This project uses NEAT algorithm to achieve competitive multiagent learning on a modified pong game environment. The algorithm defines a singular neuroevolutionary procedure to train all the agents simultaneously, such that optimal policy is achieved quickly.
$ git clone https://github.com/axe76/QuadroPong.git
$ pip3 install -r requirements.txt
For AI:
$ python3 neat_quadro_paddle.py
For Single Player:
$ python3 main.py
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details