In recent years, the prevailing of application of Deep Reinforcement Learning have granted the traditional game AI training a brand-new perspective. Google’s Alpha Go agent might mark the beginning of the trend. While many 2D games have been researched for effective trained agent to gain extraordinary performance, Flappy Bird is among, perhaps, the most popular one that could demonstrate the effectiveness of trained AI. This research has successfully trained a efficient agent using Deep-Q network that could outperforms its human counterparts. Although previous trainings have also granted successful results, due to the optimization in the memory array to store previous states, the training time has been largely reduced, which is useful for future agent training optimization.