典型文献
Research on virtual entity decision model for LVC tactical confrontation of army units
文献摘要：
According to the requirements of the live-virtual-con-structive(LVC)tactical confrontation(TC)on the virtual entity(VE)decision model of graded combat capability,diversified actions,real-time decision-making,and generalization for the enemy,the confrontation process is modeled as a zero-sum stochastic game(ZSG).By introducing the theory of dynamic re-lative power potential field,the problem of reward sparsity in the model can be solved.By reward shaping,the problem of credit assignment between agents can be solved.Based on the idea of meta-learning,an extensible multi-agent deep reinforcement learning(EMADRL)framework and solving method is proposed to improve the effectiveness and efficiency of model solving.Experiments show that the model meets the requirements well and the algorithm learning efficiency is high.
文献关键词：
中图分类号：
作者姓名：
GAO Ang;GUO Qisheng;DONG Zhiming;TANG Zaijiang;ZHANG Ziwei;FENG Qiqi
作者机构：
Military Exercise and Training Center,Army Academy of Armored Forces,Beijing 100072,China
文献出处：
引用格式：
[1]GAO Ang;GUO Qisheng;DONG Zhiming;TANG Zaijiang;ZHANG Ziwei;FENG Qiqi-.Research on virtual entity decision model for LVC tactical confrontation of army units)[J].系统工程与电子技术（英文版）,2022(05):1249-1267
A类：
army,EMADRL
B类：
Research,virtual,entity,decision,LVC,tactical,confrontation,units,According,requirements,live,structive,VE,graded,combat,capability,diversified,actions,real,making,generalization,enemy,process,modeled,zero,sum,stochastic,game,ZSG,By,introducing,theory,dynamic,lative,power,potential,field,problem,reward,sparsity,can,solved,shaping,credit,assignment,between,agents,Based,idea,meta,learning,extensible,multi,deep,reinforcement,framework,solving,method,proposed,improve,effectiveness,efficiency,Experiments,show,that,meets,well,algorithm,high
AB值：
0.584486
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
