{"title":"网络游戏中数据驱动的动态干预设计","authors":"Xiupeng Chen, Nima Monshizadeh","doi":"arxiv-2409.11069","DOIUrl":null,"url":null,"abstract":"Targeted interventions in games present a challenging problem due to the\nasymmetric information available to the regulator and the agents. This note\naddresses the problem of steering the actions of self-interested agents in\nquadratic network games towards a target action profile. A common starting\npoint in the literature assumes prior knowledge of utility functions and/or\nnetwork parameters. The goal of the results presented here is to remove this\nassumption and address scenarios where such a priori knowledge is unavailable.\nTo this end, we design a data-driven dynamic intervention mechanism that relies\nsolely on historical observations of agent actions and interventions.\nAdditionally, we modify this mechanism to limit the amount of interventions,\nthereby considering budget constraints. Analytical convergence guarantees are\nprovided for both mechanisms, and a numerical case study further demonstrates\ntheir effectiveness.","PeriodicalId":501175,"journal":{"name":"arXiv - EE - Systems and Control","volume":"1 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Data-driven Dynamic Intervention Design in Network Games\",\"authors\":\"Xiupeng Chen, Nima Monshizadeh\",\"doi\":\"arxiv-2409.11069\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Targeted interventions in games present a challenging problem due to the\\nasymmetric information available to the regulator and the agents. This note\\naddresses the problem of steering the actions of self-interested agents in\\nquadratic network games towards a target action profile. A common starting\\npoint in the literature assumes prior knowledge of utility functions and/or\\nnetwork parameters. The goal of the results presented here is to remove this\\nassumption and address scenarios where such a priori knowledge is unavailable.\\nTo this end, we design a data-driven dynamic intervention mechanism that relies\\nsolely on historical observations of agent actions and interventions.\\nAdditionally, we modify this mechanism to limit the amount of interventions,\\nthereby considering budget constraints. Analytical convergence guarantees are\\nprovided for both mechanisms, and a numerical case study further demonstrates\\ntheir effectiveness.\",\"PeriodicalId\":501175,\"journal\":{\"name\":\"arXiv - EE - Systems and Control\",\"volume\":\"1 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Systems and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11069\",\"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 - EE - Systems and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11069","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Data-driven Dynamic Intervention Design in Network Games
Targeted interventions in games present a challenging problem due to the
asymmetric information available to the regulator and the agents. This note
addresses the problem of steering the actions of self-interested agents in
quadratic network games towards a target action profile. A common starting
point in the literature assumes prior knowledge of utility functions and/or
network parameters. The goal of the results presented here is to remove this
assumption and address scenarios where such a priori knowledge is unavailable.
To this end, we design a data-driven dynamic intervention mechanism that relies
solely on historical observations of agent actions and interventions.
Additionally, we modify this mechanism to limit the amount of interventions,
thereby considering budget constraints. Analytical convergence guarantees are
provided for both mechanisms, and a numerical case study further demonstrates
their effectiveness.