Show HN: Watch a neural net learn to play Snake

Hacker News Top Tools

Summary

A web-based tool that visualizes a neural network (using PPO) learning to play Snake in real-time, with configurable parameters and 3D rendering.

In browser PPO training demo, made possible by tinygrad: TinyJit -&gt; WebGPU kernels.<p>Requires WebGPU.
Original Article
View Cached Full Text

Cached at: 05/15/26, 06:33 PM

# tinyppo-snake Source: [https://ppo.gradexp.xyz/](https://ppo.gradexp.xyz/) ## Environment Sample idle ## Trained\-policy roll\-outs 0·trained0 griddelay40ms parameterlive updateswaiting for first snapshot… Initializing 3D renderer… step \#— no tensor loaded ## Configure runs preset idle no runs yet

Similar Articles

Learning to play Minecraft with Video PreTraining

OpenAI Blog

OpenAI introduced Video PreTraining (VPT), a semi-supervised method that trains neural networks to play Minecraft by learning from 70,000 hours of unlabeled human gameplay video combined with a small labeled dataset. The model learns complex sequential tasks using the native human interface (keyboard and mouse) and demonstrates capabilities like crafting diamond tools and pillar jumping, representing progress toward general computer-using agents.