I want to do this stuff too

Ok so I‘ve been watching a bunch of videos about people using reinforcement learning to teach their agents(?) to play games such as bowling or tag, but one that stood out to me was Yosh’s video on making an ai play the game trackmania, so I wanted to make a reinforcement learning algorithm to play Geometry Dash, since I feel like it shouldn’t be too hard, but I have no clue where to start, could anybody help/give me some pointers?