reinforcement learning is so interesting *added a reward tracker for fun :) ______________________________________ so INCREDIBLY basic u can barely call it AI lol reinforcement learning in its most basic form the goal follows your mouse, scratchcat will get there :) + reward = rewarded - reward = punishment right now if its getting closer at all its rewarded, but when it moves farther away it's punished. when it's punished it turns the most optimal way to be rewarded soonest. It is always testing to see the most optimal direction to get the highest reward.