2D Quadcopter

A game where you control a 2D Quadcopter to pop balloons or move snow around

The main game consists of controlling a quadcopter with the arrow keys to hit as many balloons within a time limit against AI controlled opponents. The opponents are:

• PID: Controller using Control Theory that uses the error between the drone position and the target position to calculate inputs
• DQN: Reinforcement Learning agent that trained itself on multiple episodes of the game, by testing different actions and learning from the rewards it gets.

I added another game mode where the drone follows the mouse to move snow around a snowglobe.

Tips For the Balloon game:

• Control your drone using the arrow keys
• The drone is very sensitive so tap the keys slowly
• Reach as many balloons as you can within the time limit

For the Snowglobe simulation:

• Control the drone using your mouse
• The drone's airflow will move the snow around

Disclaimer

• This "game" was originally intended to benchmark different AI algorithms
• The original project is available here
• I turned it into a game using pygame and pyinstaller but as you'll see this is not optimal (console as a menu, poor controls, huge filesize because of the machine learning libraries)
• I am not a game developer and I fully know that the game is far from perfect
• But I still hope you can find some fun in it!