Live data from Hacker News

Show HN: Watch a neural net learn to play Snake

ppo.gradexp.xyz

41–50 of 56 posts

Re: Show HN: Watch a neural net learn to play Snake

#41

FYI this website sets off a bunch of Bitdefender alerts as being a suspicious web page. I assume probably false positives or something but still something you might want to look into. "The page https://ppo.gradexp.xyz/ has been detected with suspicious activity. It is not recommended to continue browsing this website." Same for: https://ppo.gradexp.xyz/version.js https://ppo.gradexp.xyz/dist/sizes.js https://ppo.grad…

https://www.virustotal.com/gui/url/1ee8e72b55c296ee92f38937d...

Bitdefender here shows clean

Re: Show HN: Watch a neural net learn to play Snake

#45
post #39

Earlier quoted context omitted.

But if not the snake could go into an infinite loop, never growing, never eating.

Why? It should get the reward for getting longer, but not for getting longer quicker

Because the sessions would last forever. Think of a 1 or 2 length snake, figuring out that left down up right over and over again doesn't lose any points. You're now trapped in a local minimum. You need to make the AI get impatient (lose points) or it'll never learn.

Re: Show HN: Watch a neural net learn to play Snake

#48
post #39

Earlier quoted context omitted.

Why? It should get the reward for getting longer, but not for getting longer quicker

Because the sessions would last forever. Think of a 1 or 2 length snake, figuring out that left down up right over and over again doesn't lose any points. You're now trapped in a local minimum. You need to make the AI get impatient (lose points) or it'll never learn.

I see what you are saying but then wouldn’t it miss out on the best strategies, which do require patience and not going straight for the apple?

Re: Show HN: Watch a neural net learn to play Snake

#49
post #48

Earlier quoted context omitted.

Because the sessions would last forever. Think of a 1 or 2 length snake, figuring out that left down up right over and over again doesn't lose any points. You're now trapped in a local minimum. You need to make the AI get impatient (lose points) or it'll never learn.

I see what you are saying but then wouldn’t it miss out on the best strategies, which do require patience and not going straight for the apple?

Maybe you could make it lose points for repeating a board state, I guess.
Post reply on HN