Lab — Kirsantov — Kirsantov


 ██╗      █████╗ ██████╗
 ██║     ██╔══██╗██╔══██╗
 ██║     ███████║██████╔╝
 ██║     ██╔══██║██╔══██╗
 ███████╗██║  ██║██████╔╝
 ╚══════╝╚═╝  ╚═╝╚═════╝
 Interactive Demos & Experiments

Playable demos showcasing algorithms, AI, and interactive learning

Click and explore. All demos run entirely in your browser.

🎮 MENACE — Learning Tic-Tac-Toe AI

Machine Educable Noughts And Crosses Engine

Featured

A 1960s AI experiment by Donald Michie. The AI starts knowing nothing and learns from every game using reinforcement learning with "matchbox beads." Watch it evolve from random moves to strategic play!

Features:

✓ Real-time brain visualization

✓ Persistent learning (IndexedDB)

✓ W/D/L statistics tracking

✓ Export/Import brain states

✓ Pure reinforcement learning

Tech Stack:

TypeScript - React - IndexedDB - Reinforcement Learning

-> Play MENACE

$ cat lab_philosophy.txt

The best way to understand something is to build it. The best way to learn something is to play with it. This lab is about: - Making complex concepts tangible - Learning through interaction - Showing, not just telling - Open source & educational

Want to see more demos? Have an idea for a visualization?

-> Let me know