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
Cool project!
I noticed that if you go from training to watch and then back, the training temporarily drop significantly in score.
A previous similar idea running as a Ratatui based TUI: https://github.com/bones-ai/rust-snake-ai-ratatui
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.gradexp.xyz/dist/size_6/manifest.j
Mesmerizing - could be its own digital art showcase XD Love what you've done here, friend. Looking forward to what you do next. <3
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
I noticed snake gets penalized for not getting to the apple early, is that what you really want? Snake is about how long it gets not about the balance between length and wall clock time
Here is how my LLM play snake : https://news.ycombinator.com/item?id=48167846
Poorly programmed, it doesn't learn from its mistakes, the games get stuck in a loop because the snake doesn't capture a piece but the piece remains and there's a gap, constantly moving the snake along the same path with negative scores in an infinite loop leaving an unaltered yin and yang ;) there's a repetitive pattern in these infinite games between the position of the gap and the piece
This is seriously impressive. Running PPO training directly in the browser through WebGPU feels like a glimpse into where lightweight AI experimentation is headed.
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.
Any plans to open-source the repo?
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.
More details and implementation notes please?
Give the neural network the sense of sight, to know where the point is located.
> WebGPU not available in this browser
Looks like this is for Linux and Windows, on NetBSD I get this issue :(
That's cool, i did exactly the same few years ago
sound cool; would like to show my kid for education; doesn't work on Mac/Safari though (no webGPU)
Very cool! Not GitHub repo?
Link to repo?
damn this was really interesting and really well executed
Will be open-sourced?
cool project
Crashed