使用异步优势演员评论算法播放Flappy Bird
Playing Flappy Bird via Asynchronous Advantage Actor Critic Algorithm
摘要：
拥有极高人气的Flappy Bird，经过了很多算法的训练。其中一些研究是从游戏的原始像素值和一些特定属性中训练的。在这项研究中，该模型使用了以前从未见过的原始游戏图像进行训练。经过训练的模型已经学习了什么时候做出什么决定。作为模型的输入，返回每个步骤结束时的奖励或惩罚，并完成训练。Flappy Bird游戏使用强化学习算法Deep Q-Network和Asynchronous Advantage Actor Critic（A3 C）算法进行训练。
英文摘要：
Flappy Bird, which has a very high popularity, has been trained in many algorithms. Some of these studies were trained from raw pixel values of game and some from specific attributes. In this study, the model was trained with raw game images, which had not been seen before. The trained model has learned as reinforcement when to make which decision. As an input to the model, the reward or penalty at the end of each step was returned and the training was completed. Flappy Bird game was trained with the Reinforcement Learning algorithm Deep Q-Network and Asynchronous Advantage Actor Critic (A3C) algorithms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
