Search found 386 matches

by brianr
Thu Apr 16, 2020 2:01 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Deepchess - neural network engine
Replies: 11
Views: 1497

Re: Deepchess - neural network engine

Yes.
I had tried to replicate the results and while I do not recall the details, it was disappointing.
by brianr
Thu Apr 16, 2020 1:12 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Deepchess - neural network engine
Replies: 11
Views: 1497

Re: Deepchess - neural network engine

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...
by brianr
Thu Apr 16, 2020 11:03 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Deepchess - neural network engine
Replies: 11
Views: 1497

Re: Deepchess - neural network engine

There have been major advances with NN engine development since this article came out.

Suggest starting here:

http://www.lczero.org/

And follow the links (the Github link to the repos, then Lc0, then to the Wiki), or jump to:

https://github.com/LeelaChessZero/lc0/wiki
by brianr
Mon Apr 06, 2020 12:52 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Using Freeware AI and Dynamically Generated Endgame Tablebases
Replies: 32
Views: 2849

Re: Using Freeware AI and Dynamically Generated Endgame Tablebases

Long answer: I don't think you appreciate how the nets learn, particularly the so-called "zero" approach. Zero here means almost no chess knowledge at all. The nets are not told what a bishop is, much less that two are better. Nobody, including the programmer, knows how many games/samples are enough...
by brianr
Thu Apr 02, 2020 1:30 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish Polyglot now violates the GPL
Replies: 23
Views: 3255

Re: Stockfish Polyglot now violates the GPL

I know next to nothing about GPL or any other licenses, but it took about 1 minute to find a copy of the polybook source. Here is one place:

https://github.com/massimilianogoi/Stockfish-Polyglot

It may not actually be part of SF, but an add-on.
by brianr
Tue Mar 24, 2020 4:37 pm
Forum: Computer Chess Club: General Topics
Topic: Issue with compilation of leela ver.0.24.x
Replies: 25
Views: 2159

Re: Issue with compilation of leela ver.0.24.x

Maybe there is no developer of Leela, who read TCM? Or from them lacks the readiness to help? My impression is that very few of the many helpful Leela devs read here, and then only occasionally. If you want help, suggest joining the Lc0 Discord server and asking in the #help channel, which is very ...
by brianr
Fri Mar 20, 2020 9:51 am
Forum: Computer Chess Club: General Topics
Topic: Is more dedicated memory to gaming chip better for Leela
Replies: 2
Views: 403

Re: Is more dedicated memory to gaming chip better for Leela

Short answer for game playing is no. Longer answer is that larger nets which need more GPU RAM will take longer on your GPU whereas smaller nets will see more nodes. You can experiment, but a lot will depend on time controls. Even very large 30x384 nets fit it 2GB but will be quite slow. See: https:...
by brianr
Thu Mar 19, 2020 1:14 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Poor mans testing process please
Replies: 30
Views: 3824

Re: Poor mans testing process please

Depending on the current strength of your engine, early changes that result in large improvements (hopefully) are relatively easy to test. As the engine gets stronger, it gets increasingly more difficult to measure smaller improvements. Fast time control games are helpful for search related changes ...
by brianr
Sun Mar 15, 2020 11:01 pm
Forum: Computer Chess Club: General Topics
Topic: Engine programming
Replies: 32
Views: 3083

Re: Engine programming

I would like to provide another albeit isolated data point suggesting that the language speed does not matter at first, and for quite some time afterwards either. Testing my engine Tinker vs Stockfish and giving SF a 1:200 time handicap begins to make Tinker somewhat competitive. This was long befor...