文献类型：期刊文献

中文题名：Multiagent reinforcement learning with quantified information-decision content measurement

作者：Ershen WANG[1,2];Xiaotong WU[1];Chen HONG[3,4];Yanwen WANG[5];Aidong CHEN[3,4];Hongyuan JING[3,4];Song XU[1];Pingping QU[1]

第一作者：Ershen WANG

机构：[1]School of Electronic and Information Engineering,Shenyang Aerospace University,Shenyang 110136,China;[2]School of Civil and Aviation,Shenyang Aerospace University,Shenyang 110136,China;[3]Multi-Agent Systems Research Centre,Beijing Union University,Beijing 100101,China;[4]College of Robotics,Beijing Union University,Beijing 100101,China;[5]School of Computer Science and Engineering,Northeastern University,Shenyang 110169,China

第一机构：School of Electronic and Information Engineering,Shenyang Aerospace University,Shenyang 110136,China

年份：2025

卷号：68

期号：12

起止页码：285-286

中文期刊名：Science China(Information Sciences)

外文期刊名：中国科学(信息科学)(英文版)

基金：supported by National Key R&D Program of China (Grant No. 2018AAA0100804);National Natural Science Foundation of China (Grant No.62173237);Aeronautical Science Foundation of China (Grant No. 20240055054001);Open Fund of Key Laboratory of Technology and Equipment of Tianjin Urban Air Transportation System (Grant No. TJKL-UAM-202305);Joint Fund of Ministry of Natural Resources Key Laboratory of Spatiotemporal Perception and Intelligent Processing (Grant No. 232203);Applied Basic Research Programs of Liaoning Province (Grant No. 2025JH2/101300011)。

语种：英文

中文关键词：extensive local information;partially observable markov decision process;large scale multiagent systems;multiagent reinforcement learning;mathematical framework;simulate analyze agents decisionmaking process;partial observability;

摘要：In large-scale multiagent systems (MASs), partial observability poses a notable challenge. When agents process extensive local information, global information scarcity, and high computation complexity arise [1]. To address the partial observability, researchers have adopted the partially observable Markov decision process (POMDP) as a mathematical framework to simulate and analyze agents’ decisionmaking process.