What's up guys! Today I have created a AI using RL(Reinforcement Learning)
that plays Tic Tac Toe with you.

Using a Q-Network, we train the AI using the Adam optimizer and we train on 10,000 Episodes of alternaing between itself and the opponent (so X and O in tic tac toe) and then it saves it as a .pth file (so you can reload it in pytorch (not tensorflow))

Drop a comment below on what you think 🔥

Github link for my fellow nerds 🤓:
Link to github