Haxle was a failure to launch, but not a failure at all. We learned a great deal about Pygame, coding physics engines, and using AI. Our plan was to create a side-view 2D racing game with a procedurally generated map, then use Tensorflow and Google Colab to train an AI that learns to drive along any generated track with ease. We had some stretch goals as well, but didn't quite get that far. As you can see in the video, Haxle isn't perfect, but our efforts led to an amazing experience and a whole lot of fun.

Built With

Share this project:

Updates