Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Watch a neural net learn to play Snake

ppo.gradexp.xyz

Post reply on HN
Print view View original

11–20 of 56 posts

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

#11

Post by r3trohack3r »

ldoughty wrote: post #8

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. avg500 -4.6 last 500 episodes peak 3959.3 best window roll/s 20.68 20-step avg progress 4388 562749 episodes

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.

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

#15

Post by jmclnx »

NoboruWataya wrote: post #14
jmclnx wrote: post #9

> WebGPU not available in this browser Looks like this is for Linux and Windows, on NetBSD I get this issue :(

I got this in Firefox on Linux, just had to enable WebGPU in about:config (`dom.webgpu.enabled` = true).

Did not know that existed, I enabled it but no luck. Must be a NetBSD thing based upon this new message:

> WebGPU is not yet available in Release or late Beta builds.

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

#19

Post by c1b »

ldoughty wrote: post #8

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. avg500 -4.6 last 500 episodes peak 3959.3 best window roll/s 20.68 20-step avg progress 4388 562749 episodes

Yes it just collapses eventually — never stabilizes. The training process is flawed, I suspect it has to do with the fact that some weights blow up over time, you can see in “weights” tab.

But at around 4K avg score you should see it solve the env almost every time.

Just a demo :) optimized for speed over stability.

Reward structure: Step: -1 Dot: +100 Win: +1000 so ~4k is max theoretical score on 6x6.

Post reply on HN