That’s a great intro! When can we expect the tic-tac-toe post? I have already read a few of these froze lake / maze solutions but there the environment is always the same after reset. I would love to learn how to use RL for solving a more dynamic environment with a bit of randomness in each round — like tic-tac-toe or a randomly generated maze or pac-man or something like that.

I hope I can find it here sometime soon :)