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….

That didn’t take long. A mere day after my last post where I laid out my upcoming plans for my model, I’ve thrown them out the window. Instead, it’s time to stop futzing around with anything to do with my…

This weekend, I pushed a bunch of other stuff aside and managed to complete the game-play parallelization effort. It was definitely worth it. Before the refactoring, tensorflow was able to play about 3 games per second. Now it’s able to…