TalkChess.com

the general thinking was that "fancy" sorting does not pay as so much of the tree is pruned in the first place That holds only for the "pick the best of the remaining list and put it to the current place" sort, but not compared to sorting the whole move list up-front with an n^2 algo. All the moves...

You can search for old posts about this, but the general thinking was that "fancy" sorting does not pay as so much of the tree is pruned in the first place, and then the few times sorting is done, the number of moves is too small to offset the overhead of setting up the "smart" sort routines. It mig...

Crafty with just one thread should be deterministic.
More than one...

I was not even aware of Discord prior to Leela chess, and it does take some getting used to. If you want to keep an eye on what is happening with Lc0 it is by far the most active resource. The name is Leela Chess Zero and 425419482568196106 is the "server" ID, I think. I do recall supplying an email...

Everything needed should be part of the releases download. Here is a link to the cuda version that includes the cuda files. There is a separate one that says cuda-nodll if you already have the big files and only want the engine update. https://github.com/LeelaChessZero/lc0/releases/download/v0.24.1/...

This has been a recurring topic on the Leela chess Discord for a long time. The nets have been trained to win with no extra preference given to a shorter win. In the past this was characterized as Leela "trolling". Recently, a lot more attention has been focused on this area (MLH and other approache...

Yup. I think one of the earlier suggested links (Zeta36) has a Keras implementation. Lc0 is C++ for speed (playing games) and Python for training nets. The outputs (or heads) would be Value (result of the game W/D/L mapped to some numerical range), and Policy (which move to make; actually all moves ...

See

https://web.stanford.edu/~surag/posts/alphazero.html

and

https://www.amazon.com/Deep-Learning-Ga ... 1617295329

These are for Go, but the principals are the same.

Yes.
I had tried to replicate the results and while I do not recall the details, it was disappointing.

I would skip the old paper until you better understand neural net training generally. Typically people only build Lc0 if not on Windows. Yes, Lc0 is quite complicated for chess, but there are some more introductory level options. For a simpler approach you might start here. https://github.com/Zeta36...