A computational-intelligence-based optimization of agents'initial positions in land combat simu

• 作 者: LEE Heow Pueh
• 机 构: Institute of High Performance Computing, Singapore 117528, Singapore,Department of Mechanical Engine
• 出 处: Progress in Natural Science
• 发表日期: 2003年08期
• 关键词: intelligence fitness positions combat absolutely radial machines perfectly optim

The optimization of agents’ initial properties enables agents to perform their assigned tasks more perfectly. This paperpresents an optimizing method using the combination of radial basis function (RBF) neural network and genetic algorithm (GA). In theland combat simulation, the method can ensure that the agents optimized defeat the agents not optimized absolutely. Compared with theoptimization based on support vector machines (SVM), the proposed method improves the efficiency more than twenty times, so it suitsthe cases where the speed as well as performance is required.

The optimization of agents’ initial properties enables agents to perform their assigned tasks more perfectly. This paper presents an optimizing method using the combination of radial basis function (RBF) neural network and genetic algorithms (GA). that the agents optimized defeat the agents not optimized absolutely. Compared with the optimization based on support vector machines (SVM), the proposed method improves the efficiency more than twenty times, so it suitcase cases where the speed as well as performance is required.