Write an AI in Ruby that won’t lose in Tic-Tac-Toe

Machine Learning can be intimidating

What’s the news?

Implementing is always better than just reading

First of all, the problem domain

What’s the algorithm?

an agent interacts with environment and constructs his value function

The case of TicTacToe

Learning happens during the game

Let’s implement it

Conclusion

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade