Show HN: Watch a neural net learn to play Snake (ppo.gradexp.xyz)
90 points by c1b a day ago
In browser PPO training demo, made possible by tinygrad: TinyJit -> WebGPU kernels.
Requires WebGPU.
simedw 5 hours ago
Cool project!
I noticed that if you go from training to watch and then back, the training temporarily drop significantly in score.
bguberfain 3 hours ago
It seems to be something related the moving average calculation. So it is just a glitch on the chart.
snats 2 hours ago
did a pretty similar thing last month for the text rendering library last month.
trained and made a viz for the model and then made it displace text.
should probably do a proper write-up:https://x.com/i/status/2038367016969724259
ldoughty 4 hours ago
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
c1b 2 hours ago
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.
r3trohack3r 3 hours ago
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.
mavdol04 an hour ago
That's cool, i did exactly the same few years ago
beardsciences 4 hours 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 5 hours ago
More details and implementation notes please?
LowLevelKernel 3 hours ago
Link to repo?
bozhark 2 hours ago
Crashed
jmclnx 3 hours ago
> WebGPU not available in this browser
Looks like this is for Linux and Windows, on NetBSD I get this issue :(
NoboruWataya 2 hours ago
I got this in Firefox on Linux, just had to enable WebGPU in about:config (`dom.webgpu.enabled` = true).
jmclnx 2 hours ago
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.
redshiftza 3 hours ago
If you are using brave (which i assume also applies to chrome) , there is a menu at brave://flags , you can enable unsafe web GPU from there
th1nhng0 4 hours ago
cool project
austinthetaco 4 hours ago
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.