BrainLearn

Discussion of anything and everything relating to chess playing software and machines.

Moderators: Harvey Williamson, Dann Corbit, hgm

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
amchess
Posts: 150
Joined: Tue Dec 05, 2017 1:42 pm

Re: BrainLearn

Post by amchess » Fri Oct 16, 2020 11:03 pm

abgursu wrote:
Fri Oct 16, 2020 8:05 pm
Why removing montecarlo?
Not well working in some guis and, in general, not fully mature.
Moreover, as demonstrated by the latest tcec, even on a gpu, MCTS is slower than classical alpha/beta.

abgursu
Posts: 22
Joined: Thu May 14, 2020 1:34 pm
Full name: Ahmet Burak Gursu

Re: BrainLearn

Post by abgursu » Sat Oct 17, 2020 4:57 am

amchess wrote:
Fri Oct 16, 2020 11:03 pm
abgursu wrote:
Fri Oct 16, 2020 8:05 pm
Why removing montecarlo?
Not well working in some guis and, in general, not fully mature.
Moreover, as demonstrated by the latest tcec, even on a gpu, MCTS is slower than classical alpha/beta.
But that was only an option. It was not the default. Some users like me wants to play with mcts, even if it's not the best. I believe you shouldn't remove montecarlo just because someone can't use it or lc's lost against stockfish.

carldaman
Posts: 2027
Joined: Sat Jun 02, 2012 12:13 am

Re: BrainLearn

Post by carldaman » Sat Oct 17, 2020 5:48 am

abgursu wrote:
Sat Oct 17, 2020 4:57 am
amchess wrote:
Fri Oct 16, 2020 11:03 pm
abgursu wrote:
Fri Oct 16, 2020 8:05 pm
Why removing montecarlo?
Not well working in some guis and, in general, not fully mature.
Moreover, as demonstrated by the latest tcec, even on a gpu, MCTS is slower than classical alpha/beta.
But that was only an option. It was not the default. Some users like me wants to play with mcts, even if it's not the best. I believe you shouldn't remove montecarlo just because someone can't use it or lc's lost against stockfish.
+1 I totally agree. Many of us use the engine for analysis and don't always care about the most Elo.

Leo
Posts: 990
Joined: Fri Sep 16, 2016 4:55 pm
Location: USA/Minnesota
Full name: Leo Anger

Re: BrainLearn

Post by Leo » Sat Oct 17, 2020 9:20 pm

Has anyone had good experiences with this engine learning and improving itself? I haven't.
Advanced Micro Devices fan.

amchess
Posts: 150
Joined: Tue Dec 05, 2017 1:42 pm

Re: BrainLearn

Post by amchess » Sat Dec 05, 2020 5:57 pm

https://github.com/amchess/BrainLearn/wiki/Tests
Image

An interesting result:
BrainLearnPro is BrainLearn opensource file + a bin experience file improved by a private application.
Stockfish uses probably the best ctg currently available.
The match has been run on a quadcore.
The demonstration, imho, nnue engines + learning can also ignore a book.

Pi4Chess
Posts: 50
Joined: Mon Nov 16, 2020 11:13 am
Full name: Manuel Rivera

Re: BrainLearn

Post by Pi4Chess » Sat Dec 05, 2020 6:16 pm

Interesting indeed. What was the size of the experience.bin ? :wink:

amchess
Posts: 150
Joined: Tue Dec 05, 2017 1:42 pm

Re: BrainLearn

Post by amchess » Sat Dec 05, 2020 9:23 pm

About 25MB for now.
The best would be to analyze all eco codes with Q-learning and standard learning + bin experience file improvement.
A complete rewrite of all opening theory...

Post Reply