Search found 22 matches

by Hrvoje Horvatic
Fri Oct 16, 2020 6:49 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Unsupervised reinforcement tuning from zero
Replies: 8
Views: 264

Re: Unsupervised reinforcement tuning from zero

Madeleine Birchfield wrote:
Fri Oct 16, 2020 5:07 pm

And so the only real difference between handcrafted evaluation and neural networks is handcrafted features discovered/implemented by humans vs automated feature discovery/implementation.
this is approximately true...

But it's a difference that makes the difference... a BIG difference...
by Hrvoje Horvatic
Fri Oct 16, 2020 3:51 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Unsupervised reinforcement tuning from zero
Replies: 8
Views: 264

Re: Unsupervised reinforcement tuning from zero

Is it possible to tune a handcrafted evaluation function whose values all start at zero using unsupervised reinforcement tuning? And if yes, how does this differ from training a neural network from zero using unsupervised reinforcement training? yes... it was done before, and it works... but you us...
by Hrvoje Horvatic
Sun Oct 11, 2020 9:17 pm
Forum: Computer Chess Club: General Topics
Topic: Stockfish 12 8 Cores vs Stockfish 12 16 Core Results.
Replies: 4
Views: 488

Re: Stockfish 12 8 Cores vs Stockfish 12 16 Core Results.

Leto wrote:
Sun Oct 11, 2020 4:55 pm
Practically no benefit in that result.
There IS a benefit, it shows something is "fishy"... (pun intended)
by Hrvoje Horvatic
Sat Oct 10, 2020 1:52 pm
Forum: Computer Chess Club: General Topics
Topic: Determining evaluation by a genetic algorithm
Replies: 5
Views: 261

Re: Determining evaluation by a genetic algorithm

Because of all the posts about NNUE, evaluation and related things in the last few weeks, I was thinking about something. Basically, an evaluation term is a fixed or calculated number that is added to the base value (or subtracted if the number is negative). We call such a number BISHOP_PAIR_BONUS,...
by Hrvoje Horvatic
Sat Oct 10, 2020 1:14 pm
Forum: Computer Chess Club: General Topics
Topic: Final Release of Ethereal, V12.75
Replies: 126
Views: 5637

Re: Final Release of Ethereal, V12.75

SF doesn't have a closed team of developers. Dozens of people have contributed to it, and the NNUE authors are among them. Perhaps we have a different understanding of what that means. Apparently we have, even though what I wrote is not very complex. I guess in your view 99% of Stockfish is not an ...
by Hrvoje Horvatic
Sat Oct 10, 2020 1:12 pm
Forum: Computer Chess Club: General Topics
Topic: Final Release of Ethereal, V12.75
Replies: 126
Views: 5637

Re: Final Release of Ethereal, V12.75

https://github.com/AndyGrant/Ethereal/tree/nnue Pushed NNUE support to a branch. You can load in a file. Stockfish weights are preferred. If anyone tests this for a rating list, it should be called "Ethereal 12.75 SF-NNUE". That branch actually works, unlike the Etherlito crap which broke due to me...
by Hrvoje Horvatic
Fri Oct 09, 2020 9:52 am
Forum: Computer Chess Club: General Topics
Topic: Final Release of Ethereal, V12.75
Replies: 126
Views: 5637

Re: Final Release of Ethereal, V12.75

I don't know if I'm ripping myself away from something I love for no reason. If I'm doing it because I see the pain in the future. If I'm doing it because I feel the pain now but am too daft to see the light at the end of the tunnel. I need someone to convince me that this hobby is still worth purs...
by Hrvoje Horvatic
Fri Oct 09, 2020 9:16 am
Forum: Computer Chess Club: General Topics
Topic: Final Release of Ethereal, V12.75
Replies: 126
Views: 5637

Re: Final Release of Ethereal, V12.75

Ethereal has one of the most readable, cleanest codebases out there... I enjoyed reading it... :) plenty of comments in code, too... it is not only one of the strongest engines, it's code is just beautiful... If I were to recommend to someone to clone/steal an engine codebase, it would be Ethereal.....
by Hrvoje Horvatic
Sun Mar 17, 2019 12:41 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Depth reduced but ELO increased
Replies: 3
Views: 1828

Re: Depth reduced but ELO increased

My analysis and testing have lead me to conclusion that countermove & follow-up history counters help with move ordering at all-nodes, because cut-nodes are already almost optimally ordered... what happens is that at all-nodes this history counters help with finding out new PV lines... because of su...
by Hrvoje Horvatic
Sat Mar 16, 2019 10:53 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Need MSVC with assembler file help
Replies: 24
Views: 3515

Re: Need MSVC with assembler file help

I am programming in both. Some functions like initialization functions and engine protocol functions are in C. Search functions will be in assembler. MSVC can compile both kind of files and link them. I know how to access non nested C structures from the .asm file. But nowhere shows me how to acces...