Really cool! But right as it was nearing 4,000, it seems to have corrupted itself and no longer got any scores above 0. Not sure if that's a code bug or a neural net issue.
I think I noticed it reach “end game.” The snake reaches a point where, if it gets any longer, it is out of squares and hits its own tail. So it finds the route through the squares that it can infinitely loop, never eats the ball, and score starts dropping and goes negative.
My average eventually made it to about 3900, and then stagnated between 3600-3900. I'm curious if this is universal behavior or not. I'm up to about 5k steps.
my training on a 10x10 just randomly broke. i got to like 3600 then the graph went flat, the viewer on the left just showed it constantly restarting the game, and the scores in the negative. my average is now -10.
I noticed that if you go from training to watch and then back, the training temporarily drop significantly in score.
avg500 -4.6 last 500 episodes
peak 3959.3 best window
roll/s 20.68 20-step avg
progress 4388 562749 episodes
Looks like this is for Linux and Windows, on NetBSD I get this issue :(