Application and Comparison of Particle Swarm Optimization and Genetic Algorithm in Strategy Defense Game

Particle swarm optimization (PSO) is similar to genetic algorithm (GA) but employs different strategies and computational effort. Strategic defense military games require a high degree of coordination among the characters and thus are suitable to test the performance of algorithms. In this paper, we design a scenario of tower defense game and compare the performance of PSO and GA in terms of the damage value (fitness) and the convergence speed. The comparative analysis shows the similar optimum cannon placement is obtained using PSO and GA with similar effectiveness. In addition, the results of execution time (>80 seconds) indicate that the single implement of PSO or GA is unsatisfied for real time strategy (RTS) games.