Max Pumperla

@abhinav-upadhyay you're right, thanks. sorry for the late reply. To keep the book in sync with `master`, can you please re-submit your PR against our new `improvements` branch?

Hi @fuhaoda, thank you! I'm not entirely sure what you mean by "two layers" here, but let me try to explain. What you're trying to do is select the next...

@computer-idol I agree, our implementation isn't optimized for speed at all, rather for educational clarity (or so we hope). If you want to help implementing a parallel version, that'd be...

@jeffhgs thanks for your addition. Actually, we're completely aware of this. Two things: a) Chapter 5 is "optimized" for readability, aimed at beginners. I hope you see how your performance...

@jeffhgs new `improvements` branch in now live.

@rwideman thanks for your interest in our project! yeah, we've tried to make dlgo as general a framework as possible. If you, or anyone else, creates a Chess board encoder,...

@JingOY0610 thank you. ad 1) I'm not sure I understand your point. we need to pick the best performing move among the legal ones. what do you have in mind...

@JingOY0610 got it, you're right. thanks for spotting this - extremely helpful

@VideoPac a lot of things have changed in TF 2.x since we released the book, see what old version we were using back then: https://github.com/maxpumperla/deep_learning_and_the_game_of_go/blob/master/code/setup.py#L10 I think you should be...

@VideoPac thanks, good to hear you like the book! So this all boils down to multiprocessing issues in Windows, I'm afraid. As I do not have a Windows machine right...