Show HN: Watch a neural net learn to play Snake

(ppo.gradexp.xyz)

26 points | by c1b 1 day ago

4 comments

  • simedw 1 hour ago
    Cool project!

    I noticed that if you go from training to watch and then back, the training temporarily drop significantly in score.

  • beardsciences 29 minutes ago
    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.
  • neduma 1 hour ago
    More details and implementation notes please?