Search found 317 matches

by Raphexon
Wed Oct 21, 2020 9:45 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: How to scale stockfish NNUE score?
Replies: 13
Views: 638

Re: How to scale stockfish NNUE score?

I am always getting excited when you're trying to implement engines for games other but chess. I'm just wondering what motivates you? I mean usually people developing one engine for years and it's difficult to master chess programming at a decent level... But you're trying many other games! This is...
by Raphexon
Wed Oct 21, 2020 9:42 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: NNUE incredibly poor endgame performance
Replies: 10
Views: 328

Re: NNUE incredibly poor endgame performance

Simple mating is a search task. I wouldn't blame the evaluation not finding a mate. Andreas Mostly, but SF for example has some very simple heuristics to aid in finding the mate in such situations. (Like KRvK and KQvK endgames) And if you replace the whole eval with NNUE you also throw away those h...
by Raphexon
Thu Oct 15, 2020 2:07 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: The Inferno Thread, part II
Replies: 10
Views: 1478

Re: The Inferno Thread, part II

Thanks for the information, great to hear it's still being worked on.
Hope it all works out in the end.
by Raphexon
Thu Oct 15, 2020 11:08 am
Forum: Computer Chess Club: General Topics
Topic: 87% of the poll voted that SF will win Tcec Sufi 19.
Replies: 93
Views: 4388

Re: 87% of the poll voted that SF will win Tcec Sufi 19.

Laskos wrote:
Thu Oct 15, 2020 9:29 am
Glanced at the standing:

Sf destroys Leela 9:1 =36 pairs. Poor Leela.
Soon to be 10:1.
by Raphexon
Wed Oct 14, 2020 1:29 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: The Inferno Thread, part II
Replies: 10
Views: 1478

Re: The Inferno Thread, part II

Sorry for invading your thread, but is there a download available for Inferno?
by Raphexon
Wed Oct 14, 2020 6:07 am
Forum: Computer Chess Club: General Topics
Topic: Future of computer chess: 2 top engines?
Replies: 34
Views: 2324

Re: Future of computer chess: 2 top engines?

Yes, price per performance is clearly won by Stockfish NNUE I agree. On a 4 core system or a smartphone. And If this is all I had, Stockfish is the clearly winner. The question is if price and performance is not the only consideration, is Stockfish NNUE clearly the best. And that is still up for de...
by Raphexon
Tue Oct 13, 2020 9:53 am
Forum: Computer Chess Club: General Topics
Topic: Future of computer chess: 2 top engines?
Replies: 34
Views: 2324

Re: Future of computer chess: 2 top engines?

Komodo 11.2 is only 26 Elo points behind version 14, at CCRL 40/15. It was released on July 17, 2017. SF had been the clear number one for over a year, by the time Lc0 matured, and now it is again; this last T60 run has been rather disappointing, not to mention incredibly long. The main reason why ...
by Raphexon
Sat Oct 10, 2020 12:14 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Request for someone to train an NNUE for Ethereal
Replies: 12
Views: 771

Re: Request for someone to train an NNUE for Ethereal

Eth-NNUE does seem to be a lot slower than Cfish and SF.
Only 300 knps (from start) on 1 core is really low. SFnnue always did over double.
by Raphexon
Sat Oct 10, 2020 11:29 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Request for someone to train an NNUE for Ethereal
Replies: 12
Views: 771

Re: Request for someone to train an NNUE for Ethereal

I think my data generation should be just about complete. When I create a net with it, it will be a flip net though. Look at Noob's changes what to change to make it work: (not a lot btw) https://github.com/noobpwnftw/Stockfish/tree/flip Unlikely it will pass Fishtest so you can use it. I'll try a ...
by Raphexon
Fri Oct 09, 2020 9:51 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Request for someone to train an NNUE for Ethereal
Replies: 12
Views: 771

Re: Request for someone to train an NNUE for Ethereal

I think my data generation should be just about complete. When I create a net with it, it will be a flip net though. Look at Noob's changes what to change to make it work: (not a lot btw) https://github.com/noobpwnftw/Stockfish/tree/flip Unlikely it will pass Fishtest so you can use it. I'll try a f...