Playing Flappy Bird via Asynchronous Advantage Actor Critic Algorithm
This is an incremental application of existing reinforcement learning algorithms to a popular game, with no broader implications beyond the domain.
The study tackled training an agent to play Flappy Bird using raw game images as input, a method not previously applied, and achieved successful learning through reinforcement with rewards and penalties.
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.