flappy-bird-gymnasium 0.1.2

A Gymnasium environment for the Flappy Bird game.

Flappy Bird for Gymnasium

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, by @sourabhv.

The two environments differ only on the type of observations they yield for the agents. The "FlappyBird-rgb-v0" environment, yields RGB-arrays (images) representing the game's screen. The "FlappyBird-v0" environment, on the other hand, yields simple numerical information about the game's state as observations. The yielded attributes are the:

• horizontal distance to the next pipe
• the next pipe's top vertical position
• the next pipe's bottom vertical position
• horizontal distance to the next next pipe
• the next next pipe's top vertical position
• the next next pipe's bottom vertical position
• player's vertical position
• player's vertical velocity
• player's rotation

         

Installation

To install flappy-bird-gymnasium, simply run the following command:

$ pip install flappy-bird-gymnasium

Usage

Like with other gymnasium environments, it's very easy to use flappy-bird-gymnasium. Simply import the package and create the environment with the make function. Take a look at the sample code below:

import time
import flappy_bird_gymnasium
import gymnasium
env = gymnasium.make("FlappyBird-v0")

obs, _ = env.reset()
while True:
    # Next action:
    # (feed the observation to your agent here)
    action = env.action_space.sample()

    # Processing:
    obs, reward, terminated, _, info = env.step(action)
    
    # Rendering the game:
    # (remove this two lines during training)
    env.render()
    time.sleep(1 / 30)  # FPS
    
    # Checking if the player is still alive
    if terminated:
        break

env.close()

Playing

To play the game (human mode), run the following command:

$ flappy_bird_gymnasium

To see a random agent playing, add an argument to the command:

$ flappy_bird_gymnasium --mode random