I had decided that I was going to write out in plain english how the AlphaGo Zero algorithm works. My plan is still to do that, but one big component of it is the critical Monte Carlo Tree Search algorithm. On the one had, my explanation was to gloss over that as a component of how the AI learns and does self-play, but on the other hand, it’s such an important part of how the whole thing works—not to mention an important algorithm to understand in general—that I’ve decided to start educating myself on that. I’m now reading about minmax algorithms, alpha-beta pruning and other techniques that seem to represent the state of the art in this sort of thing. Really enjoying it so far.