My first reinforcement learning project: implementing and improving q-learning in my version of the atari snake game. Originally, the project was intended to be displayed in LED box as a collaborative project for S.P.A.C.E. and Science Fest at Dawson and supervized by the wonderful Joel Trudeau.
This is my first full project. I tried to do as much as I could myself without relying on tutorials. I only researched the basic theory behind q-learning, trying not to "spoil" possible improvements for my own problem solving.