基于对策论的团队计算机生成角色任务分配方法

Team task allocation method for computer generated actor based on game theory

针对带有时间约束的、可以动态加入到环境中的复杂任务,建立了一种基于对策论的任务分配模型,并给出了一种任务分配方法。该方法中计算机生成角色(CGA)根据自身掌握的局部信息进行行为选择,并使用虚拟行动方法确保CGA快速学习到一个严格纯策略Nash平衡。仿真实验结果表明该方法是合理的,能够有效地解决动态任务的分配问题。

For the complex tasks with time constraints, which can dynamically be added to environment, a task allocation model based on game theory was established, and a task allocation method was proposed, which made Computer Generated Actor （CGA） be able to choose its actions according to the local information owned by itself, and ensured that CGA learned a strict pure strategy Nash equlilibrium quickly by using fictitious play method on behavior coordination. The simulation results show that this method is reasonable, and it can effectively solve the dynamic task allocation problem.