{"title":"优化和学习纳什均衡的一般框架","authors":"Di Zhang, Wei Gu, Qing Jin","doi":"arxiv-2408.16260","DOIUrl":null,"url":null,"abstract":"One key in real-life Nash equilibrium applications is to calibrate players'\ncost functions. To leverage the approximation ability of neural networks, we\nproposed a general framework for optimizing and learning Nash equilibrium using\nneural networks to estimate players' cost functions. Depending on the\navailability of data, we propose two approaches (a) the two-stage approach: we\nneed the data pair of players' strategy and relevant function value to first\nlearn the players' cost functions by monotonic neural networks or graph neural\nnetworks, and then solve the Nash equilibrium with the learned neural networks;\n(b) the joint approach: we use the data of partial true observation of the\nequilibrium and contextual information (e.g., weather) to optimize and learn\nNash equilibrium simultaneously. The problem is formulated as an optimization\nproblem with equilibrium constraints and solved using a modified\nBackpropagation Algorithm. The proposed methods are validated in numerical\nexperiments.","PeriodicalId":501273,"journal":{"name":"arXiv - ECON - General Economics","volume":"76 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A General Framework for Optimizing and Learning Nash Equilibrium\",\"authors\":\"Di Zhang, Wei Gu, Qing Jin\",\"doi\":\"arxiv-2408.16260\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"One key in real-life Nash equilibrium applications is to calibrate players'\\ncost functions. To leverage the approximation ability of neural networks, we\\nproposed a general framework for optimizing and learning Nash equilibrium using\\nneural networks to estimate players' cost functions. Depending on the\\navailability of data, we propose two approaches (a) the two-stage approach: we\\nneed the data pair of players' strategy and relevant function value to first\\nlearn the players' cost functions by monotonic neural networks or graph neural\\nnetworks, and then solve the Nash equilibrium with the learned neural networks;\\n(b) the joint approach: we use the data of partial true observation of the\\nequilibrium and contextual information (e.g., weather) to optimize and learn\\nNash equilibrium simultaneously. The problem is formulated as an optimization\\nproblem with equilibrium constraints and solved using a modified\\nBackpropagation Algorithm. The proposed methods are validated in numerical\\nexperiments.\",\"PeriodicalId\":501273,\"journal\":{\"name\":\"arXiv - ECON - General Economics\",\"volume\":\"76 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - ECON - General Economics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.16260\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - ECON - General Economics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.16260","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A General Framework for Optimizing and Learning Nash Equilibrium
One key in real-life Nash equilibrium applications is to calibrate players'
cost functions. To leverage the approximation ability of neural networks, we
proposed a general framework for optimizing and learning Nash equilibrium using
neural networks to estimate players' cost functions. Depending on the
availability of data, we propose two approaches (a) the two-stage approach: we
need the data pair of players' strategy and relevant function value to first
learn the players' cost functions by monotonic neural networks or graph neural
networks, and then solve the Nash equilibrium with the learned neural networks;
(b) the joint approach: we use the data of partial true observation of the
equilibrium and contextual information (e.g., weather) to optimize and learn
Nash equilibrium simultaneously. The problem is formulated as an optimization
problem with equilibrium constraints and solved using a modified
Backpropagation Algorithm. The proposed methods are validated in numerical
experiments.