According to the requirements of the live-virtual-constructive(LVC)tactical confrontation(TC)on the virtual entity(VE)decision model of graded combat capability,diversified actions,real-time decision-making,and genera...According to the requirements of the live-virtual-constructive(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 relative 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.展开更多
The use of Live, Virtual and Constructive (LVC) simulations are increasingly being examined for potential analytical use particularly in test and evaluation. In addition to system-focused tests, LVC simulations provid...The use of Live, Virtual and Constructive (LVC) simulations are increasingly being examined for potential analytical use particularly in test and evaluation. In addition to system-focused tests, LVC simulations provide a mechanism for conducting joint mission testing and system of systems testing when fiscal and resource limitations prevent the accumulation of the necessary density and diversity of assets required for these complex and comprehensive tests. LVC simulations consist of a set of entities that interact with each other within a situated environment (i.e., world) each of which is represented by a mixture of computer-based models, real people and real physical assets. The physical assets often consist of geographically dispersed test assets which are interconnected by persistent networks and augmented by virtual and constructive entities to create the joint test environment under evaluation. LVC experiments are generally not statistically designed, but really should be. Experimental design methods are discussed followed by additional design considerations when planning experiments for LVC. Some useful experimental designs are proposed and a case study is presented to illustrate the benefits of using statistical experimental design methods for LVC experiments. The case study only covers the planning portion of experimental design. The results will be presented in a subsequent paper.展开更多
基金supported by the Military Scentific Research Project(41405030302,41401020301).
文摘According to the requirements of the live-virtual-constructive(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 relative 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.
文摘The use of Live, Virtual and Constructive (LVC) simulations are increasingly being examined for potential analytical use particularly in test and evaluation. In addition to system-focused tests, LVC simulations provide a mechanism for conducting joint mission testing and system of systems testing when fiscal and resource limitations prevent the accumulation of the necessary density and diversity of assets required for these complex and comprehensive tests. LVC simulations consist of a set of entities that interact with each other within a situated environment (i.e., world) each of which is represented by a mixture of computer-based models, real people and real physical assets. The physical assets often consist of geographically dispersed test assets which are interconnected by persistent networks and augmented by virtual and constructive entities to create the joint test environment under evaluation. LVC experiments are generally not statistically designed, but really should be. Experimental design methods are discussed followed by additional design considerations when planning experiments for LVC. Some useful experimental designs are proposed and a case study is presented to illustrate the benefits of using statistical experimental design methods for LVC experiments. The case study only covers the planning portion of experimental design. The results will be presented in a subsequent paper.
