Show HN: Watch 14-Byte AI "brains" attempt to solve a 2D maze (Its hard)
A software developer shares their experiment in creating a 14-byte AI model capable of solving 2D mazes. The project highlights the use of local neighborhood observations rather than external memory or map data.
Why it matters
Demonstrates the potential for extreme model compression and efficiency in reinforcement learning tasks.
Hey HackerNews, I built this project over the last few weeks as a palette cleanser from a failed game launch. I wanted to learn a bit about AI/Neural-Networks and naively thought I could build a tiny maze-solving AI in a weekend with a 100% solve rate. Well - I couldn't, but I got pretty close. 14 Bytes total model size, and a 96.5% solve rate on unseen mazes. Trained across 46 phases experimenting with different ideas to improve the model (better performance, smaller size).
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in