Mikhail Simin

@goshawk22 If you can get something generic working, I think it'll be great regardless of the implementation. I was trying using the native multiprocessing.

Think about it, @goshawk22 you could solve this for me  # 😭😭😭

Another drastically different approach would be to parallelize the part in Coach that compares a new network to a previous one ( https://github.com/suragnair/alpha-zero-general/blob/master/Coach.py#L111 ) Here we could, in parallel, create...

What is different about this file than the top-level pit file? Is there a way to make the top level file more configurable to keep it DRY?

This is definitely more DRY. I personally would've implemented it differently - keeping top level pit file as the main executable and generic, and have settings done per game. It...

Nice! yeah I like this a lot. Feel free to copy/paste my stuff from #185 , or if @suragnair wants -- merge this and I'll piggyback off of this after...

Feel free to submit a PR. It should look something like this: ```python def getGameEnded(self, board, player): # return 0 if not ended, 1 if player 1 won, -1 if...

Actually I'm referring to the parent Game class: https://github.com/suragnair/alpha-zero-general/blob/master/Game.py#L62-L72 ```python def getGameEnded(self, board, player): """ Input: board: current board player: current player (1 or -1) Returns: r: 0 if game...

I'd like to see some flexibility around scoring in general. I'm happy to submit a PR to allow: 1. Scoring values other than win 1 / lose 1 2. Scoring...

The main goal here is to provide a developer of a new game with an easy way to configure the learning layers. Some sort of abstraction layer where they could...