Instructions
Flag = Run
Q or Stop sign = Stop
d = show debug
s = hide debug
hold mouse/press to view agent in real time
(shift click flag or on mobile on edit for turbo mode)
Notes & Credits
Since I am new to Reinforcment learning, let me know tips or mistakes about this project!
#00 Full of bugs
#01 Somewhat working
#02 Fully working and more optimized