{"title":"Scaling Up Multi-agent Reinforcement Learning in Complex Domains","authors":"D. Xiao, A. Tan","doi":"10.1109/WIIAT.2008.259","DOIUrl":null,"url":null,"abstract":"TD-FALCON (temporal difference-fusion architecture for learning, cognition, and navigation) is a class of self-organizing neural networks that incorporates temporal difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neighboring-agent mechanism, to further improve the learning efficiency of TD-FALCON in complex multi-agent domains. Through experiments on a traffic control problem domain and the herding task, we demonstrate that those strategies enable TD-FALCON to remain functional and adaptable in complex multi-agent domains.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WIIAT.2008.259","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
TD-FALCON (temporal difference-fusion architecture for learning, cognition, and navigation) is a class of self-organizing neural networks that incorporates temporal difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neighboring-agent mechanism, to further improve the learning efficiency of TD-FALCON in complex multi-agent domains. Through experiments on a traffic control problem domain and the herding task, we demonstrate that those strategies enable TD-FALCON to remain functional and adaptable in complex multi-agent domains.