, the system evolves persistently and relentlessly toward the optimal state in which all resources are used efficiently. However, the evolution process is not without interruptions: there are large fluctuations that occur but only intermittently in time. The statistical distribution of the time between two successive fluctuating events is found to depend on the parity of the evolution, i.e., whether the number of time steps in between is odd or even. We develop a physical analysis and derive mean-field equations to gain an understanding of these phenomena. Since AI is becoming increasingly widespread, we expect our RL empowered minority game system to have broad applications. |
| 学科主题 | Physics |
| 语种 | 英语 |
| 源URL | [http://ir.itp.ac.cn/handle/311006/23468]  |
| 专题 | 理论物理研究所_理论物理所1978-2010年知识产出 |
| 作者单位 | 1.Chinese Acad Sci, Key Lab Theoret Phys, Inst Theoret Phys, POB 2735, Beijing 100190, Peoples R China 2.Arizona State Univ, Dept Phys, Sch Elect Comp & Energy Engn, Tempe, AZ 85287 USA 3.Xi An Jiao Tong Univ, Key Lab Biomed Informat Engn, Minist Educ,Sch Life Sci & Technol, Key Lab Neuroinformat & Rehabil Engn,Minist Civil, Xian 710049, Shaanxi, Peoples R China 4.Xi An Jiao Tong Univ, Sch Life Sci & Technol, Inst Hlth & Rehabil Sci, Xian 710049, Shaanxi, Peoples R China 5.Lanzhou Univ, Inst Computat Phys & Complex Syst, Lanzhou 730000, Gansu, Peoples R China 6.Chongqing Univ, Sch Software Engn, Chongqing 400044, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, SP,Dong, JQ,Liu, L,et al. Reinforcement learning meets minority game: Toward optimal resource allocation[J]. PHYSICAL REVIEW E,2019,99(3):32302. |
| APA | Zhang, SP,Dong, JQ,Liu, L,Huang, ZG,Huang, L,&Lai, YC.(2019).Reinforcement learning meets minority game: Toward optimal resource allocation.PHYSICAL REVIEW E,99(3),32302. |
| MLA | Zhang, SP,et al."Reinforcement learning meets minority game: Toward optimal resource allocation".PHYSICAL REVIEW E 99.3(2019):32302. |
入库方式： OAI收割
来源：理论物理研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。