Show HN: Watch a neural net learn to play Snake

(ppo.gradexp.xyz)

17 points | by c1b a day ago ago

3 comments

  • beardsciences 3 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.

  • simedw 42 minutes ago

    Cool project!

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

  • neduma 34 minutes ago

    More details and implementation notes please?