Marco A. Wiering, J. Vreeken, J. V. Veenen, A. Koopman
{"title":"城市交通的模拟与优化","authors":"Marco A. Wiering, J. Vreeken, J. V. Veenen, A. Koopman","doi":"10.1109/IVS.2004.1336426","DOIUrl":null,"url":null,"abstract":"Optimal traffic light control is a multi-agent decision problem, for which we propose to use reinforcement learning algorithms. Our algorithm learns the expected waiting times of cars for red and green lights at each intersection, and sets the traffic lights to green for the configuration maximizing individual car gains. For testing our adaptive traffic light controllers, we developed the green light district simulator. The experimental results show that the adaptive algorithms can strongly reduce average waiting times of cars compared to three hand-designed controllers.","PeriodicalId":296386,"journal":{"name":"IEEE Intelligent Vehicles Symposium, 2004","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"159","resultStr":"{\"title\":\"Simulation and optimization of traffic in a city\",\"authors\":\"Marco A. Wiering, J. Vreeken, J. V. Veenen, A. Koopman\",\"doi\":\"10.1109/IVS.2004.1336426\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Optimal traffic light control is a multi-agent decision problem, for which we propose to use reinforcement learning algorithms. Our algorithm learns the expected waiting times of cars for red and green lights at each intersection, and sets the traffic lights to green for the configuration maximizing individual car gains. For testing our adaptive traffic light controllers, we developed the green light district simulator. The experimental results show that the adaptive algorithms can strongly reduce average waiting times of cars compared to three hand-designed controllers.\",\"PeriodicalId\":296386,\"journal\":{\"name\":\"IEEE Intelligent Vehicles Symposium, 2004\",\"volume\":\"19 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-06-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"159\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Intelligent Vehicles Symposium, 2004\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IVS.2004.1336426\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Intelligent Vehicles Symposium, 2004","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IVS.2004.1336426","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Optimal traffic light control is a multi-agent decision problem, for which we propose to use reinforcement learning algorithms. Our algorithm learns the expected waiting times of cars for red and green lights at each intersection, and sets the traffic lights to green for the configuration maximizing individual car gains. For testing our adaptive traffic light controllers, we developed the green light district simulator. The experimental results show that the adaptive algorithms can strongly reduce average waiting times of cars compared to three hand-designed controllers.