Controlling a Rigidbody Quadcopter using Control Theory and Reinforcement Learning
Controlling a 2D Quadcopter with Rigidbody Physics using Control Theory and Reinforcement Learning
The main environment consists of controlling the drone to hit as many balloons within a time limit against AI drones.
The currently implemented algorithms are:
An explanation of the environment and its agent is explained in this paper.
I also made a devlog about this project here:
I added another game where the drone follows the mouse to move snow around a snowglobe.
The games are available to try as a Python package.
Make sure you have Python installed on your computer. Then, in a terminal, run the following commands:
python -m pip install pip==21
pip install git+https://github.com/AlexandreSajus/Quadcopter-AI.git
If you want to run the balloon game:
python -m quadai
If you want to run the snowglobe game:
python -m quadai snowglobe