详情

原文传递 Multi-Objective Approach to Tactical Maneuvering Within Real Time Strategy Games.

题名：	Multi-Objective Approach to Tactical Maneuvering Within Real Time Strategy Games.
作者：	Ball, C. D.
关键词：	Computer programs, Mathematical models, Models, Theses, United states government, Video games, Weapons, Data set, Simulations, Test and evaluation, Optimization, Training, Computers, United states, Algorithms, Evolutionary algorithms, Warfare, Air force, Artificial intelligence, Genetic algorithms, Tactical analysis, Rts(real time strategy), Moea(multiobjective evolutionary algorithms), Optimization
摘要：	The real time strategy (RTS) environment is a strong platform for simulating complex tactical problems. The overall research goal is to develop artificial intelligence (AI) RTS planning agents for military critical decision making education.This particular research effort of RTS AI development focuses on constructing a unique approach for tactical unit positioning within an RTS environment. By utilizing multiobjective evolutionary algorithms (MOEAs) for finding an optimal positioning solution, an AI agent can quickly determine an effective unit positioning solution with a fast, rapid response. The resulting agent does not require the usage of training or tree searches to optimize, allowing for consist effective performance across all scenarios against a variety of opposing tactical options.
报告类型：	科技报告