QuadroPong

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.

Cloning

$ git clone https://github.com/axe76/QuadroPong.git

Dependencies

$ pip3 install -r requirements.txt

Demonstration

For AI:

$ python3 neat_quadro_paddle.py

For Single Player:

$ python3 main.py

Authors

• Anirudh Rajiv Menon
• Unnikrishnan Menon

License

This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details