This repository contains the implementation of two OpenAI Gym environments for the Flappy Bird game. The implementation of the game's logic and graphics was based on the FlapPyBird project.
pygame.window.2021-06-09.15-42-46.mp4
To check the performance and visualize the agent uncomment the agent.perform() and comment the agent.train() in the flappy.py file.
if __name__ == '__main__':
agent = DQNAgent()
#agent.train()
agent.perform()
For train the agent uncomment the agent.train() in the .py file.
if name == 'main':
agent = DQNAgent()
agent.train()
#agent.perform()
- flappy-bird-gym
- numpy
- tensorflow