All tests run on an 8-year-old MacBook Air.

This is Part 3 of my series on training a card game AI with Google Colab.

Part 1: Google Colab basics

Part 2: Reinforcement learning + 200,000 episodes

In Part 2, I got the RL side working. The next challenge: feeding real game state into the model automatically. That meant recognizing cards from screenshots. I spent about two weeks on it. It didn't work. Here's exactly what happened.