In this project, a working game of checkers is developed in Python, implementing a minimax AI and a reinforcement learning AI agent. The idea is that the RL agent can play against minimax to explore state space and learn best practices. After this initial training setup, we can utilize self learn to further optimize the performance of the RL agent.
I read trough the comments on Tim's video and saw you fixed the king bug, pretty nice and thank you for that! I'm actually using this program to have a robot playing as the AI but for that I need to know which of all the possible moves it took and have this in an variable that displays the row and col off that move. When i have that variable I can link this to points for the cobot. I can't figure out how to do this, I can only get the row/cols of all the possible moves it can take but not from the final best move.