For the Stanford science showcase project “Tic-Tac-Toe Box AI”, I built a mechanical computer out of boxes that, through reinforcement, learns to play Tic-Tac-Toe. The boxes represent each possible board configuration, and the user teaches the "computer" to play by rewarding/punishing good/bad moves using a series of

It is a fun introduction to reinforcement learning, and I've gained a lot of interest from using it in educational settings, especially with kids. However, as I'm moving out, I will no longer be able to keep it. Therefore, I'm donating it to anyone interested in using it for educational purposes or just as a design feature!

More information about the project: https://aliceheiman.xyz/menace.html

Please contact me if you want to take it over!